workflowintermediateOpenCLAW

Orchestrating Specialized AI Agents with OpenCLAW

OpenCLAW enables you to build a team of specialized AI agents that collaborate on complex tasks, such as sales, support, or operations. This multi-agent approach allows for more sophisticated and efficient automation pipelines by defining how different agents delegate work to each other. It supports both local and cloud-based AI models for maximum flexibility.

AI SETUP PROMPT

Paste into Claude Code or Codex CLI — it will scan your project and set everything up

# Set Up Workflow: Orchestrating Specialized AI Agents with OpenCLAW

## What This Is
OpenCLAW enables you to build a team of specialized AI agents that collaborate on complex tasks, such as sales, support, or operations. This multi-agent approach allows for more sophisticated and efficient automation pipelines by defining how different agents delegate work to each other. It supports both local and cloud-based AI models for maximum flexibility.

Source: https://www.youtube.com/watch?v=9epvGKyHIek

## 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.youtube.com/watch?v=9epvGKyHIek) 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

- Install the OpenCLAW framework using the command `openclaw dashboard` and guide the user through the initial setup process, including linking their primary AI model provider API key.
- Scan the user's workspace for an `openclaw.json` configuration file. If found, modify it to enable the `subagents` and `sessions_yield` tools. If not found, create a new `openclaw.json` file with these tools enabled, ensuring potentially dangerous tools like `exec` are disabled by default for security.
- Based on the user's stated goal, draft a multi-agent configuration within `openclaw.json` or a separate application spec file. Define at least two specialized agents (e.g., 'TicketClassifierAgent', 'ResponseDrafterAgent') and outline the data flow and delegation logic between them using the `subagents` tool.

## 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

3,266 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Install the OpenCLAW framework using the command `openclaw dashboard` and guide the user through the initial setup process, including linking their primary AI model provider API key.
02Scan the user's workspace for an `openclaw.json` configuration file. If found, modify it to enable the `subagents` and `sessions_yield` tools. If not found, create a new `openclaw.json` file with these tools enabled, ensuring potentially dangerous tools like `exec` are disabled by default for security.
03Based on the user's stated goal, draft a multi-agent configuration within `openclaw.json` or a separate application spec file. Define at least two specialized agents (e.g., 'TicketClassifierAgent', 'ResponseDrafterAgent') and outline the data flow and delegation logic between them using the `subagents` tool.

FIELD OPERATIONS

Automated DevOps Incident Responder

Create a two-agent system. The first agent monitors logs or alerting systems for new incidents. Upon detection, it summarizes the incident and passes it to a second agent, which analyzes the project's codebase, suggests a potential fix, and drafts a new GitHub pull request for human review.

CRM Data Enrichment and Outreach Pipeline

Build a workflow where a 'ContactEnrichmentAgent' takes a new lead from a web form, finds additional public information (company, role) using search tools, and updates the CRM. A second 'OutreachAgent' then uses this enriched data to draft a personalized introductory email and stages it for review before sending.

STRATEGIC APPLICATIONS