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 51-55 of 235 articles.

Security

When One Compromised Agent Becomes a Hundred Compromised Systems: The Lateral Movement Architecture You Cannot Detect at the Network Layer

Jul 11, 2026Security

When One Compromised Agent Becomes a Hundred Compromised Systems: The Lateral Movement Architecture You Cannot Detect at the Network Layer

A single compromised AI coding agent pivoted through the organization's npm registry, reached the CI/CD system, and propagated a malicious package to twelve production services. The propagation was authorized; the tool calls were legitimate; the only signal was the agent's reasoning. Lateral movement through AI agents is structural, not solvable by traditional tooling.

Human-in-the-loop

HITL and the Cost of Saying No: Why Reviewer Rejection Is the Most Expensive Decision and How to Make It Worth It

Jul 11, 2026Human-in-the-loop

HITL and the Cost of Saying No: Why Reviewer Rejection Is the Most Expensive Decision and How to Make It Worth It

Most HITL systems optimize approval velocity — actions approved per hour. But the most expensive decision the reviewer can make is rejection. Rejection costs the system the work the agent did, the latency the customer waited, the customer experience of the failed action, the cost of the corrective action. The system that doesn't value rejection is the system that loses the value of the most important review decision.

Engineering

MCP Spotlight: Memory MCP Server — Anthropic's Reference Implementation for Persistent, Shareable, Graph-Based Agent Memory Across Conversations

Jul 10, 2026Engineering

MCP Spotlight: Memory MCP Server — Anthropic's Reference Implementation for Persistent, Shareable, Graph-Based Agent Memory Across Conversations

The official Memory MCP Server by Anthropic — 9 tools built around a graph-based knowledge model with three primitives: entities (nodes), relations (typed edges), observations (facts). JSONL storage that's persistent across sessions, version-controllable with git, and shareable across agents. MIT-licensed.

Product

Facio's Evaluation Harness: How AI Agent Quality Stays Measurable Instead of Vibes

Jul 10, 2026Product

Facio's Evaluation Harness: How AI Agent Quality Stays Measurable Instead of Vibes

"The agent feels slower today." "The agent seems to be giving worse answers." "The agent used to handle this edge case." These are real signals, but they're not actionable. Without measurement, the team can't quantify the regression, can't identify the cause, can't validate the fix, can't prevent recurrence. Facio's evaluation harness turns agent quality from vibes into metrics. The team has golden test sets, automated regression detection, prompt-version comparison, and quality dashboards. Here's how the discipline works.

Human-in-the-loop

HITL and the Asymmetric Reversibility Problem: How Irreversible Actions Require Different Oversight Patterns

Jul 10, 2026Human-in-the-loop

HITL and the Asymmetric Reversibility Problem: How Irreversible Actions Require Different Oversight Patterns

Most HITL designs treat reversibility as a binary — reversible or irreversible. The actual reality is asymmetric: some actions are reversible in cost but not in time, some are reversible for the customer but not for the company, some are reversible technically but not semantically. The HITL system must account for these asymmetries — and the oversight pattern must match the asymmetry, not the binary.