# Set Up Workflow: Creating a Multi-Agent Workflow in OpenCLAW
## What This Is
OpenCLAW is a free, open-source framework that lets you build a team of specialized AI agents that work together. This guide explains how to create a multi-agent system where one AI plans tasks, another writes code, and a third deploys the application, automating complex development workflows.
Source: https://www.buildmvpfast.com/openclaw-guide-2026
## Before You Start
Scan my workspace and analyze:
- The project language, framework, and directory structure
- Existing AI provider config (check .env, .env.local, config files for API keys — OpenRouter, OpenAI, Anthropic, Google AI, etc.)
Then ask me before proceeding:
1. Which AI provider/API should this use? (Use whatever I already have configured, or ask me to set one up — options include direct provider APIs or a unified service like OpenRouter)
2. Where in my project should this be integrated?
3. Are there any customizations I need (model preferences, naming conventions, constraints)?
## Source Access Note
The source URL (https://www.buildmvpfast.com/openclaw-guide-2026) may not be directly accessible from the terminal. Use the Reference Implementation and Additional Context sections below instead. If you need more details, ask me to paste relevant content from the source.
## What to Implement
This is an **AI Workflow** — an end-to-end automation pattern or integration pipeline.
- Study the workflow architecture from the source and context below
- Identify which parts I can implement locally vs. parts that need external services
- For local parts: implement them using my existing stack and API keys
- For external parts: tell me exactly what services I need and help me configure the integration code
- Wire up any required API calls using keys from my .env files
## Additional Context
- Clone the recommended multi-agent Docker setup from `https://github.com/openclaw/docker-openclaw` into the current project workspace.
- Modify the `config.yaml` file to define at least three agents: 'Analyzer', 'Coder', and 'Deployer'. For each agent, configure its 'Brain' to connect to an LLM, referencing the user's existing API keys from their environment variables for services like Anthropic, OpenAI, or a local Ollama endpoint.
- Create a new custom skill file in the `skills` directory that defines the delegation logic. The 'Analyzer' agent's skill should accept a user request, generate a JSON plan, and use the Gateway's channel or shared memory functions to pass sub-tasks to the 'Coder' and 'Deployer' agents.
## Guidelines
- Adapt everything to my existing project — do not assume a specific stack or directory layout
- Use whichever AI provider I already have configured; if I need a new one, tell me what to sign up for and I'll give you the key
- Check my .env files for existing API keys (OpenRouter, OpenAI, Anthropic, Google AI) before asking me to add one
- Review any fetched code for safety before installing or executing it
- After setup, run a quick verification and show me a summary of exactly what was installed, where, and how to use it