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 141-145 of 281 articles.

Human-in-the-loop

HITL and Model Versioning: How Approval Patterns Change When the LLM Changes

Jun 28, 2026Human-in-the-loop

HITL and Model Versioning: How Approval Patterns Change When the LLM Changes

You upgraded the LLM from claude-opus-4-7 to the next generation. The HITL override rate spiked from 4% to 12% overnight. The same reviewer pool is rejecting 3× more actions. The same policy is firing 5× more synchronous reviews. Model upgrades don't just affect outputs — they affect the entire HITL calibration. Here's how to manage the version transition.

Engineering

MCP Spotlight: Postgres MCP Pro — Configurable Read/Write Access, Schema-Aware Index Tuning & the Safety Pattern Every Database MCP Needs

Jun 27, 2026Engineering

MCP Spotlight: Postgres MCP Pro — Configurable Read/Write Access, Schema-Aware Index Tuning & the Safety Pattern Every Database MCP Needs

Postgres MCP Pro by Crystal DBA — configurable read/write access at the database role level, schema-aware index tuning, migration generation with safety checks, EXPLAIN plan visibility, MIT-licensed. The defense-in-depth pattern every database MCP server should copy.

Product

Facio's Operational Metrics: The KPIs That Tell You Whether Your AI Agent Is Actually Working

Jun 27, 2026Product

Facio's Operational Metrics: The KPIs That Tell You Whether Your AI Agent Is Actually Working

Most teams running AI agents have no idea whether the agent is working. They count sessions and tokens, mistake volume for value, and have no metrics for agent quality, user satisfaction, or business outcome. Facio's operational metrics give you the structured KPIs that distinguish an agent that genuinely works from one that just runs. Here's the framework, the metrics that matter, and how to use them to improve agent performance over time.

Security

Your AI Agent Is the New DLP Blind Spot: Why 72% of AI Agent Pilots Have No Data Protection Layer

Jun 27, 2026Security

Your AI Agent Is the New DLP Blind Spot: Why 72% of AI Agent Pilots Have No Data Protection Layer

Traditional DLP cannot see agent-to-agent data flows, cannot redact sensitive content in tool calls, cannot enforce prompt-level redaction, and cannot audit cross-system leakage. The data exfiltration gap (covered in the Facio analysis from June 2026) is now the single largest ungoverned data channel in most enterprises.