Deep Research

Deep Research helps answer complex questions by retrieving and analyzing data across your Benchling tenant. It can extract information from unstructured text (whether in Notebook Entries or Attachments) and combine it with structured data (Entities, Results, and more) to produce comprehensive, citation-backed reports.

Deep Research supports multi-turn chats and file attachments. It includes citation and chip links where possible so you can verify sources quickly.

• Ask a question or describe what you need (e.g., weekly lab update, study summary, draft CoA/CoT)
• Attach relevant files (templates, recent examples) to steer structure and tone
• Review the output, follow up in the same thread, and iterate until it’s ready to export or copy into your documents

Additionally, AI Connectors allow Benchling Deep Research to access data from external systems like Microsoft Teams, SharePoint, Slack, and other platforms that support the Model Context Protocol (MCP). This extends Deep Research's ability to provide comprehensive answers by incorporating information from multiple sources across your organization's data ecosystem. AI Connectors work by establishing secure connections between Benchling and external MCP servers, allowing Deep Research to retrieve relevant information while respecting your authentication and permissions in those systems.

This is a Benchling AI feature. See the AI at Benchling page for information on how to enable this and other AI-based features.

Access Deep Research 

Each time you want to use Deep Research, you will need to create a new chat where you will enter your prompt. To create a new chat, follow the steps below: 

1. Click the sparkle icon in the Navigation bar to access Benchling agents
2. In the chat box, click Deep Research 
3. In the textbox, type your prompt in natural language, and attach necessary supporting files 
4. Send the chat to run the prompt

Deep Research outputs

Deep Research outputs contain two types of references and you can use both types to validate the correctness of the Deep Research outputs. 

Benchling Object References: Appear as interactive chips (similar to mentions in Notebook Entries)

1. Click to navigate directly to the source
2. Hover to preview key information

Data Citations: Show up as bracketed end-note style superscript links [#] that link to specific actions Deep Research took to gather information

1. Click citations to view source context 

Access previous research

Any Deep Research query you have made can be returned to at a later time by following these steps:

1. Click the sparkle icon in the Navigation bar
2. Click on AI Chats at the top of the sidebar
3. Click on a chat to open it
4. Ask follow-up questions to refine or expand previous research

Deep Research with public data

When using Deep Research with public data search, you can ask questions across both your Benchling data and public sources. Deep Research automatically crafts a query using your data, which is then used to query the internet. 

Note: Deep Research with public data search is disabled by default. To enable, go to your AI settings in the tenant admin console. Once enabled, start a Deep Research chat and toggle the option to include public data.

Generate images with Deep Research

Deep Research can generate images from your Benchling data directly within your AI chat conversation using Gemini (Nano Banana). Use it to create scientific diagrams, workflow visualizations, and conceptual illustrations without leaving your workspace.

To generate images with Deep research:

1. Click on the Sparkle icon in the Navigation bar to create a new Deep Research chat
2. Describe the image you'd like to generate in your Deep Research conversation 
   • “Create an image of…”
   • “Generate a diagram of…”
3. Send your chat 

Tips for image generation

• Be specific about layout and flow
  • Specify the visual structure you want (e.g., "left-to-right flow," "U-shaped diagram," "branching paths that converge")
• Define your visual style
  • Specify how conditions should be highlighted (e.g., "use a yellow glow around the mouse to indicate irradiation")
  • If your company already has style guidelines, consider adding a section to the tenant level Deep Research guidelines: “If generating an image, be sure to follow these style rules:... ”
• Include labeling requirements
  • Request action captions for each step (e.g., "label each arrow with the process name")
• Use color strategically
  • Request high contrast for publication readability (e.g., "white background with dark text")

Save Deep Research outputs 

Deep Research outputs can be saved in a few ways by clicking the Save as button at the bottom of the output. 

• As .docx Word files
• Appended to the end of an existing Notebook Entry
• As a new Entry or Template 

Review and export citations and plots

Deep Research's core tool set is similar to and interacts with the same tools you have access to in the Benchling UI. The Tool Details modal will show you the input and output of each step in Deep Research's process. If you would like to review the same data in the Benchling UI yourself you can do so by following these steps for the corresponding type of tool call:

Search Benchling, search Notebook entries, read Notebook, and look things up

These are all either search queries and their results or reading the contents of a Benchling Notebook Entry, its attachments, a Benchling Entity (sequence, custom entity) or other Benchling object (task).

• Search Queries will be formatted like Query: "CL001,CL002" 
  • Replicate this by pasting each item in the comma separated list into Benchling search 
• Reading Notebook or Looking things up will typically return the Entry Title, EXP ID or both near the top of the input. If you see an API ID like etr_... bfi_... or seq_... you can: 
  1. Use Global search 
  2. Add Filters 
  3. Select API ID from the filters list and then search for one or more (comma separated) API IDs

Read attachment

These refer to files attached to your Deep Research chat. Files attached to Benchling Notebook entries will be referenced in "Reading Notebook" citations. You can attach any of the following: 

• A report template the agent should follow
• A recent example (for voice, level of detail, and formatting) 
• Any constraints (audience, due date, slide length, data cut) 

For example: if you want to prepare for a lab meeting you can use or modify the example message below and attach your template and/or recent example. 

Attached are: 1) the general template and 2) a recent example of my weekly lab reports. 
Review my Notebook entries from the last two weeks. 
Summarize the relevant data and outcomes of those entries following this format. 
Format the sections so that I can easily copy and paste them into powerpoint slides and format them. 
It will be particularly helpful if you can include citation links 
to entries with images or charts that I could include.

Query the warehouse

These should be formatted like Query: "SELECT ..."

1. Create a new block in dashboard in the Insights application and replace the default query body with the query between the double quotation marks and then click "Run query" 
2. You can use SQL Writer to modify this query for other, similar use cases

"Create chart" for custom plots, charts, or graphs

The Input will contain the python code for a function named "llm_make_figure." This will include the data that will be incorporated in the graphic(s) itself, not necessarily the raw data (e.g. if the average values are being graphed, the code likely only contains the averages, not the datapoints from which they were derived). 

You can insert this function into any python context and perform actions on the figure including exporting to several image formats. 

For detailed instructions, see the next section.

Export custom plots from Deep Research citations 

In a Deep Research chat where you have created a custom chart or graph, you can export the interactive chart as a static image following these instructions:

1.  To make adjustments to how the chart looks, ask Deep Research a follow-up question in the chat thread asking it to make the changes you would like 
2. Once you have a visual you are satisfied with, locate the Creating chart citation or activity item in the Research completed banner just below the Save as... box
3. The Input box will contain the python code for a function named llm_make_figure
   • This will include the data that will be incorporated in the graphic(s) itself, not necessarily the raw data e.g. if the average values are being graphed, the code likely only contains the averages, not the datapoints from which they were derived. 
4.  Insert this function into any python context and perform actions on the figure including exporting to several image formats

Note: Deep Research replaces the previous AI-based "Report Generation" feature. Deep Research is available to any Benchling customer today through the AI Settings page in the Tenant Admin Console.

Export to .svg by Windows

1. Open a blank file in Notepad or another text editing or IDE application 
2. Copy and paste the "Input:" from the "Creating chart" activity
3. Replace return fig on the last row with fig.write_image("chart.svg")
   • Replace .svg with .png etc to save to another supported format
4. Open command prompt or powershell (or another application able to run python such as Visual Studio Code) 
5. Type python then "return" or "enter" (you should now see >>>)
6. Copy and paste in your modified code from above then "return" or "enter" until you again see see >>>
7. Type llm_make_figure() then "return" or "enter"
8. The image file should now be in the directory where you were when you started the terminal, by default typically your user's home folder (where Documents and Desktop are usually located)
9. To exit, type exit() or quit the command prompt app
    

Export to .svg by Mac, Linux

1. Open a blank file in Textedit or another text editing or IDE application.
2. Copy and paste the "Input:" from the "Creating chart" activity
3. Replace return fig on the last row with fig.write_image("chart.svg")
   • Replace .svg with .png etc to save to another supported format
4. Open Terminal (or another application able to run python such as Visual Studio Code) 
5. Type python then "return" or "enter" (you should now see >>>)
6. Copy and paste in your modified code from above then return or enter until you again see see >>>
7. Type llm_make_figure() then return or enter
8. The image file should now be in the directory where you were when you started the terminal, by default typically your user's home folder (where Documents and Desktop are usually located)
9. To exit, type exit() or quit the command prompt app

Export to .svg by Jupyter notebook 

This includes cloud-based options such as Google Colab

1. Create a new notebook
2. Create a new code block
3. You may need to run a few commands such as those below and run them first in a separate code block -- the error messages should guide you through this one-time setup
   • !pip install -U kaleido
   • import kaleido
   • kaleido.get_chrome_sync() 
4. Copy and paste the "Input:" from the "Creating chart" activity
5. Replace return fig on the last row with fig.write_image("chart.svg")
   • Replace .svg with .png etc to save to another supported format.
6. Click Run All or Run Cell
7. The File should now be available in your Files, by default in the /content/ directory

Set up AI connectors 

After an admin configures an AI Connector, you can set up your personal connection to authenticate and select which tools you want to use. To request that Benchling enable AI Connectors for your tenant, have an admin contact Benchling Support or your typical Benchling point of contact.

Connect to an available connector

To set up your connection:

1. In the Navigation bar, click Connections (the very last icon)
2. Click the AI Connectors tab
3. Click the connector you want to use
4. In the pop-up window, click Authenticate or Connect
5. Complete authentication in the new tab or window that opens
   
   
6. Return to Benchling and finalize the connection
7. Select which tools you want to enable from the options the admin has made available
   
8. Click Save

Your selected connectors are now available to Deep Research. When you use Deep Research, it automatically determines whether to query your connected systems based on your prompt.

Manage your connections

You can adjust your AI Connector settings:

• Configuration: Adjust your personal settings, including which tools are enabled
• Toggle switch: Turn the connection on or off

• Disconnect: Remove the connector from your account entirely

  
  Common use cases 

1. Creating structured reports from a template [Start by uploading a template file with the desired output structure, examples linked at the bottom of this page]
   • Certificate of Analysis (CoA) or Certificate of Testing (CoT)
   • Technology Transfer Report
   • Non-clinical Study Report, including first drafts of IND enabling or BLA enabling reports like CTD CMC reports 
     • Example: "Using the attached file ‘Nonclinical Study Report.docx’ as a template, generate a study report for experiment EXP2500001. Fill each section of the template with data from Benchling. Make sure to provide citations for each piece of data."
   • General Research Study Report
     • Example: "Use the attached template to generate a report about the study in the "EBV Study" folder."  
2.  Finding entities with specific relationships or missing connections
   • Example: "Identify all plasmids registered in the last 2 months that do not have linked stable cell lines. Create a table showing: Plasmid ID, Registration Date, Gene Insert, Selection Marker, and Intended Cell Line Type."
3. Condensing complex experimental data into digestible insights
   • Example: "Summarize all experiments from Study ST042 conducted in the last 30 days. Include completion status, primary endpoints met (>90% viability threshold), any deviations from protocol, and remaining milestones. Format as an executive summary showing completed vs. planned experiments."
4. Generating formatted documents from experimental data
   • Example: "Generate a non-clinical study report for experiment EXP2500001 including: 1) Study objective and rationale, 2) Test article information with lot numbers, 3) Methods section referencing SOPs, 4) Results with all raw data from linked Results tables, 5) Existing statistical analyses with p-values, 6) Conclusions addressing the primary hypothesis. Include all quality control checkpoints and flag any values outside acceptance criteria (CV > 15%)."
5. Investigating experimental failures and identifying patterns
   • Example: "Analyze all failed transfection experiments (efficiency <20%) in Project X. Compare against successful transfections (efficiency >70%) from the same period, examining: cell passage number, DNA concentration, reagent lot numbers, operator, incubation time, and confluence percentage. Create a ranked list of variables most correlated with failure. What caused EXP2500001 to go wrong?"
6. Evaluating data organization and access permissions
   • Example: "Audit all notebook entries and entities created in Q4 2024 for compliance issues. Identify: 1) Entries without project associations, 2) Entities missing required metadata fields (lot number, expiration date, creator), 3) Users with edit permissions on archived projects, 4) Sensitive data (patient/clinical) accessible to non-clinical team members. Output a prioritized action list with specific remediation steps."
7. Exploring research directions and identifying knowledge gaps
   • Example: "Analyze all data from Project Y to identify research gaps. Map which combinations of our lead compounds and cell lines have been tested, what assays have been run (binding, toxicity, stability), and what concentrations have been evaluated. Create a matrix showing tested vs. untested conditions and recommend the top 5 experiments to run next based on existing trends and missing critical data."
8. Generating workflow schematics
   • Example: “Create a diagram of our antibody purification workflow"
9. Diagram a study or experiment:
   • Example: “Summarize the study described in EXP2500123. Include a diagram outlining the study design.”
10. ERD
    • Example: “Make an image that shows the entity schemas in our registry and their relationships as an ERD.”
    • Example: “Summarize the lineage and links to key entries for purified antibody lot Benchlingimab 1.4-001 Produce an image with a diagram of these relationships. 

Quality and Risk reminders

• All AI-based systems may make mistakes. Treat outputs as a draft and verify before sharing or saving to a Notebook
• The system may produce false positives, which may be misleading. Deep Research will include citation links and chip links where possible to facilitate double-checking its responses
• Think of Deep Research as a capable new teammate who just started working at your company. Use its speed to reduce searching and formatting work so you can focus on analysis and polish

Data Protection & Security

Deep Research operates on behalf of the user who made the query. That means it has access to the same data as the user who made the query, not all of the data within Benchling.

For more information about privacy and security for AI-powered features, see Data protection and security for AI at Benchling.

Frequently Asked Questions

• Can I choose which connectors Deep Research uses for specific questions?
  • Not today. All connections you've enabled in the Connections app are available to Deep Research, which automatically determines which systems to query based on your prompt. You cannot enable or disable specific connections on a per-chat basis through the chat UI. Though you can return to the connections tab to enable or disable connections at any time. 
• ​​Why am I getting an authentication error?
  • If you encounter authentication errors when setting up your connection, the external system may require pre-registration of the connection on the MCP server side. Benchling will support these pre-registered connections in the near future. Contact Benchling Support for assistance with authentication issues.

• Certificate of Analysis Template.docx20 KB
• Tech Transfer Report Template.docx20 KB
• General Study Report Template.docx30 KB
• Nonclinical Study Report Template.docx30 KB