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 166-170 of 281 articles.

Human-in-the-loop

Right-Sized HITL: The Action Classification Engine That Decides What Actually Needs a Human

Jun 21, 2026Human-in-the-loop

Right-Sized HITL: The Action Classification Engine That Decides What Actually Needs a Human

The HITL industry is converging on a wrong assumption: that every AI action should have a human in the loop. The right architecture isn't 100% HITL — it's right-sized HITL. Most actions should be autonomous. Some should be sampled. A few need synchronous review. The challenge is mapping the right oversight to the right action.

Engineering

MCP Spotlight: Atlassian Rovo MCP Server — The Official Jira, Confluence & Compass Bridge That Went GA With OAuth 2.1, Claude First Partner

Jun 20, 2026Engineering

MCP Spotlight: Atlassian Rovo MCP Server — The Official Jira, Confluence & Compass Bridge That Went GA With OAuth 2.1, Claude First Partner

Atlassian's official Rovo MCP Server — GA February 2026 with Claude as first partner — exposes Jira, Confluence, Compass, and Jira Service Management via OAuth 2.1 with per-request scopes, JQL/CQL passthrough, and full tool annotations.

Product

Facio's Checkpoint Discipline: How Periodic State Snapshots Let AI Agents Resume After Crashes and Budget Exhaustion

Jun 20, 2026Product

Facio's Checkpoint Discipline: How Periodic State Snapshots Let AI Agents Resume After Crashes and Budget Exhaustion

An AI agent that loses its work to a crash, an exhausted budget, or a network failure is starting over from scratch. The hours of research, the partially-completed deployment, the half-written report — all gone. Facio's checkpoint discipline turns sessions into resumable workflows through periodic state snapshots persisted to the workspace. Here's how checkpoints work, when the agent takes them, and why checkpoint-aware agents finish work that checkpoint-blind agents abandon.

Human-in-the-loop

Who Is Liable When the Human Approves a Bad Action? The Accountability Chain in HITL

Jun 20, 2026Human-in-the-loop

Who Is Liable When the Human Approves a Bad Action? The Accountability Chain in HITL

When an AI agent takes a bad action and a human approved it, who is legally liable? The agent's vendor, the deployer, the reviewer, the manager — the answer is unclear and inconsistent across jurisdictions. Here's how the accountability chain works, where it breaks, and what the audit trail must capture to make the answer defensible.

Engineering

MCP Spotlight: WhisperGraph — 7.39B-Node DNS/BGP/Threat-Intel Graph MCP With 6 Tools & Open Cypher Query

Jun 19, 2026Engineering

MCP Spotlight: WhisperGraph — 7.39B-Node DNS/BGP/Threat-Intel Graph MCP With 6 Tools & Open Cypher Query

WhisperGraph MCP gives AI agents a single read-only MCP interface to a 7.39B-node, 39B-edge graph covering DNS, BGP, WHOIS, GeoIP, certificates, and 40 threat feeds — queryable in Open Cypher. Self-hostable, free open-data tier, 6 tools + 6 resources + 8 prompts.