Human approval, review, correction, escalation, or intervention boundaries in AI-system operation.
Tagged articles
13 articles in this tag.
A scanner that flags ten thousand findings and a researcher who proves three are both "finding vulnerabilities." Only one of them has evidence you can…
Read tutorial
The demo works. The agent reads the queue, drafts the update, and posts it. Then someone asks who approved the change, which run produced it, and how to…
Read tutorial
The demo works. The agent reaches a consequential step, pauses, and asks a human to approve. The human clicks approve. Then the resumed run re-executes the…
Read tutorial
You have a routing step in an agent pipeline. Four possible destinations. The LLM call costs a full generation, 1–2 seconds, and a token bill. The answer…
Read tutorial
Ask a system to synthesize five documents into one answer. It does the work. Ask the same question tomorrow, and it does the work again, from scratch, with…
Read tutorial
Two projects both advertise "open source, model-agnostic, multi-channel, MCP support." A builder picks one, ships it, and discovers the real difference the…
Read tutorial
A goal-based agent that never terminates is not a model failure. It is a contract failure.
Read tutorial
A coding agent is handed a fixed training script and a fixed success metric: make it run faster without breaking correctness. It rewrites, runs, times, and…
Read tutorial
That is the shape of the failure I keep seeing in agent systems that look governed and are not. A team writes a planner prompt, a coder prompt, a reviewer…
Read tutorial
The loop that improves the harness can also edit the evaluator, the permissions, and the rollback path. That is the whole problem in one sentence.
Read tutorial
Two teams ship the same model, the same prompt, the same tool list. One agent finishes a multi-step task. The other stalls, loops, and quietly corrupts its…
Read tutorial
Two seed-stage teams ship an LLM-backed product. Same headcount, same model access, same demo polish. Eighteen months later, one compounds while the other…
Read tutorial
The demo worked. Production didn't. Somewhere between the two, the system took a path nobody wrote down, and when it failed there was no artifact…
Read tutorial