workflowadvancedGeneral AI

AI Agent Casebook: Multi-Agent Workflows with LangGraph

This project provides blueprints for building automated AI assistants to handle complex business tasks like customer onboarding or content creation. It demonstrates how multiple AI 'agents' can collaborate, offering a model for creating a specialized digital workforce.

AI SETUP PROMPT

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

# Set Up Workflow: AI Agent Casebook: Multi-Agent Workflows with LangGraph

## What This Is
This project provides blueprints for building automated AI assistants to handle complex business tasks like customer onboarding or content creation. It demonstrates how multiple AI 'agents' can collaborate, offering a model for creating a specialized digital workforce.

Source: https://github.com/BittnerPierre/AI-Agent-Casebook

## 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.)
- Whether this repository or a similar tool is already cloned or installed

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

Clone or inspect the repository to understand what needs to be installed:
```bash
gh repo clone BittnerPierre/AI-Agent-Casebook
```
Review the README, directory structure, and any install instructions before proceeding.

## 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 repository using `git clone https://github.com/BittnerPierre/AI-Agent-Casebook` and change into the new directory.
- Create a `.env` file in the project root. Scan the user's environment for `MISTRAL_API_KEY`, `OPENAI_API_KEY`, and `LANGCHAIN_API_KEY`. If any are missing, prompt the user to provide them and populate the file.
- Execute `poetry install` to install all project dependencies from `pyproject.toml`, then activate the virtual environment with `poetry shell` to prepare for running the application.

## Reference Implementation

```
```ini
[CustomerOnboarding]
model = GPT_5_MINI

[VideoScript]
# Planner uses Agents SDK (model name as-is, with litellm prefix for non-OpenAI)
planner_model = gpt-4o-mini
# Worker and producer use core enums (see app/core/base.py)
worker_model = GPT_4_O_MINI
producer_model = GPT_4_O_MINI

[CorrectiveRAG]
model = GPT_4_O_MINI
# Pre-load documents at startup (comma-separated URLs)
preload_urls = https://lilianweng.github.io/posts/2023-06-23-agent/,https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/
```
```

## 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

3,491 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Clone the repository using `git clone https://github.com/BittnerPierre/AI-Agent-Casebook` and change into the new directory.
02Create a `.env` file in the project root. Scan the user's environment for `MISTRAL_API_KEY`, `OPENAI_API_KEY`, and `LANGCHAIN_API_KEY`. If any are missing, prompt the user to provide them and populate the file.
03Execute `poetry install` to install all project dependencies from `pyproject.toml`, then activate the virtual environment with `poetry shell` to prepare for running the application.

CODE INTELLIGENCE

bash

```ini
[CustomerOnboarding]
model = GPT_5_MINI

[VideoScript]
# Planner uses Agents SDK (model name as-is, with litellm prefix for non-OpenAI)
planner_model = gpt-4o-mini
# Worker and producer use core enums (see app/core/base.py)
worker_model = GPT_4_O_MINI
producer_model = GPT_4_O_MINI

[CorrectiveRAG]
model = GPT_4_O_MINI
# Pre-load documents at startup (comma-separated URLs)
preload_urls = https://lilianweng.github.io/posts/2023-06-23-agent/,https://lilianweng.github.io/posts/2023-03-15-prompt-engineering/
```

FIELD OPERATIONS

Contract Analysis Agent Team

Build a multi-agent system where a 'Finder' agent scans legal documents for key clauses (liability, termination), a 'Summarizer' agent explains each clause in plain English, and a 'Risk Assessor' agent flags clauses that deviate from standard templates using a RAG knowledge base of approved legal phrasings.

Automated PR Review Agent

Create a workflow triggered on a new GitHub pull request. A 'Code Scanner' agent checks for style violations, a 'Logic Reviewer' agent explains the changes in plain language using RAG against project documentation, and a 'Test Suggestion' agent proposes new unit tests based on the changed code.

STRATEGIC APPLICATIONS

→Deploy a multi-agent system to handle inbound support tickets. A 'Triage' agent categorizes the issue, a 'RAG' agent retrieves relevant knowledge base articles, and an 'Escalation' agent decides whether to route the ticket to a human expert based on issue complexity and customer history.
→Automate the creation of weekly market trend reports. A 'Researcher' agent scrapes specified news sites, a 'Synthesizer' agent identifies recurring themes, and a 'Writer' agent drafts a summary report with source links for internal stakeholders.