Facio Blog
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 106-110 of 235 articles.
Human-in-the-loop
Your HITL system approved a bad action. The customer is harmed. The audit trail shows the human said yes. Now what? Most teams don't have a HITL incident response procedure — they treat it like a software incident when it's actually three incidents in one. Here's the playbook.
Engineering
Playwright MCP — Microsoft's official browser-automation server with 20+ tools, multi-browser support (Chromium, Firefox, WebKit), and the accessibility-snapshot model that beats vision-based clicking on cost, resilience, and model compatibility. Apache 2.0.
Product
The first AI agent workflow you ship determines whether your team ever ships a second one. Most teams make the same mistake: they pick their most ambitious, highest-impact use case for the pilot — and when it fails or underperforms, the team concludes "AI agents don't work for us." Facio's approach is the opposite. Start small, ship the boring workflow, build trust, then expand. Here's the graduated deployment methodology and why the choice of first workflow is the most important product decision you'll make.
Security
You get paged at 3 AM. The agent is calling APIs at 10x normal rate, your SIEM is silent, your audit trail has the first 200 events but not the last 8,000, and the compliance officer needs an incident timeline by 9 AM. The agent runtimes that survive this are the ones built for it.
Human-in-the-loop
You're shipping an AI agent to production in a regulated industry. The compliance team is asking how HITL works. The security team is asking how to audit it. The legal team is asking who is liable. This is the executive briefing document that answers all three — and survives scrutiny from all three.