human-in-the-loop

Interactive local workspace for reviewing and iterating on Markdown and agent-generated HTML artifacts

A calm way for your coding agent to ask you for decisions: one HTML page of question cards that you answer in any…

Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native…

Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.

Ask before AI agents pay, share data or act: allow, deny or ask a person, with signed receipts.

An agent asks a human questions. Create a questionnaire, inspect or edit it on the private manage link, paste the…

Build CopilotKit + AG-UI web apps on Microsoft Foundry hosted agents (Microsoft Agent Framework): wiring, native…

A communication layer for your AI coding agent: plain language, no jargon, no invented timelines, and one clear yes…

Self-coordinating Codex engineering team for interfaces that expose agent conclusions, supporting evidence, provenance,…

Pause agent work, poll for durable human decisions, and resume safely through Attenza.

A human-governed, resumable engineering workflow for coding agents.

Let your agent ring your iPhone, read you a question, an update or your day ahead, and get your spoken reply back as…

Minimalist Human-in-the-Loop & LLM Output Ranking Arena with preference convergence.

PRsquad: Supervised Agentic Workflow for GitHub Copilot. Supervised multi-agent autonomy with deterministic policy…