Facio Blog

Practical notes on human-reviewed AI agents.

Payload-powered product notes, security writing, HITL patterns, and operational guidance from the Facio runtime: long sessions, Placet approvals, audit trails, memory, providers, channels, tools, and Docker-first operations.

Showing 16-20 of 57 articles in Human-in-the-loop.

Human-in-the-loop

HITL and the Cost of Saying Yes: Why Reviewer Approval Velocity Is the Wrong Optimization Target

Jul 7, 2026Human-in-the-loop

HITL and the Cost of Saying Yes: Why Reviewer Approval Velocity Is the Wrong Optimization Target

Every HITL dashboard celebrates approval velocity — actions approved per hour, queue cleared per shift, throughput maximized per reviewer. But "yes" is the cheapest possible review decision. The system optimizes for the wrong thing. Real review quality means saying no when the action is wrong, asking questions when the context is unclear, and requesting changes when the action is incomplete. Here's why the cost of yes is the hidden tax on your HITL system.

Human-in-the-loop

HITL Observability: Why the Agent Must Be Transparent to the Reviewer (and Not Just to the Developer)

Jul 6, 2026Human-in-the-loop

HITL Observability: Why the Agent Must Be Transparent to the Reviewer (and Not Just to the Developer)

Most agents are transparent to developers — trace logs, reasoning chains, debug panels. But they're opaque to reviewers, who see only the final action proposal. Reviewers make worse decisions on opaque agents — they rubber-stamp what they can't evaluate. The HITL system needs its own observability layer, designed for the reviewer's eyes, not the developer's.

Human-in-the-loop

The HITL Boundary Problem: Where Exactly Does the Agent Stop and the Human Start?

Jul 5, 2026Human-in-the-loop

The HITL Boundary Problem: Where Exactly Does the Agent Stop and the Human Start?

Most HITL posts assume the boundary between agent and human is obvious. It's not. The boundary is contested, contextual, and constantly shifting. The agent does some preparation, the human does some finalization, the agent does some cleanup. Where exactly does oversight end and execution begin? The boundary problem is the deepest architectural challenge in HITL — and the one most teams don't even realize they're facing.

Human-in-the-loop

HITL for Production Incidents: When the Agent Becomes the On-Call Rotation

Jul 4, 2026Human-in-the-loop

HITL for Production Incidents: When the Agent Becomes the On-Call Rotation

AI agents are increasingly the first responders to production incidents. They detect, triage, and remediate before humans wake up. But the HITL pattern for incident response is the highest-stakes variant of all — wrong action can take down production, the human reviewer is sleep-deprived, and the rollback window is closing. Here's how to design HITL for incidents.

Human-in-the-loop

HITL and the Audit Trail of Doubt: Why the Reviewer's Uncertainty Is the Most Valuable Signal

Jul 3, 2026Human-in-the-loop

HITL and the Audit Trail of Doubt: Why the Reviewer's Uncertainty Is the Most Valuable Signal

Most HITL audit trails record what the reviewer decided. The best HITL audit trails record what the reviewer was uncertain about. Doubt is the signal that catches what confidence misses — the inklings, the hesitations, the "I'm not sure but I can't quite place why" moments that turn out to be the early warnings of failures. Here's why the audit trail of doubt matters more than the audit trail of decisions.