Agents and tool use · MLD-0528
Human-in-the-loop
A design requiring human input, review, or approval at selected stages.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Require approval before an external action.
Original caveat
Review quality depends on time, information, and authority.
Context and aliases
Level: Intermediate. Stages: Inference · Deployment · Evaluation.
Tags: SLM · LLM · RL · Agents.
Aliases: HITL.
Related concepts
Concepts linking here
Technology connections
- Chainlit — Toolkit for conversational AI interfaces.
- FastAPI — Python framework for typed HTTP APIs.
- Flask — Minimal Python web application framework.
- Gradio — Python toolkit for interactive model demos.
- JupyterLab — Interactive notebook and development environment.
- marimo — Reactive Python notebook system.
- Panel — Python toolkit for interactive dashboards and applications.
- Streamlit — Python framework for data and AI web applications.
- Vercel AI SDK — TypeScript toolkit for model integration and streaming interfaces.
Original references
- Anthropic: Building effective agents ↗ · Reference link
- Model Context Protocol Python SDK: first steps ↗ · Consulted
- ReAct: Synergizing Reasoning and Acting in Language Models ↗ · Reference link
- Original reference URL ↗