workflowintermediateOpenCLAW

Creating a Multi-Agent Software Factory with OpenCLAW

Use the OpenCLAW framework to build a virtual team of specialized AI agents that automate complex software development. Create a 'software factory' with distinct agents for architecture, coding, code review, and documentation, each configured with different AI models and tools to operate efficiently.

AI SETUP PROMPT

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

# Set Up Workflow: Creating a Multi-Agent Software Factory with OpenCLAW

## What This Is
Use the OpenCLAW framework to build a virtual team of specialized AI agents that automate complex software development. Create a 'software factory' with distinct agents for architecture, coding, code review, and documentation, each configured with different AI models and tools to operate efficiently.

Source: https://www.meta-intelligence.tech/en/insight-openclaw-agents-guide

## 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.meta-intelligence.tech/en/insight-openclaw-agents-guide) 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

- Verify the OpenCLAW CLI is installed. Use the `openclaw agents add` command to create the first agent in the software factory team: an 'architect' agent using a powerful model like Claude 4 Opus, specified tools, and a low temperature for precise, high-level design tasks.
- Following the same pattern, create the 'coder', 'reviewer', and 'documenter' agents. Assign each a specific model (e.g., Claude 4 Sonnet for the coder, Haiku for the documenter), token limit, and toolset appropriate for their role as described in the source documentation.
- Inspect the `openclaw.json` file to confirm that all four new agents ('architect', 'coder', 'reviewer', 'documenter') are listed under `agents.registered`. Then, create a sample mission file delegating a simple task to the 'coder' agent to test the setup.

## Reference Implementation

```
openclaw agents add architect --model anthropic:claude-opus-4 --fallback-model anthropic:claude-sonnet-4 --max-tokens 128000 --temperature 0.3 --tools file,shell,browser,mcp --description "System architect"
```

## 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

3,507 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Verify the OpenCLAW CLI is installed. Use the `openclaw agents add` command to create the first agent in the software factory team: an 'architect' agent using a powerful model like Claude 4 Opus, specified tools, and a low temperature for precise, high-level design tasks.
02Following the same pattern, create the 'coder', 'reviewer', and 'documenter' agents. Assign each a specific model (e.g., Claude 4 Sonnet for the coder, Haiku for the documenter), token limit, and toolset appropriate for their role as described in the source documentation.
03Inspect the `openclaw.json` file to confirm that all four new agents ('architect', 'coder', 'reviewer', 'documenter') are listed under `agents.registered`. Then, create a sample mission file delegating a simple task to the 'coder' agent to test the setup.

CODE INTELLIGENCE

bash

openclaw agents add architect --model anthropic:claude-opus-4 --fallback-model anthropic:claude-sonnet-4 --max-tokens 128000 --temperature 0.3 --tools file,shell,browser,mcp --description "System architect"

FIELD OPERATIONS

Automated Tech Debt Refactoring Team

Build a team of agents to manage technical debt. An 'auditor' agent scans the codebase for code smells and anti-patterns, a 'planner' agent prioritizes the findings and creates a refactoring plan, a 'refactor' agent executes the code changes, and a 'validator' agent runs tests to ensure no regressions were introduced.

AI-Powered SEO Content Pipeline

Create a multi-agent workflow for content marketing. A 'researcher' agent identifies trending keywords and topics using browser tools. A 'writer' agent drafts an SEO-optimized article based on the research. A 'promoter' agent creates social media snippets from the article and queues them for posting.

STRATEGIC APPLICATIONS

→A startup can use an OpenCLAW agent team to accelerate the creation of a minimum viable product (MVP). The 'architect' agent designs the initial structure, the 'coder' agent builds core features, and the 'documenter' agent creates user guides, significantly reducing the initial engineering headcount and time-to-market.
→A digital marketing agency can deploy an autonomous agent team to manage multiple client accounts. A 'writer' agent drafts blog posts and ad copy, an 'analyst' agent pulls performance data from Google Analytics and ad platforms, and a 'strategist' agent suggests campaign adjustments based on the data.