workflowintermediateClaude Code

Real-World Developer Workflows with Claude Code

This guide showcases how developers use the Claude Code AI assistant to build complete applications, beyond just writing small code snippets. Examples include creating a personalized daily digest, a smart photo search tool, and a central dashboard that manages social media and community engagement from one place.

AI SETUP PROMPT

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

# Set Up Workflow: Real-World Developer Workflows with Claude Code

## What This Is
This guide showcases how developers use the Claude Code AI assistant to build complete applications, beyond just writing small code snippets. Examples include creating a personalized daily digest, a smart photo search tool, and a central dashboard that manages social media and community engagement from one place.

Source: https://gsong.dev/articles/ai-dev-workflow/

## 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://gsong.dev/articles/ai-dev-workflow/) 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

- Analyze the user's project goals. Based on the workflows described (Daily Digest, Photo Search, Content Hub), propose a high-level architecture for a similar system, including a choice of core technologies and APIs.
- Create a new git worktree or branch named `feature/ai-workflow-poc` to provide an isolated environment for building the selected proof-of-concept system.
- Bootstrap the project by creating a test file (e.g., `test_digest.py`) and an empty implementation file. Guide the user through a red-green-refactor cycle, starting with a failing test that defines the first piece of required functionality.

## 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

3,030 charactersCompatible with Claude Code & Codex CLI

MANUAL SETUP STEPS

01Analyze the user's project goals. Based on the workflows described (Daily Digest, Photo Search, Content Hub), propose a high-level architecture for a similar system, including a choice of core technologies and APIs.
02Create a new git worktree or branch named `feature/ai-workflow-poc` to provide an isolated environment for building the selected proof-of-concept system.
03Bootstrap the project by creating a test file (e.g., `test_digest.py`) and an empty implementation file. Guide the user through a red-green-refactor cycle, starting with a failing test that defines the first piece of required functionality.

FIELD OPERATIONS

Local Document Semantic Search

Build a desktop application using Electron or Tauri that indexes a local folder of documents (PDFs, .md, .txt). Use an embedding model to allow the user to search their documents using natural language questions instead of just keywords.

Automated GitHub Digest Bot

Create a scheduled script (e.g., a GitHub Action) that scans a user's GitHub organization for recent PRs, comments, and issues. The script should use an AI model to generate a concise summary report and post it to a Slack or Discord channel every morning.

STRATEGIC APPLICATIONS