# Set Up Workflow: OpenClaw: Building Multi-Agent Teams for Parallel Task Execution
## What This Is
This guide demonstrates how to create a team of specialized AI agents within the OpenClaw framework that work together to solve complex problems. By coordinating agents for parallel tasks like research, data analysis, and reporting, you can automate large projects and get results up to 40-60% faster than with a single AI.
Source: https://eastondev.com/blog/en/posts/ai/20260205-openclaw-multi-agent-routing/
## 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://eastondev.com/blog/en/posts/ai/20260205-openclaw-multi-agent-routing/) 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 community showcase repository 'hesamsheikh/awesome-openclaw-usecases' to access multi-agent team configurations and examples.
- Locate an example YAML configuration file within the repository. Use it as a template to define a new multi-agent workflow for the user's project, specifying a 'coordination_mode' (e.g., orchestrator), subagents, and target models.
- Create a dedicated directory for the new agent team to ensure isolation. Populate it with the new YAML configuration and a 'GOALS.md' file defining the objective. Ensure API keys for the specified models are available in the environment, prompting the user if missing.
## Reference Implementation
```
research-coordinator:
model: claude-3-5-sonnet
subagents: [paper-searcher, web-scraper, data-analyst, report-writer]
team:
coordination_mode: orchestrator
max_parallel_agents: 3
shared_memory: enabled
```
## 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