workflowadvancedOpenCLAW

Multi-Agent Specialized Team for Solo Founders

Set up a virtual team of specialized AI agents, each with a unique role like strategy, marketing, or development. This allows a single person to manage multiple business functions efficiently from a single chat interface, overcoming the limitations of using one generic AI for all tasks.

AI SETUP PROMPT

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

# Set Up Workflow: Multi-Agent Specialized Team for Solo Founders

## What This Is
Set up a virtual team of specialized AI agents, each with a unique role like strategy, marketing, or development. This allows a single person to manage multiple business functions efficiently from a single chat interface, overcoming the limitations of using one generic AI for all tasks.

Source: https://github.com/hesamsheikh/awesome-openclaw-usecases/blob/main/usecases/multi-agent-team.md

## 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)?

## Fetch the Source

Fetch the raw file content from GitHub:
```bash
curl -sL "https://raw.githubusercontent.com/hesamsheikh/awesome-openclaw-usecases/main/usecases/multi-agent-team.md"
```

## 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

- Scan the user's project for an existing OpenCLAW configuration. Create a new directory named `/openclaw/agents/` if one does not exist.
- Create subdirectories for each specialized agent (e.g., `/milo`, `/josh`, `/marketing`, `/dev`) and populate each with a `SOUL.md` file containing the specific personality, responsibilities, and model configuration provided in the source.
- Configure the OpenCLAW orchestrator to connect these agents to a single Telegram group chat. Scan the user's `.env` file for a `TELEGRAM_BOT_TOKEN`. If not found, prompt the user to create a new bot via BotFather and add the token to their secrets.

## Reference Implementation

```
## SOUL.md — Milo

You are Milo, the team lead. Confident, big-picture, charismatic.

Responsibilities:
- Strategic planning and prioritization
- Coordinating the other agents
- Weekly goal setting and OKR tracking
- Synthesizing insights from all agents into actionable decisions

Model: Claude Opus
Channel: Telegram (responds to @milo)

Daily tasks:
- 8:00 AM: Review overnight agent activity, post morning standup summary
- 6:00 PM: End-of-day recap with progress toward weekly goals
```

## 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

3,493 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Scan the user's project for an existing OpenCLAW configuration. Create a new directory named `/openclaw/agents/` if one does not exist.
02Create subdirectories for each specialized agent (e.g., `/milo`, `/josh`, `/marketing`, `/dev`) and populate each with a `SOUL.md` file containing the specific personality, responsibilities, and model configuration provided in the source.
03Configure the OpenCLAW orchestrator to connect these agents to a single Telegram group chat. Scan the user's `.env` file for a `TELEGRAM_BOT_TOKEN`. If not found, prompt the user to create a new bot via BotFather and add the token to their secrets.

CODE INTELLIGENCE

bash

## SOUL.md — Milo

You are Milo, the team lead. Confident, big-picture, charismatic.

Responsibilities:
- Strategic planning and prioritization
- Coordinating the other agents
- Weekly goal setting and OKR tracking
- Synthesizing insights from all agents into actionable decisions

Model: Claude Opus
Channel: Telegram (responds to @milo)

Daily tasks:
- 8:00 AM: Review overnight agent activity, post morning standup summary
- 6:00 PM: End-of-day recap with progress toward weekly goals

FIELD OPERATIONS

AI Creative Agency Pod

Build a team of agents for a freelance creative. One agent acts as Creative Director, setting project vision. A second agent researches market trends and competitor visuals. A third agent generates copy variations, and a fourth agent generates visual concepts using a text-to-image model.

Personal Finance Advisory Team

Create a multi-agent system to manage personal finances. A 'CFO' agent tracks budgets and sets savings goals. A 'Market Analyst' agent monitors investment portfolios and relevant news. A 'Tax Assistant' agent categorizes expenses and flags potential deductions throughout the year.

STRATEGIC APPLICATIONS

→A solo SaaS founder can delegate tasks to this AI team, using the 'Dev Agent' for coding, the 'Marketing Agent' for user acquisition research, and the 'Strategy Lead' to maintain focus on high-level goals, effectively simulating a small company's core functions.
→A small consulting firm can create a specialized research pod. Each agent is an expert in a different domain (e.g., legal precedent, financial data, scientific papers). A human consultant uses the team to rapidly gather and synthesize cross-disciplinary information for client reports.