Agents
An Agent is a specialized assistant you configure once and reuse across conversations. Give it instructions, tools, and knowledge sources, and it handles the rest.
When you catch yourself repeating the same prompts, attaching the same files, or enabling the same tools every time you start a conversation, that's a good sign you need an Agent.
Common use cases
Agents work best when you need the same instructions, tone, or knowledge applied consistently:
- Brand voice editor: paste any draft and get it rewritten in your company's tone, with the same formatting rules every time.
- Legal clause checker: upload a contract and ask the Agent to flag non-standard clauses based on your internal policy Library.
- Meeting prep assistant: share a prospect's website or a briefing doc and get structured talking points, key figures, and open questions.
- Technical FAQ: attach your product documentation as a Library and share the Agent with your team so anyone can get accurate, sourced answers.
- Translation with context: an Agent that translates content while respecting your glossary and brand terminology, attached as a Library.
Creating an Agent
- Click
Agentsin the left sidebar. - Click
Create Agentto start from scratch, or pick a pre-built template as a starting point. - Configure the Agent (see next section).
- Test it in the preview panel on the right side of the screen.
Agents save automatically as you configure them. There's no save button.
Templates cover common patterns like summarizers, translators, and code assistants. Start with one and customize it rather than building from scratch.
Configuration
Agent configuration is split into main settings and more advanced options. You can always come back and edit these later.
Every Agent starts with four fields.
- Name: use a clear, descriptive name your team can find at a glance. For example,
Customer Support TriageorSales Brief Generator. - Description (optional): a short explanation of what the Agent does, visible in the Agent picker.
- Avatar (optional): choose from presets or generate a custom one.
- Instructions: detailed guidance for the Agent's behavior. This is where you define its role, scope, and output format. Type
/in the field to reference tools and knowledge sources inline.
Using Agents in chat
Starting a conversation with an Agent
- Click
+then selectAgentsor type/in the message box.
- Search for or select an Agent. Its name appears at the top of the chat box.
- Send your message. The Agent responds according to its configuration.
Switching Agents
Click the dropdown arrow next to the Agent name, or repeat the process above, and select a different Agent.
Only one Agent can be active at a time within a conversation.
Returning to the default model
Click the cross icon next to the Agent name to remove it. The conversation continues with the default Le Chat model. You can also start a new chat, which always begins with the default model.
Writing effective instructions
Good instructions make the difference between a generic chatbot and a reliable team tool. Here are a few principles:
- Define the role clearly. Start with who the Agent is and what it does: "You are a code reviewer. Focus on Python best practices, security issues, and performance."
- Specify the output format. Tell the Agent whether you expect bullet points, JSON, prose, a table, or something else. Include a short example if the format matters.
- Set explicit boundaries. State what the Agent should not do: "Don't provide legal advice" or "Only reference documents from the attached Library."
- Reference tools inline. Type
/in the instructions field to mention specific tools or knowledge sources. This tells the Agent when and how to use them. - Iterate in small steps. Change one thing, test in the preview panel, repeat. Getting instructions right is an iterative process.
For a broader introduction to prompt writing techniques, see our prompt engineering guide.
By default, a new Agent is private (only you can see and use it).
Sharing with specific people
- Open the Agent's card on the
Agentspage. - Click the sharing status label (
Private,Organization, orx people). - Search for users or groups and assign a permission level:
- Collaborator: can use, edit, and delete the Agent.
- Viewer: can use the Agent in their own conversations but can't edit or delete it.
Changes save automatically. Close the modal when you're done.
Sharing with your entire organization
In the same sharing modal, toggle Entire organization and choose whether everyone gets Collaborator or Viewer access.
We don't send notifications when you share an Agent. Let your teammates know so they can start using it.
Managing Agents
Duplicating an Agent
Open the three-dots menu (⠇) on the Agent card and select Duplicate my Agent. This creates a new, independent copy you own. Changes to one won't affect the other.
Duplicating is also the workaround for transferring an Agent to a colleague. Share it as a Collaborator, ask them to duplicate it, then delete the original if needed.
Deleting an Agent
- Open the three-dots menu (
⠇) on the Agent card. - Select
Deleteand confirm.
Deleting an Agent is permanent and can't be undone. If the Agent was shared, it becomes unavailable to everyone.
Agents are available on all plans. If you change or cancel your subscription, your Agents and their sharing settings are preserved. Some tools or knowledge sources may become unavailable on lower-tier plans.
Agents and the API
Agents created in Le Chat are designed for the chat interface and can't be used programmatically. If you need API access, create Agents through Studio›Agents ↗ or the REST API.
Studio Agents can be deployed to Le Chat and appear in a dedicated section of your Agent list.
- Custom instructions: set persistent behavior rules that apply to all conversations (Agents override these when active).
- Libraries: build knowledge bases from uploaded documents to attach to your Agents.
- Connectors: connect external data sources like Google Drive, GitHub, or Notion.
- Canvas: create and edit content collaboratively with AI.
- Code Interpreter: run Python for data analysis and visualization.
- Projects: organize conversations into scoped work areas.