Skip to main content
subagent CX Codex

ai-engineer · qdhenry — Claude Code subagent: what it does, how to install

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

no license ★ 1,357 updated 2026-03-01

Install into Claude Code · Manually: put the files in place All methods and platforms ↓
.claude/agents/ai-engineer.md
Open on GitHub

What ai-engineer 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.

What it helps with

  • 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 for the agent

  • 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.

How to install ai-engineer

Manually: put the files in place

.claude/agents/ai-engineer.md

For all projects use ~/.claude/agents/. Claude delegates by the description field or an @-mention

Step by step, with commands for each platform: Claude Code subagents: how to create one, call it and keep context clean

Questions about ai-engineer

How do I install ai-engineer in Claude Code?

Add the agent definition file to your project directory at .claude/agents/ai-engineer.md.

What does the ai-engineer subagent do?

It assists with RAG architectures, prompt templates, vector database setups, and multi-agent workflows for production LLM apps.

Which MCP servers does ai-engineer require?

The configuration references context7 for fetching framework docs and sequential-thinking for step-by-step architectural planning.

Similar subagents

All subagents for AI and ML →

ai-engineer by other authors comes first.

ai-engineer VoltAgent Community The ai-engineer subagent helps design AI systems, choose models, build training pipelines, and prepare deployment. Use it when work spans research through production. CX Codex 7,687installs ai-engineer Seth Hobson The ai-engineer subagent designs LLM applications, RAG systems, and AI agents. Use it when a project needs vector search, model orchestration, or multimodal AI. CX Codex 7,687installs ai-engineer VoltAgent ai-engineer — a Codex subagent that fixes model-backed features as system failures: orchestration, tool wiring, fallbacks. Not just prompt tweaks. CX Codex ★ 6,505repo stars llm-application-dev Seth Hobson llm-application-dev adds an LLM architect agent, RAG scaffolding, and reference patterns for prompt engineering and LangChain orchestration to Claude Code. ★ 126repo stars prompt-engineer josstei prompt-engineer — a subagent for designing and testing LLM prompts. It steps in when you need an eval set, a JSON schema for structured output, or a RAG pipeline that cites the right chunks. CX Codex ★ 489repo stars rag-pipeline-builder patricio0312rev rag-pipeline-builder designs a retrieval-augmented pipeline for a document assistant: chunking, metadata, hybrid search, reranking and a way to measure retrieval quality. CX Codex +1 251installs context-window-management sickn33 The context-window-management skill helps count, trim, summarize, and route LLM context. Use it when long conversation history starts competing with the current request. CX Codex +1 1,600installs developer-kit-ai Giuseppe Trisciuoglio The developer-kit-ai plugin adds skills for prompt design, RAG pipelines, and document chunking. Use it when building applications that rely on LLMs. ★ 372repo stars langchain-development Mindrally langchain-development gives your agent a rulebook for LangChain and LangGraph work in Python: chain composition, agents, memory, RAG. Useful once a Python LLM project outgrows one file. CX Codex +1 726installs

From the same set112

The whole set →
quickstart quickstart is a command that guides a first run of the skill builder, from task questions to a validated skill with examples. CX Codex +1 ★ 1,357repo stars issue-to-linear-task issue-to-linear-task exports individual GitHub issues into Linear tasks while keeping descriptions, comment threads, milestones, and assignees intact. CX Codex +1 ★ 1,357repo stars ml-engineer The ml-engineer subagent designs and runs the full ML model lifecycle, from data pipelines to deployment and monitoring. Use it for production MLOps work. CX Codex ★ 1,357repo stars python-pro python-pro is a Claude Code subagent for Python refactoring, performance work, and complex features. It joins these coding tasks and includes tests with its changes. CX Codex ★ 1,357repo stars project-health-check project-health-check is a Claude Code command that reviews Git activity, dependencies, security findings, and Linear task metrics in a project health report. It helps identify risks to investigate. CX Codex +1 ★ 1,357repo stars setup-agent-tail setup-agent-tail is a Claude Code skill that deploys agent-tail in a project, detects its framework, installs the CLI and plugins, and routes server and browser logs to files for an agent. CX Codex +1 ★ 1,357repo stars todo-branch todo-branch executes backlog items on your active Git branch through guided phases, step-by-step approvals, and a single final commit. CX Codex +1 ★ 1,357repo stars graphql-architect The graphql-architect subagent designs and improves GraphQL APIs, covering schemas, resolvers, federation, and subscriptions. Use it for new APIs, performance audits, or refactoring. CX Codex ★ 1,357repo stars

Project sponsors

Companies that keep this analytics open