Managed Deep Agents - Quickstart
Summary
This quickstart guides users through scaffolding, configuring, testing, and deploying a Managed Deep Agent (MDA). The process involves using the MDA CLI to initialize a project structure, setting up API keys for model providers (e.g., OpenAI), defining agent instructions (`instructions.mmd`), and integrating tools like web search. Testing is done locally via `MDA dev` in LangSmith Studio before deploying the final version to the production environment.
Key takeaways
-
Project Scaffolding
0:25
Use `uv tool install managed deep agents` followed by `MDA innit <project-name>` to scaffold the agent project. This creates necessary files like `agent.py`, `instructions.mmd`, and populates environment variables.
-
Agent Configuration
2:05
The agent's behavior is defined in `instructions.mmd`. Model selection (OpenAI, Google, Anthropic) and tool definitions (e.g., web search) are configured within the project files.
-
Local Development Cycle
3:20
To test locally, run `uv sync` to install dependencies, followed by `MDA dev`. This spins up a local LangSmith Studio environment for iteration and testing.
-
Production Deployment
4:40
Deployment requires a paid Langsmith account. The process syncs context to the Context Hub—a centralized location for instructions and skills that can be edited via UI without redeployment.
Technical details
-
Prerequisites & Setup
15s
Requires Python, UV tool, a LangSmith API key, and an API key for the chosen model provider (e.g., OpenAI).
-
CLI Commands
30s
Installation: `uv tool install managed deep agents`. Initialization: `MDA innit <project-name>`. Local Dev Server: `MDA dev`.
-
Agent Definition Files
40s
Core agent logic resides in `agent.py`. Instructions are managed and edited in the markdown file `instructions.mmd`.
-
Context Management
300s
The Context Hub is a LangSmith feature that stores instructions and skills, allowing for runtime modification of agent context without requiring a full redeployment.
Mentioned resources
- LangChain
- LangSmith Studio
- Managed Deep Agents (MDA) CLI
Channel & topics
Watch on YouTube · Back to latest
This independent, AI-assisted summary is provided for commentary and informational purposes. It may contain errors or omit important context. Please watch the original video for the creator's complete presentation. Video, thumbnail, and related copyrights belong to their respective owners.