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.

Clear

Showing 51-55 of 73 articles in Human-in-the-loop.

Human-in-the-loop

HITL for Code Generation Agents: Why 'Looks Good' Approvals Are Creating Production Incidents

Jun 17, 2026Human-in-the-loop

HITL for Code Generation Agents: Why 'Looks Good' Approvals Are Creating Production Incidents

Code generation agents are the fastest-growing HITL use case — and the worst-implemented. Reviewers approve diffs they don't fully understand, miss subtle security flaws, and let prompt injection land in production. The 10× velocity claim isn't real if 30% of approvals are rubber-stamps.

Human-in-the-loop

HITL for Steuerberater und Wirtschaftsprüfer: The Kanzlei-Compliant Agent Architecture

Jun 16, 2026Human-in-the-loop

HITL for Steuerberater und Wirtschaftsprüfer: The Kanzlei-Compliant Agent Architecture

Steuerberater, Wirtschaftsprüfer, Notare — the DACH regulated professions face a HITL problem most generic frameworks ignore. You cannot delegate professional judgment to an agent, but you can make the agent do 90% of the work and route the 10% that requires your signature to you. Here's the architecture.

Human-in-the-loop

When AI Agents Talk to Customers: The HITL Architecture Behind Refunds, Cancellations, and Account Changes

Jun 9, 2026Human-in-the-loop

When AI Agents Talk to Customers: The HITL Architecture Behind Refunds, Cancellations, and Account Changes

A customer-service AI agent just approved a $50,000 refund — to a fraudulent account. The CFO wants answers. Here is the four-tier HITL architecture that lets customer-facing agents move at conversational speed for routine cases and force a synchronous human checkpoint for everything that can hurt the business.