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 6-10 of 281 articles.

Human-in-the-loop

HITL and the Epistemic Asymmetry: Why the Reviewer Knows Less About the Agent's Reasoning Than the Agent Knows About the Reviewer's Decision

Aug 5, 2026Human-in-the-loop

HITL and the Epistemic Asymmetry: Why the Reviewer Knows Less About the Agent's Reasoning Than the Agent Knows About the Reviewer's Decision

The reviewer sees the agent's final proposal. The reviewer doesn't see the agent's reasoning chain, the agent's uncertainty distribution, or the agent's alternative considerations. The agent sees everything the reviewer does: the decision, the reasoning, the timestamp, the audit trail. The information flows one way. The epistemic asymmetry produces rubber stamps, false confidence, and reviews that can't defend themselves. Here is why the asymmetry is HITL's most fundamental design flaw — and how to fix it.

Engineering

MCP Spotlight: Sequential Thinking MCP Server — Anthropic's Reference for Structured Reasoning, Reflective Loops, and the Reasoning-Default for Agents

Aug 4, 2026Engineering

MCP Spotlight: Sequential Thinking MCP Server — Anthropic's Reference for Structured Reasoning, Reflective Loops, and the Reasoning-Default for Agents

The official Sequential Thinking MCP Server by Anthropic — 1 tool (sequential_thinking) with explicit numbered thought steps, revision of earlier thoughts, and branchable parallel investigations. MIT-licensed. The structured-reasoning default for AI agents in 2026.

Product

Facio's Action Execution Discipline: How AI Agents Carry Out Side-Effecting Operations Safely Without Breaking Production

Aug 4, 2026Product

Facio's Action Execution Discipline: How AI Agents Carry Out Side-Effecting Operations Safely Without Breaking Production

AI agents take actions with real-world consequences: delete records, send emails, charge cards, deploy to production. The naive approach lets the agent act whenever it decides. Facio's action execution discipline gives agents structured mechanisms to carry out side-effecting operations safely: declaration before execution, pre-execution validation against authorization and scope, approved channels for execution, idempotency with duplicate prevention, and post-execution verification with comprehensive audit trails. The damage is contained.

Human-in-the-loop

HITL and the Decision Latency Exposure: Why the Time Between the Agent's Proposal and the Reviewer's Approval Is Itself a Risk Variable

Aug 4, 2026Human-in-the-loop

HITL and the Decision Latency Exposure: Why the Time Between the Agent's Proposal and the Reviewer's Approval Is Itself a Risk Variable

Every second between the agent's proposal and the reviewer's approval is a second the world changes. The customer's context drifts. The customer's emotional state shifts. The competitor's offer arrives. The agent's proposal ages. The reviewer's decision is being made on stale data, but the reviewer doesn't know how stale. Here is why decision latency is HITL's most underrated exposure variable — and how to design systems that treat time as a first-class risk signal.

Engineering

MCP Spotlight: Notion MCP Server — The Official Workspace Bridge With Markdown-First Formatting, OAuth Workspace Scope, and the Knowledge-Default Reference for Agents

Aug 3, 2026Engineering

MCP Spotlight: Notion MCP Server — The Official Workspace Bridge With Markdown-First Formatting, OAuth Workspace Scope, and the Knowledge-Default Reference for Agents

The official Notion MCP Server by Notion — ~22 focused tools (search, fetch, create, update, delete, comment) with Markdown-first formatting (no block JSON). OAuth 2.0 with workspace scope for SaaS, internal integration tokens for self-hosted. Apache 2.0-licensed. The knowledge-workspace default for AI agents in 2026.