User Guides

The Projects page is your hub for organizing bioprocess work around a shared objective. A project groups related runs, reports, and team members so you can track progress against goals and keep context in one place.

Projects list

The project list gives an overview of every project in your organization, grouped by status: Active, Paused, and Complete. Each row shows the project name, number of linked runs and reports, goal progress, target date, members, and last update.

Click any project to open its detail page. Use the New project button to start a new project from scratch. Until the first project exists, the page shows No projects yet with a View runs shortcut to the Runs directory.

Creating a project

New project opens the Start a project dialog. Give the project a name — names must be unique, and a duplicate is rejected — and answer What is your objective?. Assist grounds every conversation in the project in the objective you write, so a clear description improves later analysis. Click Create project to finish.

Project detail page

A project detail page is organized into four tabs: Overview, Runs, Reports, and Activity.

Overview

The Overview tab contains an Objective field, a Goals list, an optional Background field, Attachments, and a right-hand sidebar with properties, progress, data quality, and recent reports.

The Objective field describes what the project is trying to achieve. The Background field can hold additional context such as prior results or experimental rationale. Both fields are auto-saved.

The Goals section lists measurable criteria for the project. Click a goal's status icon to cycle it through Met, At risk, and Not met. Each goal also has an edit icon to change its text and a trash icon to remove it. Use Add goal to add a new one. If your organization has AI Assist enabled, goal suggestions from Assist appear under the list, and you accept or dismiss each one individually.

Use the Add files button to attach supporting documents such as protocols, SOPs, or slide decks to the project. Click an attachment to open it, or hover and click the trash icon to remove it.

The right-hand sidebar contains Properties, Progress, Data quality, and Recent reports. Properties lets you set the project's Start date, Target date, Status, and Members. Progress summarizes the goals: how many of the total are met, and how many are at risk. Recent reports lists the most recently updated linked reports; View all opens the Reports tab. Data quality shows a FAIR score scoped to the project's runs, broken down into Findable, Accessible, Interoperable, and Reusable pillars. Click Review to open the Data Quality page filtered to the project's runs.

Runs

The Runs tab lists every run linked to the project. You can filter, search, group, and sort the table the same way as the main Runs directory, and save your current table configuration as a view using the saved-view control next to the filter — reset unsaved changes, save them, or save them as a new view. Use Table to change which columns are shown and how the table is laid out. Select runs and click Analyze to open the selected data in the Analysis page.

Use Edit selection to add or remove runs from the project. This opens the run selection drawer so you can adjust the project's scope. When assigning runs to a project from the Runs directory, you can also create a new project directly from the project picker.

Reports

The Reports tab shows reports linked to the project, and can be sorted by title, last modified, or owner. Use Add reports to link an existing report, or click a report row to open it. Open a report's actions menu (⋮) and choose Remove from project to unlink it. A report can also be linked to a project from the actions menu on the report itself. Guest users can open the linked reports, but cannot add or remove them.

Activity

The Activity tab is a reverse-chronological feed of the project's history: creation, objective and status changes, goal status changes, runs added or removed, reports linked or unlinked, attachments added or removed, and Assist activity such as generated summaries and accepted or dismissed suggestions. Each entry shows who made the change and when, and Assist entries link to the session with View session. Use Show more at the end of the feed to load older entries.

AI-generated summaries and goal suggestions

If your organization has AI Assist enabled, the Overview tab starts with an Invert summary written by Assist from the project's runs and goals. View session opens the Assist session behind it. Use the Regenerate menu next to the project tabs to regenerate the Invert summary or the Goal suggestions.

Archiving a project

To archive a project, open the actions menu (⋮) in the project header and choose Archive, then confirm in the Archive project? dialog. An archived project is removed from the Projects page and its detail page is no longer available — opening an old link reports Project not found. The runs and reports that were linked to it are not changed, and remain in the Runs and Reports directories.

Related guides

• Runs
• Reports
• Data Quality
• Assist

The Experiments page allows you to manage experiments in Invert. From here, you can review past and ongoing experiments in either List or Schedule view. Create a new experiment as necessary or navigate to a given experiment details page for a close-up view on a specific experiment.

Creating a New Experiment

To create a new experiment, click the New Experiment button. This action directs you to the 'New experiment' view, where you enter the experiment Name and set Responsible, Scheduled Start Time, and Expected End Time. Click Save to create the experiment; it then appears in the experiment list on the Experiments page.

Runs are added after the experiment exists: open the experiment, go to the Runs tab, and use Add → Add runs.

Experiment list

The List view gives you an overview of all your experiments whether past, ongoing or future, with a column for the experiment, its scheduled start, its scheduled end, and the number of runs it contains. Use Filter... to narrow the view by Start Date or End Date.

The Schedule view shows the same experiments as bars on a timeline, with the run count and duration next to each name. Choose the time span from the Week, Month, Quarter, or Year dropdown and press Today to bring the timeline back to the current date. An experiment that falls outside the visible dates shows an arrow button on its row; press it to move the timeline to that experiment.

Clicking on an experiment in either view will direct you to the respective experiment page.

The experiment page

The experiment page has a Properties tab with the experiment metadata, and a Runs tab with the runs in the experiment. On the Runs tab, use Edit to change run values directly in the table and Save to commit them, and use the display control to group by a column or change which columns are shown. Use Edit on the Properties tab to change the name, responsible, or scheduled dates. The same edit view holds the rename and Archive actions; archiving an experiment asks whether to archive its sub-runs as well.

Experiment Summary Dashboard

For organizations with the Experiment Summary feature enabled, the experiment page opens on a Summary tab. This tab aggregates all runs in the experiment:

• A header with the number of Runs, the run Types, the Duration (days), and Run progress
• Insights — key metric comparisons across the runs
• Run Overview — run status and condition-level groupings at a glance
• Process lineage — how the runs in the experiment connect
• A sidebar with the Experiment objective and an Overview narrative, plus Status, Lead, Initiated, Completed, and Duration

The narrative sections are generated by AI and should be reviewed for accuracy. Press Generate to create the overview for an experiment that has none, the edit icon to change the text by hand, and Regenerate to rebuild selected sections after the underlying run data changes.

The Import page is your gateway for bringing data into the app. It is organized into two tabs: File for uploading data from local files, and Integrations for viewing hardware and software connections that push data into Invert automatically. The History button in the top right corner opens the import history for the tab you are on.

File Tab

This is the primary method for uploading bioprocess data from files. Pick a file, choose a mapping, and press Start import to initiate ingestion.

• Step 1: File Picker

  Select one or more files from your computer using the file picker. Supported file extensions are .csv, .xls, .xlsx, .xlsm, .json, .parquet, .lcd, and .dino. Not every mapping supports every file type; if the selected mapping cannot read the file, the page reports it before the import starts. You can upload multiple files at once, as long as they use the same mapping. It is recommended to carefully review files before ingestion to avoid importing faulty data.

  

• Step 2: Mapping Picker

  Select the mapping that best fits your data structure. Mappings are available for run data, timeseries data, run events, and Invert export files; your organization can also have custom mappings. Custom mappings can be added to the list upon request. When a mapping has an example, the page shows Example (partial) data below the picker, with Download template to get a blank file in the expected structure. Refer to the Mapping Guide below for more information on a particular mapping.

  When you upload a file, Invert will automatically suggest a mapping if it can infer the format from your file's structure. Accept the suggestion with Apply mapping or dismiss it to choose manually.

  

• Step 3: Settings (Timeseries Data Only)

  When importing timeseries data, set Timeseries Import Mode to either Merge or Replace. Choose Merge to update an existing dataset by either overwriting or appending data. Alternatively, select Replace to discard the existing timeseries data for the imported metrics on the selected runs and replace it entirely with the imported data.

  Mappings that use relative time convert the time column into absolute time at ingestion, based on the current run start time. If you change the run start time later, re-import the data.

• Step 4: Start Import

  Click Start import to initiate file ingestion. This will direct you to the Importing page where you can review Import details for more information on ingestion status. Depending on the file size, file ingestion may take up to several minutes to complete.

• Step 5: Ingestion Evaluation

  • Step 5.1: Successful File Uploads

    Upon file ingestion, ensure data imported into Invert meet your expectations. The page has a tab per data type created by the import — for example Runs, Metrics, Events, or Material Streams — for a comprehensive overview of the imported data. The Import details sidebar gives who initiated the import (with Via Assist when Assist staged it), the mapping used, the timeseries mode, the status, the counts per data type, and a download link for the source file. Use Analyze in the top right corner to start a new report from the imported data. Consider editing and re-uploading files to update or replace data inside the app as needed.

    

  • Step 5.2: Failed ingestion attempts

    Failed file ingestions may occur if the source file contains unexpected or incomplete data, or if the file structure is not supported by the selected mapping. Consult the error log on the Importing page for details and verify the file meets the mapping criteria. For organizations with Assist enabled, use Fix with Assist on the failed import to diagnose the failure and stage a corrected ingestion for your review. Contact Invert support via Help & Support if you need further assistance.

Ingestion Preview

Ingestion Preview lets you see exactly what will be imported before any data is committed. Use the Preview before import toggle to turn it on or off; it is on by default. Preview applies to single-file uploads only — if you select more than one file, the import starts without a preview.

Invert processes the file and shows a structured summary of what would be created, organized into tabs (Runs, Library, Timeseries, Events, and, where the file contains them, Lineage, Samples, and Measurements) so you can catch mapping issues or unexpected data before they land in your workspace. Each tab name shows a count of items, and tabs with zero items are grayed out and non-clickable. The Library tab lists the unique metrics and properties detected in the file so you can verify nomenclature before approval. Click Complete import to proceed with the actual import, Dismiss to discard the preview without importing anything, or go back to adjust the file or mapping.

The preview is based on the previewed file only. If other files are processed at the same time, the final result can differ.

Mapping Guide

• Run Data
  • Description: Metadata associated with a run
  • Example: LOT#, Reactor ID, Site, Operator
  • Mapping: 'Run Data'
    • Required Columns:
      • Run
      • Metric A (unit)
    • Recommended Columns:
      • Experiment
• Timeseries Data
  • Description: Time-based metrics
  • Example: Time (h) versus Temperature (**°**C)
  • Mapping:
    • Timeseries Data (absolute time)
      • Required Columns:
        • Run
        • Timestamp
        • Metric A (unit)
    • Timeseries Data (relative time)
      • Required Columns:
        • Run
        • Time (h) or Time (min)
        • Metric A (unit)
• Run Events
  • Description: Notes associated with a run.
  • Example: Reactor Foaming @ 24h EFT
  • Mapping:
    • Run Events (absolute time)
      • Required Columns:
        • Run
        • Timestamp
        • Event Type
    • Run Events (relative time)
      • Required Columns:
        • Run
        • Time (h) or Time (min)
        • Event Type
• Invert Data
  • Description: Import data from an Invert export file
  • Example: Time (h) versus Temperature (**°**C)
  • Mapping:
    • Invert Data
      • Required Columns:
        • Export file structure generated by Invert

Integrations Tab

The Integrations tab lists all configured data sources for your organization — hardware agents, ELN connections, and other automated data streams. Each card gives the data source name, the date of the latest import, a Live pill while an ingestion is in progress, a Failed badge when the last ingestion failed, and a Manual badge for sources that are fed by file upload. Clicking a data source opens its detail page where you can review the connection configuration and its ingestion activity. Connectors opens the connector overview for your organization.

Import History

Navigate to the Import History page for an overview of all historical file ingestions. Use the Manual and Integrations toggle to switch between file uploads and integration ingestions. The list gives the source data file, the mapping used, when the import was created, who created it, and its status; imports staged by Assist are marked Via Assist and imports created by an Automation are marked Via Automation. Select View on an entry to open the import, where you can see the runs and metrics created and download the original source file.

Use the filters above the list to narrow it down by mapping, source data file name, who created the import, creation date, or status.

The Runs directory is your hub for managing all your bioprocess runs. Here, you can view, filter, group, and sort your runs in a table format. Whether it's shake flask, bioreactor or any other type of run, this page helps you keep track of your data and serves as a starting point for your analysis.

Get Started

Begin by exploring your runs in the run directory. Use the filtering option to tailor your view to include relevant runs for your analysis. Customize the layout by adding or removing columns. Select runs for bulk editing or timeseries analysis.

Key Features

• Filtering: Narrow down your view by applying filters based on different attributes like experiment, organism type, or any other relevant metadata associated with your runs.

• Sort: Sort your runs alphabetically in ascending or descending order depending on your needs. Click on the arrow down icon inside any of the column headers and select 'Sort A to Z' or 'Sort Z to A'.

• Grouping: Group your runs by specific criteria for a clearer overview. Choose from options like operator, site, strain, or any other run property from the list. Bulk select grouped runs by clicking the checkbox next to the group label.

• Table Layout: Tailor your run directory view by adding or removing columns. Change the column order by dragging-and-dropping. Take advantage of the 'Add Similarities'/'Add differences' feature to quickly compare run data across highlighted runs. DSP-enabled organizations also get a By Run & Streams view for comparing each unit operation with its material streams; see the Downstream Processing guide.

  

• Saved Views: Save your run directory configuration for a more streamlined and reproducible data analysis experience. Apply filter settings and adjust the table layout followed by pressing 'Save'. Select a view from the dropdown to restore a previously built configuration. Views can be shared with teammates via the 'Share' option in the view dropdown, which copies a direct URL to the current view.

  

• Aggregations and Units: Choose between a variety of aggregation settings for timeseries metrics (e.g. Mean, Last, Maximum, Minimum, etc.). Use the built-in unit conversion tool to quickly change between available unit options (e.g. mL/min to L/h).

• Search: Use the search feature to quickly identify relevant runs in the current run directory view. Search for run names or any other metric entry, like NH4OH or Process development.

• Experiment planning: Take advantage of the 'Status' property to organize runs by its status. Use the 'Status' filter and select 'Completed', 'In-progress', 'Scheduled' or any of the other options to further customize your view.

• Quick access to Summary page: Runs and Experiments are clickable entities, allowing you to quickly access the associated Summary page for detailed information related to a particular entry.

• Editing: Select a run and make edits to its associated metadata. Use our bulk editing feature to streamline editing across multiple runs simultaneously. Use shift-click feature for quickly highlighting multiple cells.

• Run merging: To merge two or more runs into a single run, select the relevant runs and click the 'merge' button accessible through the dropdown menu in top right corner. Choose the run to keep and proceed with the run merge.

• Export: Select one or more runs and click 'Export' to open the Full Data Export page. Choose which timeseries metrics and run metadata columns to include, then download a structured Excel file containing all selected data.

• Transfer to Analysis: Choose a specific run or a selection of runs to carry forward to the Analysis page. This allows you to create line, scatter, or bar charts based on the selected data for deeper insights and visualization. You have the option to save the analysis as a sharable report.

The Library page allows you to explore and manage the key components of your bioprocess data analysis: metrics, properties, unit operations, and event types. You can easily add, remove, or modify library entries either through the user interface (UI) or by importing files. The page is organized into tabs: Alerts, Event Types, Mappings, Metrics, Properties, and Unit Operations.

• Metrics are entities representing time-based data with a distinct x and y value pairs for each data point. Example: Online pH time course signal coming from a bioreactor, or offline product titer concentration time course.
• Properties are single value entities typically considered as meta data providing additional context to a run or experiment. Supported data types are numeric, text, date, among others. Examples: 'Host Organism' with a value 'E. coli' or 'Bioreactor size (L)' and '200'.
• Unit Operations are process steps within a run or experiment that group together related metrics and properties for a specific stage of work.
• Both metrics or properties can be used as formula inputs. Depending on how the formula is configured, formulas may qualify as a metric or property. Examples: A time series aggregation function converts a time series metric into a property (e.g. Maximum(pH) = 7.9) whereas multiplying a metric with a property results in a metric (e.g. Metric[Feed delivery volume (L)] x Property [Feed concentration (g/L)] = Metric[Substrate delivery mass (g)]).
• Parent metrics organize and consolidate data streams into groups. This is recommended because bioprocess hardware and data stream tag names can vary widely. Additionally, this enables Invert based formulas to be grouped with pre-calculated data streams from your hardware. For example, use 'Temperature (°C)' parent metric to bundle 'TP001 (°C)', 'Temp (°C)', and 'T_PV (°C)'.

Navigation

Move between Library sections using the breadcrumb dropdown in the top left. Click the current section name (e.g. "Metrics ▾") to switch between Alerts, Event Types, Mappings, Metrics, Properties, and Unit Operations:

Metrics

The Metrics tab provides an exhaustive list of all timeseries metrics currently in Invert. This list includes time series data uploaded by the user or hardware agent - as well as formula-derived time series data. Click any entry to open a sidebar panel with additional information and inline editing options.

Properties

On the Properties tab, you'll find a collection of single-value properties. Similar to the Metrics tab, this tab presents entries in a table layout. Click any entry to open the sidebar panel for viewing and editing.

Unit Operations

On the Unit Operations tab you'll find a collection of process steps. Similar to the Properties tab, this tab presents entries in a table layout. Click any entry to open the sidebar panel for viewing and editing.

Event Types

The Event Types tab lists all event categories and types defined for your organization. Event types are used when annotating runs on the Analysis page or the Run Summary Events tab. You can view and manage the available event categories (such as Critical Operations, Additions / Removals, and Observations) and the specific types within each category from this tab.

Mappings

The Mappings tab lists the ingestion mappings available to your organization — the templates that describe how an uploaded file is translated into runs, metrics, properties, and events. Each entry shows the file types it supports and, in the Created by column, whether the mapping is provided by Invert or which team member created it. You can filter the list by file type or by whether a mapping is managed by Invert or custom to your organization.

Click a mapping to open its sidebar panel, where you can edit its name and description, jump to the imports that used it via 'View related imports', or archive it. Mappings managed by Invert are marked with a lock and cannot be edited or archived.

Alerts

The Alerts tab gives a read-only overview of the process alerts defined across your organization's runs. Each entry shows the run the alert belongs to, the metric or property it watches, its condition, and whether it is enabled. Click the run link to open that run's Alerts tab, where alerts are created and managed — see the Run Summary guide.

Skills live on the dedicated Skills page under Assist in the sidebar — see the Skills article.

Key Features

• Data Sources
  • Data Sources column provides insights into the origin of a metric or property. The displayed value is automatically generated and cannot be changed by the user. Example: Time series metric 'Aeration' uploaded via file ingestion - mapping name is used for Data Source value. Similarly, metrics imported via hardware or ELN Integration will automatically derive their label from the respective ingestion agent. Metrics and properties can have multiple Data Sources labels.

• Adding a new metric
  • Create a new metric by clicking the 'Add' button on the 'Metric' tab. Enter a metric name and adjust metric properties as needed. The newly created metric will show in the metric table view.
• Archiving a Sub or Parent metric
  • To archive a metric or parent metric from the library, click on the metric name to open its sidebar panel. Then, open the kebab (⋮) menu in the top right corner and select 'Archive...' to remove the metric. The same kebab-menu pattern is used to archive an individual property, formula, or unit operation type from its sidebar panel.
• Bulk archive
  • Select multiple rows in the Metrics, Properties, or Unit Operations tab using the row checkboxes, then choose 'Archive' from the table's kebab (⋮) menu to archive them all at once. The bulk archive modal lists each item, flags any that are blocked by associated runs or formulas, and lets you proceed with the archivable subset.
• Show Related
  • In the sidebar panel of a metric, property, formula, unit operation type, or event type, the kebab (⋮) menu in the top right corner exposes 'Show related runs' and 'Show related reports' shortcuts. These open the Runs or Reports directory pre-filtered to entries that reference the entity you came from.

Bundling 'Sub metrics' into 'Parent metric'

• Bundle one or multiple sub metrics into a parent metric to streamline metric management across bioreactor platforms. Select relevant sub metrics and click 'Change Parent'. In the modal, select 'Add new parent' from the dropdown and confirm with 'Change Parent'. Specify name and display unit - optionally you can update the sub metric list as needed. Once saved, you may select runs and transfer to analysis page or wait until 'State' updates to 'Ready'. Sub metric<>Parent metric relationships are reversible. Parent metrics can be archived and recreated at any point in time.

Expand the dependency tree to full screen using the expand icon in the upper-right corner of the tree panel:

Updating Units

• You can update the unit associated with a metric from the sidebar panel, either by updating the Default Display Unit or Default Ingestion Unit (see Metric Property Guide). Click the metric name in the table to open the sidebar panel and modify the unit directly. Press 'Save' when done.

Adding a Formula

• You can calculate derived-quantities in a streamlined and automated fashion using Invert's formula feature. Formula use cases include KPIs (e.g. Yield, Productivity), mass balance (e.g. reactor volume over time) or signal noise reduction (e.g. moving average). Refer to the 'How to use Formulas?' info box for more information on supported mathematical operations. Formulas accept both properties and metrics as input variables. Depending on the formula configuration, the formula output could either be a time series metric or a single-value property.
  • Example: f(x) = centered_moving_average(DO) = Timeseries metric
  • Example: f(x) = last(Product titer) = Single-value property
• Assist can be launched from the formula create and edit panels to help write or adjust a formula, including its dependencies and expression.
• Once a formula is configured, Invert automatically calculate results for runs that meets the formula criteria. Formula calculation triggered upon file ingestion or after changing the formula configuration via the formula sidebar panel.

Adding a Constant into an existing Formula

• Enter a formula name and set your dependencies. Press 'Add constant' and pick a constant from the list or create a new constant. Ensure the units of the constants is compatible with the mathematical operation. Proceed with formula creation.

Adding Notes

• You can annotate metrics by adding a note. Notes are accessible from Line charts via tool tip hover. Open the metric sidebar panel and update the 'Notes' section, then press 'Save' when done.

Dependency Tree

• The sidebar panel for any metric, property, or formula includes a Dependency Tree section that visualizes how the item connects to other items in the library. The collapsed view shows direct inputs (upstream) and formulas that consume the current item (downstream). Click the expand button (⤡) to open a full-screen modal with the complete dependency chain — pan, zoom, and click any node to navigate directly to that item's sidebar panel.

Metric & Property Sidebar Panel - User Guide

Name

Description: Name of the metric

Impact: Changing the value will update the metric name.

Example: Oxygen Uptake Rate or Final OD.

Type (Property only)

Description: Indicates the metric data type is timeseries data or run data.

Impact: Changing the data type has implications on the types of analysis the metric can be used for. For instance, only numeric metrics can be used for formulas.

Example: Number, Text, Timeseries, Date, etc.

Default Display Unit

Description: Default unit in which the metric is displayed across the app.

Impact: Changing default display unit converts the metric value into a different unit in accordance with the base unit when displayed in Invert. The value is not altered.

Example: mg/L or g/L

Base Unit

Description: The SI unit in which the metric is stored inside the app.

Impact: Unit conversions and other unit related features require metric units to be unambiguous and defined so that it can be stored in SI unit. E.g. Yield in 'g product/g biomass' should be represented as 'g/g' (kg/kg in SI Unit).

Example: K or kg/m^3

Molar mass

Description: The molar mass of the substance associated with a metric, used to enable molar unit conversions.

Impact: When set, Invert can convert between mass-based and molar units (e.g. g/L ↔ mmol/L) for that metric.

Example: 180.16 g/mol (glucose)

Notes

Description: Text field used for capturing notes

Impact: Text shows when hovering over a metric/formula name in Line charts.

Example: Primary Nitrogen Source | Measured via Thermo Gallery Analyzer

Expresses Timeseries Data

Description: Converts a metric with an 'Unknown' data type into timeseries data. Only applies to metrics that were not classified correctly upon ingestion.

Impact: Once a metric is expressed as timeseries data, this action cannot be reversed.

Uses Log Scale

Description: Enables Log Scale for a specific metric.

Impact: Metric show on a logarithmic Y-axis when feature is turned on.

Disable Interpolation

Description: Disables linear interpolation for a specific metric.

Impact: Interpolation affects the way data sets are shown in line charts. When disabled, data show without connecting lines when feature is turned off.

Resampling Method

Description: Determines how data is aggregated when condensing time series data into manageable intervals. You can select either 'Mean' to smooth data trends by averaging values, or 'Max' to capture the highest value within each interval.

Impact: Choosing 'Mean' provides a clearer view of overall trends by reducing noise, while 'Max' emphasizes peak conditions, making it useful for identifying extreme events or anomalies in the data.

Example: For temperature data, selecting 'Mean' will show the average temperature over each hour, whereas 'Max' will highlight the highest recorded temperature for that period.

Default Ingestion Unit

Description: The unit in which the metric is ingested into the app.

Impact: Changing default ingestion unit alters the metric value. E.g. changing the default ingestion unit to g/L for a metric originally ingested as mg/L will result in a 1000x multiplication of the base values. E.g. 1 mg/L will change to 1 g/L.

Example: mg/L or g/L

Example metric sidebar panel

The Run Summary page contains all the information associated with a given run. It covers every aspect of your bioprocess including run data, properties, metrics, lineage, and event notes. Switch to the editing view for run editing and archiving or plot your data by clicking the Analysis button.

Navigation

To access the Run Summary page, double-click on a run in the run data table on the Runs page. This will open the Run Details page. Available tabs are: Summary (when enabled), Properties, Metrics, Lineage, and Events, with the less frequently used destinations — including Alerts and Import History — grouped under a More menu at the end of the tab row.

Summary

The Summary tab provides an AI-generated overview of the run in a structured dashboard format. It is available for organizations with the AI-generated summaries feature enabled. The dashboard is composed of several sections:

• Key Indicators: A curated set of the most relevant metric aggregations (e.g., final titer, peak biomass, mean pH) displayed as cards for at-a-glance review.
• Graphs: Pre-configured line charts showing key timeseries profiles for the run, such as growth curves, feed profiles, or DO/pH trends.
• Objectives & Notes: A text section capturing the run's objectives and any analytical notes.
• Events: A timeline of annotated events associated with the run.
• Lineage: A visual summary of the run's upstream and downstream material stream relationships.

The Summary tab respects run-specific configuration when available, otherwise using organization-level defaults. Click 'Analyze' on any graph in the Summary tab to jump directly to the Analysis page with that chart pre-loaded.

Properties

The Properties tab presents a list of the run meta data, including Run Start, Run End, and any other custom property that was previously associated with the run through file ingestion or manual editing. Navigate to the 'Edit' page to switch to the editing view for run archiving and property editing. Data Sources labels provide insights into the origin of a property. Labels are automatically generated upon ingestion.

Metrics

In the Metrics tab, users can access an overview of the time series data associated with a given run. This tab displays a list of time series metrics and formulas, along with useful aggregations and metric units for easy reference. Metrics are categorized into parent and sub-metrics, allowing users to quickly understand the structure and relationships of the data (See 'Library' Article for more details). From this view, users can navigate directly to the metric details page for more information or archive a specific metric from the run without removing it from the overall metric library. This feature provides a centralized place for exploring and managing time series data efficiently. Data Sources labels provide insights into the origin of a metric. Labels are automatically generated upon ingestion.

Lineage

In the Lineage tab, users can access the process flow diagram that tracks the relationships between individual runs. This functionality is particularly useful for understanding the lineage of a run, such as identifying which seed flask was used to inoculate a certain bioreactor or tracing the bioreactor run used for downstream processing testing. To use this feature, enter a valid run name into the 'Input Run' property and navigate to the Lineage tab. Click 'Add property' to provide additional context to the blocks. Organizations with downstream processing enabled see an enhanced lineage view for unit operations and material streams, where each unit operation block states how many properties and time series it holds; see the Downstream Processing guide.

Events

The Events tab facilitates the annotation of timestamped event notes. Users can document important process annotations such as Inoculation, Feed Start, or any other observations or milestones associated with the run. Event notes show in Line Chart enhancing your analysis by providing context to understanding of the bioprocess workflow. When you ask Assist to archive or rename an event, the link it returns opens this tab with the change staged as a pending edit, which you then save or discard.

Alerts

The Alerts tab allows users to manage alerts for a run. Alerts are most useful for runs with data streaming into the app in real time via hardware integration. When an alert's condition is reached (example: Dissolved Oxygen < 60 %), Invert sends notification emails to the selected recipients — chosen from the users in your workspace — and creates an event on the run. If a run has no alerts yet, the tab offers a shortcut to create the first one.

Import History

The Import History tab shows the file upload history for a given run providing insights on the origin of data at a single glance. Each entry in this table links to the relevant page on the Import History tab for additional insights on mappings used, metrics uploaded, etc.

The Analysis page is your go-to destination for visualizing and analyzing your bioprocess data. Choose between line charts, scatter charts, and bar charts to tell the story behind your data. Use line charts for timeseries data, scatter charts for quantitative cross-run comparisons, and bar charts for a clean categorical summary view.

Navigating to the Analysis Page

To access the Analysis page, start by navigating to the Runs page and selecting a set of runs you wish to analyze. Press the 'Analyze' button in the top right corner of this view to transition to the Analysis page. The line chart is the default. Switch chart types using the Chart settings button in the chart header.

Workflow

1. Metric selection

   Select one or multiple metrics from the metric dropdown. Formulas can be added here as well — type the formula name and click 'Add'.

2. Chart settings

   Click the Chart button in the chart header to open the chart settings panel. From here you can change chart type, split by, layout, axis ranges, events, grouping, coloring, and time filters.

3. Run selection

   Update run selection as needed by checking/unchecking run checkboxes in the table underneath the graph. Optionally, click 'Run selection' for altering the full list of runs included in the analysis.

4. Full Screen view

   Switch to Full Screen view for a close-up view of the graph.

5. Export

   Export the graph as an image (.PNG) or export the displayed data as an Excel file.

   

   

6. Save Analysis

   Save the analysis as a report by creating a new report or appending it to an existing report.

Chart Settings

All chart configuration is in the Chart button popover, accessible from the chart header. It contains the following sections:

Chart Type

Switch between Line, Bar, and Scatter using the button group at the top of the panel.

Split By

Controls how runs and metrics are distributed across graphs:

• Separate — one graph per run and metric combination.
• Split runs — one graph per run (line charts only).
• Split metrics — one graph per metric; compare a single metric across multiple runs.
• All in one — all runs and metrics in a single graph.

Chart Layout

Controls how many charts appear side-by-side: Auto, Full width, 2 columns, or 3 columns.

X-Axis Range

Set a custom Min, Max, and optional Interval for the x-axis. For time-based line charts, values are entered in the selected time unit (e.g. hours). Overrides compose with drag-zoom so both can be used together. Overridden values are highlighted in the panel. This control is disabled for bar charts and categorical scatter charts.

Y-Axis Settings

Set a custom Min, Max, and optional Interval for each y-axis. Toggle Combined Y-Axis to merge all metrics onto a single axis. When Split by Metrics is active, each metric gets its own independent axis. Values support Python-style exponentiation (e.g. 10**6).

Events (Line Charts)

Toggle Show events on or off. When on, filter by event category — Phases, Additions / Removals, and Observations — using the category buttons.

Time Filters (Line Charts)

Use Data Start and Data End to restrict the x-axis to a specific window (e.g. growth phase only, pre-run data). Use Normalization Basis to control what t=0 means — Run Start, a specific event type (e.g. Feed Start), or a phase start. Click Reset to restore defaults.

Line Charts

Visualization of Timeseries Data

The line chart is the primary tool for visualizing timeseries data. It supports a wide range of layouts for close-up single-run views, per-metric comparisons, and all-in-one overviews across a full experiment.

Drag Zoom (X-Axis)

Click and drag within the graph to zoom into a specific time window. The current zoom bounds appear in the top right corner under "ERT" (Elapsed Run Time). Click the ✕ on the zoom annotation to reset. Drag zoom composes with the X-axis range set in the Chart settings panel — both can be active at the same time.

Custom Axis Ranges

Both the X and Y axes support manually entered Min / Max / Interval values, set via the Chart settings panel (see Chart Settings above). Overridden values are shown highlighted; use the Reset button within each axis section to revert individual axes to their default. Toggling Combined Y-Axis changes which axes are displayed, but stored zoom values for each axis are preserved.

Formulas

Create derived metrics using the built-in formula editor. Type a new metric name into the metric dropdown field and click 'Add'. Enter the formula name, input dependencies, and expression in the editor. Use the formula preview to verify results before saving. For full details on supported operations and formula types, see the Library article. As an example, air flow rate (L/h) and reactor volume (L) can be combined to calculate VVM — a scale-independent aeration metric that enables meaningful comparison across bioreactor sizes ranging from 0.25 L to 100,000 L.

Events & Phases

Utilize the event annotation feature to create time-stamped and interactive event notes, enhancing your analysis. Supported event types are: Inoculation, Induction, Transfection, Sample, Harvest, Drawdown, Feed Start, Foamout, and Observation. Optionally, upload an image to provide additional context to your data. Control which event categories appear on the graph using the Show events toggle and category filters in the Chart settings panel.

Phase markers are visual indicators that delineate different process segments, such as Growth or Production phase. In a formula context, a phase can be selected in the Applied Time Frame dropdown, scoping the formula calculation to that segment only — for example, a Specific Growth Rate formula applied to the Growth phase, or a Productivity formula applied to the Production phase.

Grouping & Coloring

The chart settings panel offers Group by and Color by as two tabs of the same control, available for line, bar, and scatter charts.

Use Group by to aggregate and compare related runs based on specific attributes, such as "Experimental Condition", "Strain", or "Alias". When runs are grouped, it enables the analysis of variability (shaded regions representing 16th and 84th percentiles) and central tendencies (median) within those groups. Run IDs in run tables and chart legends are replaced by the attribute name enabling users to assign custom run names.

Use Color by to color chart series by a run attribute or a parent metric, making it easy to distinguish groups at a glance without aggregating the data. On bar and scatter charts your Group by selection carries over to Color by automatically when you switch chart type.

Metric/Formula Notes

Add notes to metrics or formulas from the Library editing page. On the Analysis page, hover over a metric or formula name to surface the note as a tooltip — useful for documenting assumptions, data sources, or calculation details directly within the chart view.

Run Data Table Customization

Customize the run data table to provide additional context to the timeseries graph. This includes displaying relevant metadata such as strain ID, run ID, bioreactor size, and more, enhancing the interpretability of the visualized data.

Scatter Chart

Aggregation

Use scatter charts when you want to explore relationships between two variables in your data. They are particularly useful when the input variable for X is non-time-based (e.g., Strain ID, Run ID). You have the option to choose between a variety of aggregations for the Y input variable, such as mean, standard deviation, sum, count, minimum, maximum, last value, etc. For example, compare 'Product (Last)' versus 'Run ID' or 'OD (Maximum)' versus 'Strain ID'. Use this tool to identify trends, clusters, outliers, or other patterns in your data, facilitating data-driven decision-making and analysis.

Continuous vs. Categorical X-Axis

When the selected X variable is numeric, you can switch between Continuous and Categorical mode in the Chart settings panel under X-Axis. Continuous mode plots values on a numeric axis and enables statistics. Categorical mode treats each X value as a distinct group, which is useful for comparing conditions that happen to have numeric labels (e.g., passage numbers, concentration levels).

Statistics

Enable the Show statistics toggle in the Chart settings panel to overlay statistical summaries when X values have multiple entries per category. The available statistics are mean, standard deviation, standard error, count, and lower/upper 95% confidence intervals. Statistics are disabled when the X-axis is set to Categorical mode.

Bar Chart

Bar charts offer a clean categorical view of your aggregated run data — ideal for comparing a metric's summary value (e.g., final titer, peak OD, mean pH) across a set of runs or conditions side-by-side. Switch to bar chart view using the Chart settings panel. The X-axis is driven by a categorical run attribute (e.g., Run ID, Strain, Condition) and the Y-axis uses the same aggregation options available in scatter charts (mean, max, last, etc.). Use Color by in the Chart settings panel to color bars by a run attribute for additional visual grouping. Statistics overlays such as mean, standard deviation, and 95% confidence intervals are calculated automatically when multiple runs share the same X category.

Analysis Templates

Analysis Templates let you save and reuse chart configurations — metric selections, split settings, y-axis ranges, and more — so you can apply a consistent view across different sets of runs without re-building it each time.

Creating a Template

Set up your chart view as desired (metrics, split settings, layout, y-axis configuration), then open the template selector in the chart header and choose 'Save as new'. Give the template a name. Templates are shared across your organization.

Applying a Template

Select a saved template from the template dropdown in the chart header. The analysis will update to match the saved configuration. If you modify the view after applying a template, an 'Edited' badge appears to indicate the current state has drifted from the saved template.

Managing Templates

From the template dropdown you can save changes back to the current template ('Save'), rename it, reset to the last saved state ('Reset to saved'), or delete it. Use 'Start over' to clear the template selection and begin with a fresh, unsaved configuration.

Compile your bioprocess data analysis into standardized, reproducible summary reports. A report brings together charts, tables, text, code, and diagrams — all in a single shareable document. Once complete, reports can be shared with collaborators for data review, or duplicated as a template for future experiments.

The four most recently edited reports appear as cards under Recent reports. The list below shows each report's visibility, title, last modified date, and owner, and can be sorted by title, last modified, or owner. Use Add filter to narrow the list, and New to create a report.

Adding Content

In report editing mode, click the + button between blocks to open the Insert menu. Every piece of content in a report is a block, and blocks can be reordered, duplicated, or deleted independently.

The available block types are:

• Plot — A chart (line, scatter, or bar) paired with a run data table and a title/description field. This is the primary block type for data visualization. For details on chart configuration options, see the Analysis article.
• Image — Embed an image directly in the report body, useful for annotated screenshots, microscopy images, or process diagrams.
• Attachment — Link a file attachment (e.g. a raw data file, an instrument export, or a protocol document) so it is accessible alongside the analysis.
• Code Block — Execute custom Python analysis inline within the report. Results, plots, and tables appear directly below the code. See Code Blocks below for details.
• Mermaid Diagram — Render flowcharts, process diagrams, or decision trees using Mermaid syntax, without leaving the report editor.
• Table — Insert a structured data table for presenting values, comparisons, or reference data.
• Table of Contents — Automatically generate a linked navigation index from the headings in the report — useful for longer documents.
• Separator — Insert a horizontal rule to create visual breaks between sections.
• Mention — @mention a team member to draw their attention to a specific section of the report. Mentioned team members receive a notification (see the Notifications guide) once the report is saved and shared with them.
• Equation — Insert typeset equations using LaTeX syntax anywhere in your text, powered by KaTeX. Useful for documenting kinetic models, mass-balance equations, or statistical expressions directly in the report. Equations can also be inserted from the (x) button in the editor toolbar.

Code Blocks

Reports support Python Code Blocks, allowing you to execute custom analysis directly within your report. Code blocks enable advanced data transformations, calculations, and visualizations without leaving Invert.

When to Use Code Blocks

Code blocks are useful for:

• Custom calculations: Compute metrics not available as formulas (e.g., specific yield calculations, kinetic parameters)
• Advanced visualizations: Create custom charts beyond standard line and scatter plots
• Data transformations: Reshape or filter data to highlight specific insights
• Batch processing: Analyze multiple runs with custom logic

Creating a Code Block

1. In report editing mode, click the + Insert button and choose Code Block
2. Write your Python code in the editor
3. Click 'Run' (or press shift + enter) to run the code
4. Results display inline in your report—output, tables, and plots appear immediately below the code block

When a report contains code blocks, the editor toolbar shows a Run all menu. Use Run all to execute every code block in the report in order, and Restart runner to reset the Python session before running again.

Available Libraries and Data

Code blocks have access to:

• pandas: DataFrame operations, grouping, aggregations
• numpy: Numerical computations
• matplotlib/seaborn: Plotting and visualizations (recommended for reports)
• scipy: Statistical analysis, curve fitting
• Your report data: Access bioprocess runs, metrics, and properties loaded in the report

Datasets

Datasets are the tables available to your code blocks — in Python they appear as data frames. Open the Data control in the editor toolbar to manage them:

• Add — define a dataset from runs in your workspace
• Upload .csv — bring in an external table
• Per dataset, use the edit, refresh, and remove icons to change its definition, pull the latest data, or delete it

Each dataset lists the number of runs it covers and when it was last updated, so it is clear which data an analysis ran against.

Example Code Block

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Example: Calculate specific growth rate
df = pd.DataFrame({
    'time': [0, 2, 4, 6, 8],
    'od': [0.1, 0.2, 0.5, 1.2, 2.8]
})

# Calculate growth rate
df['ln_od'] = np.log(df['od'])
df['specific_growth_rate'] = df['ln_od'].diff() / df['time'].diff()

# Plot results
plt.figure(figsize=(10, 4))
plt.plot(df['time'], df['specific_growth_rate'], 'o-')
plt.xlabel('Time (h)')
plt.ylabel('Specific Growth Rate (1/h)')
plt.title('Growth Rate Analysis')
plt.show()

Tips for Code Blocks

• Keep code simple and focused—complex analysis is harder to review
• Use comments to explain what each section does
• Test calculations with sample data before finalizing
• Use descriptive variable names for clarity
• Avoid external API calls or file operations (sandboxed environment)

Workflow

1. Add New Report:

   Navigate to the Reports page and click 'New' to create a blank report. Type the report title at the top of the document — it sits as a fixed first element above the body content and stays in sync with the report name shown in the page header.

2. Add your first Plot block:

   Click the + Insert button and choose Plot. Enter a title and description, click 'Select Runs', and choose the relevant runs. Then configure your chart — select metrics, chart type, and layout — and press 'Done'. You can return to edit the chart at any time via the 'Edit Plot' button on the block.

3. Build out the report:

   Use the Insert menu to add additional blocks — more plots, code blocks, images, tables, or text separators. Duplicate any existing block to carry forward its run selection and chart settings, which speeds up building multi-chart reports. Blocks can be reordered by dragging.

4. Save and Share:

   Once your report is complete, save it by clicking the 'Save' button. If you leave the editor with unsaved changes, Invert asks whether to save, save as a copy, keep the changes as a draft, or discard them.

   Sharing is controlled from the visibility control in the top right corner of the report, which shows the report's current state ('Personal' or 'Workspace'). Open it to set General access — 'Workspace' makes the report available to anyone in your workspace, 'Personal' keeps it owner-only in report lists — and use Copy link to put a direct link to the report in your clipboard. Personal reports can still be opened by teammates in read-only mode via that link. Where guest users are enabled, add people by name or email under Guest users to give named individuals access to a single report — useful for managing access to sensitive analyses. Sharing reports with users outside your organization requires assistance from Invert support — contact us via Help & Support to arrange this.

5. Report Archiving:

   To remove a report from the list, open the actions menu (⋮) in the top right corner of the report and press 'Archive'.

6. Additional Actions:

   The actions menu (⋮) also offers 'Make a copy' — duplicate a report to create backups or use it as a starting point to streamline the analysis of related experiments — plus 'Print' and 'Presentation Mode' for reviewing or presenting a finished report. For bulk editing run selection across all plot blocks within a report, press 'Charts' in the editor toolbar, select the runs to apply to every chart block, and press 'Apply'.

Alternative Workflow

1. Start Analysis from Runs Page:

   Alternatively, you can begin your analysis from the Runs. Select the runs you're interested in and transfer them to the Analysis page.

2. Visualize Data: Visualize your data using line, scatter, or bar charts. Customize the chart view settings and run data table as needed.

3. Save to Report: Click 'Add to report' and choose 'Create a new report' or 'Add to a report' to incorporate your analysis into a new or existing report.

The Data Quality page gives an organization-wide view of the health of your bioprocess data. It has three summary cards and a list of data issues.

Summary cards

• FAIR Data Score — how well your data conforms to the FAIR principles. Each pillar is scored, and the gauge shows the average. Hover over a pillar for its measure. Findable counts runs that are in an experiment, Interoperable counts data that has parent metrics, and Reusable counts runs that have events. Accessible is satisfied for all workspaces. To improve the score, put runs into experiments, add events, and group metrics under parent metrics.
• AI Readiness — how well the data supports AI/ML workflows. The score combines the distinctiveness of metric names and property values, the presence of property values, and how much of your data reports use. If Assist is not enabled for your organization, the card asks you to contact Invert through Help & Support.
• Scope — the volume of data that the assessment covers: runs, experiments, events, timeseries, and properties.

Data issues

The list gives one row per issue, sorted by severity. The columns are Severity, FAIR (the affected pillars), Issue Type, Affected (the number of affected entities), and Data Type.

Use Add filter to filter by project, severity, FAIR pillar, or data type. Use the search control to find an issue by title, severity, data type, or FAIR pillar.

Issues cover missing metadata, runs without timeseries or events, experiments without runs, duplicate metric or property names, properties with the wrong or unspecified data type, and metrics or properties that no run data uses.

Issue details

Click an issue to open it. The page gives the severity, the FAIR pillars, a description of the effect on your work, and the recommended actions. It also lists the affected runs, experiments, metrics, or properties, each linked to the entity in Invert.

Some issues can be corrected on the page: Group into Parent for duplicate names, conversion of numeric values that are stored as text, Update all or Review individually for suggested data types, rounding for floating point artifacts, and Archive all for entities that no data uses. For the other issues, Review & Resolve opens the affected data in Invert with the filters applied, so you can correct it in context.

Invert Assist lets you query your bioprocess data in plain language. Instead of navigating manually through plots and exports, you can ask questions conversationally and receive results generated directly from your data. Behind the scenes, Assist writes and executes Python code against your data, so every answer is reproducible and traceable.

What you can do with Invert Assist

• Outlier Detection: Scan all your timeseries data to surface excursions worth investigating further.
• Root Cause Analysis: Identify drivers behind unexpected trends or deviations in your process data.
• Experiment Summarization: Generate clear summaries of multi-run experiments, highlighting key similarities and differences.
• Iterative Exploration: Refine questions and follow up to dig deeper — Assist retains context across the full conversation.
• Report Generation: Ask Assist to create comprehensive analysis reports with charts, tables, and summaries — automatically structured and ready for review.
• Interactive Outputs: Assist can render charts and other visual outputs directly in the conversation and in a side drawer for closer inspection. It can generate both Invert native charts and Python-based visualizations, so you can choose the right format for the analysis. Files that Assist produces open in the same drawer — tables (CSV, TSV, JSON), images, PDFs, and videos are previewed inline, and every file can be downloaded.
• Data Import Staging: Ask Assist to prepare data imports — it can stage timeseries datapoints and run events for your review via the standard ingestion preview, so nothing is written until you approve.
• Data Management Routines: Assist can carry out data management routines such as archiving or renaming runs, experiments, quantities, and events. Assist sends you a link with the change staged; you open it and complete the action in the app, so nothing is changed until you confirm it.
• Library Mapping Preparation: Ask Assist to prepare updates to Library items — parent metrics, formulas, and metric or property definitions — from a structured file; the changes appear in the standard ingestion preview for review before anything is written.
• Document Data Extraction: Attach a batch record or other PDF and ask Assist to extract structured data from it. Extracted values appear in a review card where you can verify, correct, or discard each value before signing off; signed-off data is staged for import through the standard ingestion preview.
• Product Q&A: Ask Assist how Invert features work — it can consult the Invert product documentation to answer questions about the platform.

Generating Reports with Assist

Assist can create complete analysis reports from your bioprocess data. Instead of manually building reports from charts and tables, you can ask Assist to generate one in plain language.

How to Generate a Report

1. Select your runs - Choose the runs you want analyzed
2. Open Assist - Open Invert Assist from the left navigation sidebar
3. Ask for a report - Try prompts like:
   • "Generate a process monitoring report for my most recent experiment"
   • "Create a comparative analysis of these two runs"
   • "Build a summary report highlighting key metrics and trends"
4. Review the result - Assist will produce a report with analysis, charts, and data tables
5. Refine if needed - Ask Assist to modify specific sections or regenerate with a different prompt
6. Save to Reports - Once satisfied, save the report to your Reports library

Tips for Better Reports

• Be specific about what analysis you want (e.g., "Compare yield between these two strains")
• Mention timeframes if relevant (e.g., "Report on the growth phase data")
• Ask follow-ups to refine the analysis (e.g., "Can you add a section on pH impact?")
• Review for accuracy before saving, especially for presentation or publication use

How to use Invert Assist

1. Select your runs. For best performance, starting with a focused set of runs (around 15 or fewer) produces the fastest, most targeted results — you can always load additional runs mid-conversation using Assist's run loading tools.

2. Open Invert Assist from the left navigation sidebar:

   

3. Type your question—for example:

   • “What caused the excursion in Run75?"
   • "Is there any effect of pH on titer based on these runs?"
   • "What is the next experiment that might be interesting to explore?"

4. Review the answer and trace the reasoning chain alongside the code that was executed for the analysis.

5. Use follow-up questions to refine your results or switch context.

Attaching files

You can attach files directly to an Assist conversation for analysis. Assist accepts any file type, including:

• Images (PNG, JPEG, etc.) — interpreted visually
• PDFs — parsed as documents
• Tabular data — CSV, Excel (.xlsx), and Parquet files are read programmatically (e.g., with pandas) so Assist can summarize columns, compute statistics, or join the data with your bioprocess runs

To attach a file, click the attachment icon in the Assist input bar and select files from your computer, or drag and drop files directly into the chat. There is no restriction on file format — if Assist can read it with Python, it can analyze it.

History and context in Assist

• Your Assist queries and outputs are saved at a user-level. Past conversations are listed in the Assist sidebar for easy access.

• In addition to Runs, Reports can also be provided as context to Assist. This allows users to leverage existing analysis templates as a reference for Assist to perform calculations. For this, navigate to the relevant report page, open Assist, and add the report as context.

• Workspace admins can further add context at the organizational level, which will be used in all Assist queries for your team. Use this space to provide terminology, conventions, or guidelines that should inform the assistant's responses. Organization context can be added under Settings > AI in the left navigation.

Editing Reports with Assist

For organizations with the Assist report editing feature enabled, Assist can also modify existing saved reports — not just generate new ones. Open a report, launch Assist, and ask it to update specific sections, add new plot blocks, or revise text.

When Assist edits a report, it produces a draft — an unsaved, private suggestion you can review before saving. Drafts have these characteristics:

• Unsaved: Drafts are private to you until you explicitly save them
• Editable: You can accept the draft as-is or ask Assist to modify it further before saving
• Stale draft warning: If a draft sits for more than 5 minutes without being reviewed, you'll see a warning (⚠️) indicating the analysis may be outdated
• Accept or reject: You control whether the draft is applied to the saved report or discarded
• Visual diff on review: When you open a draft, modified blocks are marked with a blue stripe and added blocks with a green stripe so you can spot Assist's changes at a glance.

Tips for better results

• Be specific: include timeframes or phases, run names, or metrics in your question.
• Use follow-ups: instead of repeating full queries, build on the last response.
• Long conversations: when a chat approaches its context limit, an indicator appears next to the input bar. Use it to prefill a handoff-summary prompt so you can continue the work in a fresh chat before the current one runs out of space.

FAQs

Will Invert Assist chat change my data?

Assist's analysis tooling is read-only — it queries and visualizes data but never edits it directly. The exceptions are data import staging, library mapping preparation, and data management routines such as archiving or renaming: Assist prepares the change and sends you a link, but nothing is written until you complete the action in the app.

What data can Invert Assist chat access?

It has access to your structured bioprocess data stored in Invert, including runs, metrics, properties, events, lineage, formulas, and reports. Your data is processed within Amazon Bedrock infrastructure and is never used for model training or fine-tuning.

How does Invert ensure reliability?

Invert maintains a suite of automated benchmarking evaluations that run continuously to characterize Assist's analytical capabilities and detect any regressions caused by model or infrastructure changes.

What if the result is incorrect or Assist misunderstands the question?

Try rephrasing with more specific detail — for example, naming the run, metric, or time range you have in mind. You can also submit feedback on a response using the Send feedback button, which helps the team investigate edge cases and improve accuracy over time.

Still need help? Reach out to our support team via the Help & Support link in the app.

Skills

Your team has established ways of doing RCA, DoE review, regression analysis — methods refined through years of experience. Until now, that knowledge lived in people's heads or buried in SOPs. Now you can capture it directly in Invert as a Skill: a reusable set of instructions that tells Assist how to conduct a specific type of analysis, so it works the way your team works.

How it works

Create a Skill on the Skills page, found under Assist in the left sidebar, by giving it a name, description, and a body — written in plain text, code, or both. The body is your method: step-by-step procedures, statistical thresholds, decision criteria, preferred chart types, or Python snippets that define how an analysis should be done.

You can also ask Assist to draft a Skill for you based on an analysis you've just worked through. Assist proposes the Skill as a draft you can review, edit, and save, so a one-off investigation becomes a reusable method.

When you're ready to use it, open Assist, type @ to bring up the mention menu, and select your Skill alongside any runs or reports you want to work with. Assist reads the Skill's instructions and follows your approach — same methodology, every time, regardless of who's running the analysis.

What can you do with Skills?

• Standardize root cause analysis: Define the steps your team follows for RCA — which metrics to check first, what thresholds flag a deviation, how to structure the final summary — and let anyone on the team run the same investigation
• Encode DoE review procedures: Specify how to evaluate experimental results, which statistical tests to apply, and what constitutes a meaningful difference between conditions
• Create reporting templates: Describe the sections, plots, and key metrics that should appear in a campaign summary or tech transfer package, then let Assist generate it
• Capture domain-specific calculations: Include Python code for custom analyses — growth rate calculations, metabolite ratios, yield corrections — so Assist executes them consistently
• Compose multiple Skills: Reference more than one Skill in a single conversation. Combine a "Growth Phase Analysis" skill with a "Metabolite Profile" skill to build a complete picture

Example Skills to get started

Skill name	What it does
Fed-Batch RCA	Walks through a structured root cause analysis: check feeds, DO, pH, temperature, then correlate deviations with titer impact
Campaign Summary	Generates a standardized report with VCD/viability overlay, titer bar chart, and key observations per condition
Scale-Up Comparison	Compares matched parameters between bench and pilot scale, flags any that fall outside defined equivalence bands
Harvest Timing	Evaluates viability trend and titer plateau to recommend optimal harvest window

Available now for all Assist-enabled organizations.

Run Assist workflows unattended. An Automation pairs a Skill with a trigger — a schedule, or an import event — so that reports, data imports, or analyses happen automatically without anyone needing to start a session.

What you can do with Automations

• Generate periodic reports: Produce a batch summary or campaign report every Monday morning, ready for the team before standup.
• Stage data imports on a schedule: Automatically stage incoming instrument data for review at a fixed time each day.
• React to incoming data: Trigger an analysis or notification as soon as an import succeeds or fails, instead of waiting for the next scheduled run.
• Reduce repetitive work: Any analysis you would otherwise run by hand on a recurring basis can be turned into an Automation.

Creating an Automation

1. Open the Automations page from the sidebar.
2. Click New Automation.
3. Give the automation a descriptive name.
4. Select a Skill — this determines what the automation does when it runs.
5. Choose Outputs — select whether each run produces a Report, an Import Preview, or both. Every run also creates an Assist session you can review.
6. Set a Trigger — either a schedule (daily, or weekly on a specific day) or an import event: an import succeeded, an import failed, or a bulk import completed. For import event triggers, use Mappings to limit the automation to imports that use specific ingestion mappings; the default is Any mapping.
7. Choose whether to Notify when finished — leave it on to get a notification each time the automation completes.
8. Click Save.

Managing Automations

Select any automation from the list to open its detail panel. From here you can:

• Edit configuration — change the name, skill, outputs, or trigger at any time.
• Duplicate — create a copy of an existing automation as the starting point for a new one.
• Enable or disable — toggle the automation on or off without deleting it.
• Run now — trigger a one-off run immediately, outside the normal schedule.
• Take over — make future runs use your account instead of the account the automation runs as now. Take over is not available if the automation already runs as you.
• View run history — see past runs with their status, trigger source, duration, and links to the resulting report or session.
• Delete — permanently remove an automation you no longer need.

Finding automations

The list page has two tabs: Running as me shows only the automations that run under your account, while All shows every automation in the organization — useful to see what recurring analyses colleagues have set up and to avoid duplicating effort. Filter the list by trigger, outputs, or the account an automation runs as, and search by name.

Halted Automations

If an automation fails on consecutive runs it is automatically halted to prevent repeated failures. A halted automation shows a warning banner explaining when it stopped and why. To resume, fix the underlying issue in the linked Skill, then use Run now to confirm it succeeds — the automation re-enables on the next successful run.

Invert supports downstream processing (DSP) — the purification train that follows the bioreactor. This guide covers the DSP-specific views available to organizations with DSP enabled.

The DSP data model

DSP is organized around two core concepts: Unit Operations, which represent the process steps in the purification train such as chromatography, hold or viral inactivation, and viral filtration, and Material Streams, which represent the material flowing into and out of each step.

Material streams are also typed, so a stream can be identified as a load, pool, feed, filtrate, eluate, or another process-specific stream type. That relationship between unit operations, streams, and stream types is the foundation for the DSP views described below; see the Library guide for the unit operation definitions.

Run table — By Run & Streams

The Runs table adds a pivoted DSP view that lets you switch between By Run and By Run & Streams, so you can compare each unit operation down to its individual material streams in one table. See the Runs guide for the base table experience.

Lineage

The Lineage tab visualises the purification train as a connected flow of unit operations and material streams, with per-step figures such as Mass Closure and Step Yield so you can follow recovery and purity across the process. Each unit operation block also states how many properties and time series it holds, so you can see at a glance where data exists.

You choose which properties and metrics appear on each block from the View panel, and select a mass-balance property such as Recovered Mass to track material recovery step to step. See the enhanced Run Summary Lineage section for the base lineage experience.

Reading mass balance

Each unit operation shows two figures derived from the mass-balance property you select (for example, Recovered Mass), comparing what enters a step with what leaves it:

• Step Yield — the proportion of the input recovered in the step's output stream(s), shown as a percentage (output ÷ input). It reflects how much material the step retained.
• Mass Closure — how much of the input is accounted for across both the output and any known waste stream(s), shown as a percentage ((output + known waste) ÷ input). Values near 100% mean the step's material is fully accounted for; a large gap points to unmeasured losses or missing data.

Invert converts stream values to a common basis (including mass-to-molar conversions where a molar mass is defined) before computing these figures, so streams recorded in different units still compare correctly.

Unit operations in the Library

Downstream processing is built on unit operation types, which you manage on the Unit Operations tab of the Library. Each type carries a Name (e.g. Chromatography, Viral Filtration, Hold), an optional Icon that identifies it across the DSP views, and a Context note describing the step.

From a unit operation type's panel, Show related runs opens the Runs table filtered to that unit operation and Show related reports opens the matching reports. With DSP enabled you can also group the runs table and charts by unit operation, letting you compare the same step across many runs. See the Library guide for managing library entries in general.

Importing DSP data

DSP structure — unit operations, material streams, and the lineage connections between runs — is populated through the same Import flow as the rest of your data, using either the standard Run Data mappings or a custom-built mapping:

• Material streams — a multi-stream Run Data mapping with a Material Stream column lets a single run carry several typed streams (load, pool, feed, filtrate, and so on).
• Unit operations — a Unit Operation column places each run's data under the right step in the train.
• Lineage connections — an Input Run column names each run's upstream source, linking one step's output to the next step's input.

Standard mappings cover the common file shapes; when a source file doesn't fit, a custom mapping can be built to the same effect. See the Import guide for the ingestion workflow.

Plotting line charts against a non-time x-axis

By default, line charts on the Analysis page plot values against time. With DSP enabled you can set a metric or property as the x-axis instead, plotting one variable directly against another rather than against elapsed time. You choose the x-axis from the chart's axis controls; for non-DSP organizations, line charts remain time-based.

Where DSP fits in the rest of Invert

The DSP views described above are extensions of the core Invert pages rather than separate tools — the same runs, run details, and library definitions you already use, with an added downstream-processing layer. These guides cover the standard experience each DSP view builds on:

• Runs — the runs table and how to filter, group, and lay it out. DSP adds the By Run & Streams pivot to this same table.
• Run Summary — a single run's detail tabs, including the standard Lineage flow. DSP enriches that Lineage with unit operations, material streams, and per-step recovery figures.
• Library — where unit operation types, metrics, and properties are defined. The unit operations and stream properties shown in the DSP views come from these definitions.

Getting downstream processing

Downstream processing is an add-on that is enabled per organization. If your organization doesn't yet have DSP and you'd like access to the views described here, or you have questions about setting it up, contact us at support@invertbio.com.

The command palette is a keyboard-driven way to search and move around Invert without hunting through menus. Open it from anywhere to jump straight to a run, report, or Library item, navigate to a page, or start an action.

Opening the command palette

Press ⌘K (Mac) or Ctrl+K (Windows/Linux), or click Search in the left navigation sidebar. Start typing and results update as you go; use the arrow keys to move through them and Enter to open the highlighted result. Press esc to close the palette.

What you can do

• Search across your workspace: Find runs, reports, experiments, projects, metrics, properties, unit operation types, event types, skills, and Assist sessions by name and open them directly.
• Ask Assist: Type a question and send it straight to Assist as a new session, with the page you are on as context.
• Navigate to pages: Jump to any main section of the app — Projects, Experiments, Runs, Reports, Metrics, Properties, Unit operation types, Event types, Skills, Import, Import history, Data Quality, Automations, Users, and the settings pages — without using the sidebar.
• Create something new: Start a new run, experiment, report, Assist session, automation, skill, metric, property, formula, parent metric, unit operation type, or event type.
• Reopen recent Assist history: Browse and return to your recent Assist sessions.
• Account actions: Open the notification drawer, read What's new, get to Organization settings, open Help & Support, send feedback, or sign out.
• Invite a team member: Tenant admins can start an invite directly from the palette.

Searching one entity type at a time

Results are grouped by Open, Go to, Create, and Account. To search inside one entity type only, pick an Open … entry under Navigation — for example Open Run… — and then type. The palette then searches runs alone, and the placeholder tells you which type you are searching.

You can also type the type followed by > to go straight there. run>P061 searches runs for P061, and the same works for report>, experiment>, project>, metric>, property>, unit-operation-type>, event-type>, skill>, and assist>. Short aliases exist for the common ones (r>, rep>, e>, p>, m>), new> (or +>) lists the create actions, and go> lists the pages you can navigate to.

Which entries you see depends on your access: guest users see a reduced set, and some actions are limited to tenant admins.

Notifications keep you up to date on activity in your workspace without having to watch a page. They cover data imports — so you learn when an ingestion finished or failed — automation runs, process alerts, and Invert product updates, so new features show up where you already work.

Opening notifications

Click the bell button next to Search in the left navigation sidebar. The bell shows an indicator while you have unread notifications.

Working through your notifications

Notifications are grouped into Today and Earlier so recent activity is at the top. Filter the list with All, Unread, or Dismissed to focus on what still needs attention or to find something you cleared earlier.

Opening a notification marks it as read and takes you to the related import, automation run, process alert, or product update. Dismiss individual notifications you no longer need, or use Dismiss all to clear the list; a dismissed notification can be restored from the Dismissed filter.

Notification emails

Notifications are also sent to you by email. Control this on the Preferences tab in Settings, where each event has an In-app and an Email switch. The events are grouped into Imports (Failed, Preview ready, Complete), Automations (Run completed, Run failed), Process monitoring (Process alert), Reports (Mentions — when a team member @mentions you in a report), and From Invert (Product updates). Product updates are in-app only. Use Turn all email off to stop every notification email at once while keeping the in-app notifications. An event with both switches off is silenced and does not reach you anywhere.

A subtle sound plays when a new in-app notification arrives. To stop the sound, turn off Play a sound for in-app notifications on the Preferences tab.

Related guides

• Import
• Automations