Skip to main content
Instructions define the agent’s behavior. They make up the core of the agent’s system prompt. You can define them in a simple markdown file and they are picked up automatically by the agent.
Managed Deep Agents is in public beta and available on LangSmith Cloud in the US region only.

​
Project structure

The instructions.md file lives at the project root:

​
Add instructions

Create or modify instructions.md:
instructions.md
Use this file to define the agent’s role, behavior, constraints, and guidance for using its tools.

​
How the agent uses instructions

Instructions are inserted into the agents system prompt on every run. They are always present and help guide the agents behavior.

​
Syncing to Context Hub

When you run mda deploy to deploy the agent, instructions are automatically synced to the agent’s Context Hub repo. You can then edit the instructions in the LangSmith UI and have your changes automatically propagated to the agent.

​
How instructions compare to other concepts

Use skills for task-specific procedures that the agent loads only when relevant. Use memory for knowledge the agent learns and retains across threads.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.
Edit this page on GitHub or file an issue.