# ai-engineer

ai-engineer designs RAG pipelines, configures vector databases, and writes agent workflows for LLM applications. Built for developers adding AI features.

- subagent · `type=agent` · Claude Code, Codex, Cursor · ★ 1357 repo stars
- Author: qdhenry
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/data-ai/ai-engineer.md
- Updated: 2026-03-01
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/agents/qdhenry-ai-engineer

## What it does

Running on the Sonnet model, this subagent handles the mechanics of building LLM-driven software. It designs vector retrieval pipelines, configures databases like Pinecone, Weaviate, or Chroma, and connects models from OpenAI, Anthropic, or Google. The agent follows an iterative approach, enforcing structured outputs like JSON and writing tests alongside application code.

It relies on built-in editing tools alongside two dedicated MCP connections. The subagent queries `context7` to inspect framework documentation and uses `sequential-thinking` to reason through multi-step architectures. Missing MCP servers will limit its research and planning abilities.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/agents/ai-engineer.md` — For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

### Codex

**Manually: put the files in place**
- File: `.codex/agents/ai-engineer.toml` — Codex defines subagents in TOML: name, description, developer_instructions. Move the Markdown text into developer_instructions by hand. For all projects use ~/.codex/agents/

### Cursor

**Manually: put the files in place**
- File: `.cursor/agents/ai-engineer.md` — Cursor also reads .claude/agents/

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/qdhenry/Claude-Command-Suite/tree/HEAD/.claude/agents/data-ai/ai-engineer.md

## When to use it
- design a RAG architecture with vector retrieval
- connect LLM APIs from Anthropic, OpenAI, or Google
- set up multi-agent workflows using LangChain or LangGraph
- reduce token usage across prompt pipelines

## Example prompts
- Set up a retrieval pipeline using Chroma for product documentation.
- Implement API error handling and retries for Anthropic completions.
- Build a structured JSON extractor with a reusable prompt template.

## Similar
- [llm-application-dev](https://affpapa.org/en/nevibecode/plugins/seth-hobson-llm-application-dev.md) — plugin · ★ 126 repo stars
- [prompt-engineer](https://affpapa.org/en/nevibecode/agents/josstei-prompt-engineer.md) — subagent · ★ 489 repo stars
- [rag-pipeline-builder](https://affpapa.org/en/nevibecode/skills/rag-pipeline-builder.md) — skill · 251 installs
- [context-window-management](https://affpapa.org/en/nevibecode/skills/sickn33-context-window-management.md) — skill · 1600 installs
- [developer-kit-ai](https://affpapa.org/en/nevibecode/plugins/developer-kit-ai.md) — plugin · ★ 372 repo stars
- [langchain-development](https://affpapa.org/en/nevibecode/skills/langchain-development.md) — skill · 726 installs

## Other versions with the same name
- [ai-engineer · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-community-ai-engineer.md) — 7687 installs
- [ai-engineer · wshobson](https://affpapa.org/en/nevibecode/agents/ai-engineer.md) — 7687 installs
- [ai-engineer · voltagent](https://affpapa.org/en/nevibecode/agents/voltagent-ai-engineer.md) — ★ 6505 repo stars

From the same set: [qdhenry/claude-command-suite](https://affpapa.org/en/nevibecode/by/qdhenry/claude-command-suite.md) — 112 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
