What it does
The ai-engineer agent covers end-to-end AI systems in two areas. The first is classical machine learning, including model selection, training pipelines and production serving. The second is generative AI and LLM application engineering, including retrieval-augmented generation (RAG), agentic tool use, LLM API integration and evaluations (evals).
It suits work that needs architecture, model choice, training setup and deployment decided together. The publisher's examples include a recommendation engine with a latency target under 100 ms, where the agent proposes a model type such as LightGBM/XGBoost or a two-tower embedding model, a Feast feature store for training, and ONNX Runtime or TensorRT for inference.
It also addresses optimizing a working research model for production. The publisher's example is a PyTorch model that must serve high request volumes with sub-50 ms latency, where the suggested techniques are post-training INT8 quantization, structured pruning and knowledge distillation, combined with dynamic batching and response caching. The agent is listed as an agent component in the claude-code-templates collection.
Safety
Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.
- Runs code or changes an assistant's behaviour
Sources
- AI Templates (aitmpl) first seen 13 Nov 2026 · last seen 17 Nov 2026 · its page on the source · figures reported by the source: aitmpl downloads 7936
ai-engineer
Use this agent as the generalist entry point for end-to-end AI systems spanning both classical ML (model selection, training pipelines, production serving) and generative-AI/LLM application engineering (RAG, agentic tool use, LLM API integration, evals). Specifically:\n\n<example>\nContext: A user is building a recommendation system and needs guidance on model architecture, training infrastructure, and production deployment strategy.\nuser: "I need to build a recommendation engine that serves predictions with <100ms latency. What's the best approach for model selection, training infrastructure
As shown on www.aitmpl.com when we last read it