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 26-30 of 281 articles.

Engineering

MCP Spotlight: Linear MCP Server — The Official Engineering-Execution Bridge With Read-by-Default Tools, Project Status Updates, and the Issue-Tracking Default for Agents

Jul 30, 2026Engineering

MCP Spotlight: Linear MCP Server — The Official Engineering-Execution Bridge With Read-by-Default Tools, Project Status Updates, and the Issue-Tracking Default for Agents

The official Linear MCP Server by Linear — ~25 focused tools covering issues, projects, cycles, initiatives, customers, with read-by-default semantics and structured filter syntax. OAuth 2.0 with principle-of-least-privilege scopes. Project update primitive for stakeholder communication. MIT-licensed.

Product

Facio's Credential Lifecycle Discipline: How AI Agents Hold Secrets for Exactly as Long as They Need Them — and Never Longer

Jul 30, 2026Product

Facio's Credential Lifecycle Discipline: How AI Agents Hold Secrets for Exactly as Long as They Need Them — and Never Longer

AI agents authenticate to systems. The systems require credentials. The naive approach gives the agent long-lived secrets that sit in memory, logs, and context for months. Facio's credential lifecycle discipline gives AI agents short-lived, scoped, rotating credentials: just-in-time issuance scoped to minimum required permission, automatic rotation based on stakes, credential isolation from agent context, and fast revocation. The credential is issued when needed, scoped to the work, rotated frequently, and revoked when done. The exposure window is shrunk.

Human-in-the-loop

HITL and the Counterfactual Review: Why the Best Decisions Are Made by Reviewers Who Consider What They Would Have Done Without the System

Jul 30, 2026Human-in-the-loop

HITL and the Counterfactual Review: Why the Best Decisions Are Made by Reviewers Who Consider What They Would Have Done Without the System

The best reviewers pause to ask: "what would I have done if this action had been proposed by a human, not an agent?" The counterfactual review sharpens judgment, removes deference bias, and produces decisions that defend themselves on their own merits. Here is why the counterfactual is HITL's most underrated mental discipline — and how to design systems that train reviewers to ask it.

Engineering

MCP Spotlight: Memory MCP Server — Anthropic's Reference Implementation for Persistent Knowledge Graphs, Entity-Relation Schema, and the Long-Term-Memory Default for Agents

Jul 29, 2026Engineering

MCP Spotlight: Memory MCP Server — Anthropic's Reference Implementation for Persistent Knowledge Graphs, Entity-Relation Schema, and the Long-Term-Memory Default for Agents

The official Memory MCP Server by Anthropic — 9 tools (create_entities, create_relations, add_observations, search_nodes, open_nodes, read_graph, delete_*) built around a knowledge graph primitive. Local JSON file persistence by default. Typed entities + typed relations + append-only observations. MIT-licensed.

Product

Facio's Decision Tracing Discipline: How AI Agents Make Their Reasoning Inspectable Before, During, and After Every Action

Jul 29, 2026Product

Facio's Decision Tracing Discipline: How AI Agents Make Their Reasoning Inspectable Before, During, and After Every Action

AI agents make decisions. The decisions chain into actions. The actions reach the customer. Without decision tracing, the agent is a black box: the team can't debug, the auditor can't verify, the customer is left doubting without evidence. Facio's decision tracing discipline gives agents structured mechanisms to capture, surface, and preserve reasoning at every decision point: reasoning capture, decision provenance, trace storage and queryability, multi-audience surfacing, and trace replay. The reasoning is complete, inspectable, and accountable.