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 126-130 of 235 articles.

Human-in-the-loop

Five HITL Scaling Inflection Points: The Architecture That Breaks at Every Order of Magnitude

Jun 19, 2026Human-in-the-loop

Five HITL Scaling Inflection Points: The Architecture That Breaks at Every Order of Magnitude

The HITL roadmap that worked for five agents breaks at fifteen. The patterns that worked for one team don't transfer to five. The approval gates that worked for one action type break at thirty. Here are the five scaling inflection points and how to design for the order you'll hit them.

Engineering

MCP Spotlight: ArcadeDB — The Built-In MCP Server for the Only Multi-Model DBMS That Speaks SQL, Cypher, Gremlin, GraphQL, MongoQL & Redis

Jun 18, 2026Engineering

MCP Spotlight: ArcadeDB — The Built-In MCP Server for the Only Multi-Model DBMS That Speaks SQL, Cypher, Gremlin, GraphQL, MongoQL & Redis

ArcadeDB ships the only multi-model DBMS with a first-party built-in MCP server — 7 data models (graph, document, key/value, search, time series, vector, geospatial), 6 query languages (SQL, Cypher, Gremlin, GraphQL, MongoDB QL, Redis), 70+ graph algorithms, Apache 2.0.

Product

Facio's Reflection Process: How Periodic Memory Curation Keeps AI Agents Honest at Scale

Jun 18, 2026Product

Facio's Reflection Process: How Periodic Memory Curation Keeps AI Agents Honest at Scale

Memory that grows without curation becomes noise. Facts accumulate, contradictions pile up, stale entries linger, and the agent's passive context fills with information that no longer matters. Facio's Reflection process is the periodic curator that keeps MEMORY.md honest — identifying staleness, resolving contradictions, consolidating patterns, and pruning noise. Here's how the curator works and why automated memory hygiene is a non-negotiable for production agents.

Human-in-the-loop

The Reviewer Doesn't Know What the Agent Knows: Closing the Information Asymmetry in HITL

Jun 18, 2026Human-in-the-loop

The Reviewer Doesn't Know What the Agent Knows: Closing the Information Asymmetry in HITL

Most HITL designs assume the human knows what's being asked of them. But the reviewer's mental model — what the agent is doing, why, with what risk — is often incomplete or wrong. The agent knows things the reviewer doesn't. The reviewer guesses. The guess becomes the decision. How to fix the information asymmetry.

Engineering

MCP Spotlight: Agent Config — The Universal AI Agent OS With 227 Skills, 79 Rules, 150 Commands & 6 Role-Shaped Profiles

Jun 17, 2026Engineering

MCP Spotlight: Agent Config — The Universal AI Agent OS With 227 Skills, 79 Rules, 150 Commands & 6 Role-Shaped Profiles

Agent Config is the first AI Agent OS: 227 skills, 79 rules, 150 commands, 6 role-shaped profiles (developer, founder, creator, agency, finance, ops), projected into 12 host tools (Claude Code, Cursor, Augment, Windsurf, Copilot) from one npm package.