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 21-25 of 81 articles.

Product

Facio's Multi-Provider Architecture: How switch_model Enables Dynamic Model Routing

Jun 4, 2026Product

Facio's Multi-Provider Architecture: How switch_model Enables Dynamic Model Routing

Locking an AI agent to a single model provider is like locking a developer to a single programming language — it works until it doesn't. Facio's switch_model tool lets agents change LLM providers mid-conversation with human approval, enabling cost-optimized routing, provider fallback, and capability-aware task delegation across OpenAI, Anthropic, Google, OpenRouter, and any OpenAI-compatible endpoint.

Human-in-the-loop

Synchronous vs. Asynchronous HITL: When to Block the Workflow and When to Let It Continue

Jun 4, 2026Human-in-the-loop

Synchronous vs. Asynchronous HITL: When to Block the Workflow and When to Let It Continue

The biggest architectural decision in HITL isn't which framework to use — it's whether your approval gates should block execution or let the workflow continue. Synchronous HITL halts everything. Asynchronous HITL keeps moving. Both are right. Neither is right everywhere. Here's how to decide.

Product

Facio's Heartbeat System: How Interval-Based Task Polling Complements Cron Scheduling

Jun 3, 2026Product

Facio's Heartbeat System: How Interval-Based Task Polling Complements Cron Scheduling

Cron is perfect for "run this at 9 AM every Monday." It's the wrong tool for "check if there's something to do every 5 minutes." Facio's Heartbeat system fills that gap — a configurable polling interval that reads HEARTBEAT.md and executes pending tasks, with file-based task management that agents can modify at runtime.