Benchling has a suite of AI-based productivity features. These features use large language models to intelligently interpret and generate natural language and make decisions.
Access to all AI-based features are managed by tenant-admins in the tenant admin console where each capability can be enabled or disabled individually. Your data is never used for cross-customer training or training by our AI model providers. For more information, see Data protection and security for AI at Benchling.
Benchling offers various AI agents, features and structure prediction models. AI agents are advanced AI powered capabilities that help you retrieve and capture data on Benchling. AI features provide lighter weight AI functionality to improve productivity. Structure prediction models leverage LLMs to help you visualize protein structures on Benchling.
| Name | Description |
| Chat | Chat allows you to explore data, generate documents, and conduct in-depth research from a single entry point. With each query, Benchling will select the right tools and skills to complete a task |
| SQL Writer | SQL Writer helps you write, debug, and modify SQL queries using natural language |
| Notebook Check | Notebook Check flags entry typos, inconsistencies, incomplete sections, and more |
| Plate Annotator |
Plate annotator interprets natural language prompts to assign well roles Note: Plate annotator is in Preview |
| Data Entry Agent | Data Entry Agent supports import of unstructured data into Benchling structured tables by interpreting document context, user instructions and the uploaded file(s) to map data points accurately |
| Structure prediction models | Structure Prediction Models generate 3D Structures for Amino Acid Sequences on Benchling |
| Model Hub | Browse available Scientific AI Models on the Benchling Model Hub, across entities on Benchling. |
Legacy Agents
Legacy agents will be deprecated in the future. All capabilities of the legacy agents are integrated with the Chat tool. For more information about Chat and how to use it, see the linked help article.
| Name | Description |
| Ask Agent | Ask lets you explore your Benchling data quickly through natural-language questions |
| Deep Research Agent |
Deep Research answers complex questions by retrieving and analyzing data across your entire Benchling tenant Note: Deep Research with public literature search is in Preview |
| Compose Agent | Compose accelerates notebook entry and template creation through conversational chat |
| Analysis Agent |
Use the Analysis Agent to explore, visualize, and interpret your analysis data through natural language questions Note: Analysis Agent is in Open Beta |
Capabilities marked preview or beta are available, and may be enabled via the tenant admin console using the steps below. Please keep in mind that these features are still a work in progress, and any feedback is welcome via the in-app feedback mechanisms.
Control Benchling AI access
Tenant Admins control Benchling AI capabilities through the Tenant Admin Console, where each capability can be enabled or disabled individually.
To control access to Benchling AI capabilities:
- Click on your avatar in the bottom corner of the main navigation bar
- Click Tenant admin console in the menu
- Click the Settings tab
- Click AI Settings in the menu
- Identify the capability you would like to manage
- To enable for all users, toggle the capability on
- To disable for all users, toggle the capability off
- To enable for specific users, click Show details > Enabled for select users > search box for the relevant users who should have the capability enabled
- A Settings changed banner will appear, click Save to apply the changes
These settings can be changed at any time by visiting the page again.
Onboard your team
Once your desired Benchling AI capabilities are enabled for the appropriate set of users, share key resources and best practices noted below with your team for them to get started.
Best practices:
- Review our agent specific help center articles to find example use cases or prompts that your team can try
- Benchling AI agents use the permissions of the user. Before provisioning access, review your team's permission settings to ensure users have the right level of access
-
Start with high-value, low-risk queries to build confidence
- Example: Instead of a broad question like "Summarize all our cancer research," begin with a focused query such as "Summarize the results from the latest C9ORF72 antibody validation study."
-
Incorporate into recurring workflows (weekly summaries, compliance checks)
- Example: Instead of manually compiling a project update, use a prompt like "Generate a summary of our progress on the lead optimization phase of program X."
-
Keep refining prompts for better accuracy
- Example: A broad prompt like "Summarize our in vivo studies" can be refined to a more specific query: "Summarize the design of in vivo studies ST042 and ST043, including a table of key differences."
-
Save useful queries for reuse
- Example: If a query like "Write a report for how we engineered viral vector X, including the objective, methods, and results" proves effective, save the exact prompt so it can be easily adapted for future reports on other viral vectors.
- Try multiple queries in parallel
Key resources:
- Read about how other teams and organizations are applying Benchling AI
- Check out past Benchling AI trainings and discuss with others in our Community here
Customize Benchling AI with tenant-wide instructions
Chat and Notebook Check support custom guidelines which provide additional admin defined context and rules that shape how the relevant AI agents and features work for your tenant.
Custom guidelines are managed by tenant admins in the Tenant Admin Console. To view or modify custom guidelines, open the Tenant Admin console’s settings page following the instructions above and navigate to the AI settings tab on the left hand side.
Custom guidelines can be written in plain language and may contain rules to enforce, areas to focus on, explanations about which rules apply in which situations, etc.
Personalize your Benchling AI experience
Benchling AI offers two ways to tailor the agent to how individual users work: About You and Custom Instructions. Both can be updated at any time as your needs change.
About You is a structured setup experience that helps the agent better understand your role and the work you do. Completing it gives the agent useful context it can draw on across all your conversations. You can revisit and update your answers whenever your role or focus shifts.
To complete About You:
- Click the sparkle icon in the navigation bar to open Benchling AI
- Click the gear icon to access AI Chat Setting
- Click About You
- Answer the structured questions about your role, team, and the work you do
- Click Save — the agent will use your answers to personalize responses going forward
Custom Instructions let you go further with free-text instructions that shape how the agent responds — your preferences for tone, formatting, and output style. You can edit these at any time. Some examples:
- I prefer bulleted summaries over long text paragraphs
- Always reference the Benchling Study name
- When I use abbreviations like VCD (viable cell density), CPP (critical process parameter), or CQA (critical quality attribute), use the full term in responses
To add Custom Instructions:
- Click the sparkle icon in the navigation bar to open Benchling AI
- Click the gear icon to open the AI Chat Settings panel
- Enter your instructions in the Custom Instructions text box — they'll save automatically
Custom Instructions and About you apply only to your own conversations and complement any admin-defined guidelines already in place.
Note: you can only create and save one set of instructions, you cannot save multiple sets or versions of instructions and switch between them to add different context for specific types of queries.
Use Skills
Skills teach Benchling AI how to handle specific tasks reliably. Use skills in Benchling to extend the default capabilities of the Benchling AI Chat. Benchling Skills conform to the open Agent Skills standard.
There are two types of skills:
- Benchling-authored skills that are written by Benchling and made available for use in your tenant
- Custom skills written by you or your organization
Benchling-authored skills
Benchling-authored skills are auto installed by Benchling. Benchling-authored skills cannot be edited or deleted by users, Benchling will control all content and updates for these skills.
The list of available Benchling-authored skills are below:
Access skills
- Open AI in the main sidebar
- Click the gear icon in the top right corner of the AI panel
- Select the Skills tab
Manage your active skills
Each user controls which skills are available to Benchling AI during their sessions. Active skills can be pulled into context by the agent when relevant, while inactive skills are ignored.
Toggle skills on or off from either:
- AI Settings → Skills tab
- The + button inside AI Chat
Archive skills you authored if you no longer need them:
- Open AI Settings
- Navigate to Skills tab
- Click the Archive button in the top right corner of the skill
Using skills
Once a skill is active, the AI will pull it in automatically when it's relevant to your request. You can also invoke a skill directly from the + button in AI Chat if you want to use it explicitly.
Create a new skill
Describe the task you want Benchling AI to handle - what should trigger it, what steps it should follow, and any details specific to your workflow. Benchling AI will draft a skill you can review and refine.
Edit an existing skill
Mention your existing skill and tell Benchling AI what isn't working. It can fix outdated steps, add missing edge cases, or improve when the skill fires.
Upload an existing skill
If you've built a skill outside of Benchling or want to bring one in from another project, you can upload the skill file directly to make it available in your workspace. Benchling accepts .zip or .skill files for upload as skills. Simply click + Add in the top right corner of the Skills page to upload a skill file.
A few tips:
- Base your request on a real task: the more concrete, the better the result
- Include any templates, data sources, or sample outputs the AI should follow or reference. The more concrete your inputs, the more reliably the skill will perform.
- If the skill isn't triggering when you expect, ask Benchling AI to revisit its description - that's usually where the issue is
See your Benchling AI usage
Open the Tenant Admin console’s settings page following the instructions above and navigate to the AI Usage tab on the left hand side.
View your tenant's available AI credits and usage data and adjust the date period as needed. If you have questions about Benchling credits and usage, please reach out to Benchling Support.
Benchling Credits
Benchling AI brings AI-powered features, agents, and models directly into the Benchling platform so scientists can accelerate their everyday R&D workflows. Some Benchling AI features are included with your subscription at no additional cost. Agents and models use a credit system — and to ensure every team can start using AI right away, credits are included with every Benchling subscription.
Features that don’t consume credits:
- SQL Writer
- Notebook Checker
Agents and models that do consume credits:
- Chat
- Ask
- Deep Research
- Compose
- Data Entry
- Structure prediction
The number of credits used per run depends on each agent, model and the complexity of the tasks being performed. See the current Rate Card and learn more here.
Rate limits
Benchling AI has rate limit controls that help ensure compute capacity for all users at all times (and to prevent any unintended usage or abuse). These rate limits are set to default values that accommodate the vast majority of routine workflows. In some cases, such as a large volume of queries in a short time, you could run up against the rate limits. If you hit a rate limit, you'll see a notification that reads: "You have exceeded the daily usage limit for AI features. Please try again later."
If your team is hitting rate limits frequently, or if hitting a rate limit is blocking work, an admin can contact Benchling Support to request an increase. Adjustments can be made for specific users or for the entire tenant depending on the situation.
Note: rate limits are independent from Benchling Credits, which means you or other users on your tenant could hit a rate limit even when credits are still available. Benchling Support can adjust rate limits, but they cannot adjust your Benchling Credits balance. Adding monthly credit capacity requires a purchase order.