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 1-5 of 281 articles.

Product

Facio's Async Processing Discipline: How AI Agents Handle Long-Running Tasks Without Blocking Conversations, Losing State, or Breaking the Customer Experience

AI agents process long-running tasks: data analysis, batch operations, model training, multi-stage workflows. The naive approach blocks the conversation until the task completes — the customer waits, the connection times out, the state is lost. Facio's async processing discipline gives agents structured mechanisms to handle long-running tasks without blocking: non-blocking task submission with submission metadata, state persistence with checkpointing, progress indication with multiple progress types, task recovery from transient and worker failures, and completion notification via registered channels.

Aug 7, 2026Product

Read article

Human-in-the-loop

HITL and the Recency Trap: Why Reviewers Who Optimized for Last Quarter's Failures Will Miss This Quarter's

Aug 7, 2026Human-in-the-loop

HITL and the Recency Trap: Why Reviewers Who Optimized for Last Quarter's Failures Will Miss This Quarter's

Every HITL team tunes their reviewers based on the failures they've seen. The tuning works for the failures that already happened. The tuning fails for the failures that haven't happened yet. The recency trap — over-optimizing for the most recent failure mode — is HITL's most predictable self-inflicted wound. Here is why the trap works, how it produces invisible failures, and how to design systems that stay current without becoming reactive.

Product

Facio's System Prompt Discipline: How AI Agent Behavior Stays Bounded, Auditable, and Evolvable Without Becoming a Black Hole of Hidden Instructions

Aug 6, 2026Product

Facio's System Prompt Discipline: How AI Agent Behavior Stays Bounded, Auditable, and Evolvable Without Becoming a Black Hole of Hidden Instructions

AI agents follow system prompts that define role, tool usage, output format, refusal patterns, escalation rules, and behavioral boundaries. The naive approach writes one giant unstructured prompt that becomes an ungovernable black box. Facio's system prompt discipline gives agents structured mechanisms to define, version, audit, test, and evolve the behavioral contract: prompt decomposition into named sections, per-section versioning with full history, audit capabilities showing what the agent was told and when, prompt testing for behavioral verification, and safe evolution via feature flags and rollout strategies.

Human-in-the-loop

HITL and the Approval Refusal Problem: Why Reviewers Who Never Reject Are Not Engaged — They're Coasting

Aug 6, 2026Human-in-the-loop

HITL and the Approval Refusal Problem: Why Reviewers Who Never Reject Are Not Engaged — They're Coasting

Every HITL team has a reviewer who approves everything. The metrics look great: low latency, high throughput, zero escalations. The reviewer is celebrated. The reviewer is, in fact, coasting. The approval refusal rate is the most reliable signal of reviewer engagement — and the one most teams refuse to track. Here is why the absence of rejections is a red flag, not a green light, and how to design HITL systems that detect coasting before it becomes institutional.

Product

Facio's Orchestration Discipline: How AI Agents Coordinate Multi-Step Workflows Without Losing Track, Running in Circles, or Breaking the Process

Aug 5, 2026Product

Facio's Orchestration Discipline: How AI Agents Coordinate Multi-Step Workflows Without Losing Track, Running in Circles, or Breaking the Process

AI agents orchestrate multi-step workflows with tool calls, decisions, retries, branches, parallelism, and humans in the loop. The naive approach lets the agent decide at each step what to do next. The agent loses track. The agent runs in circles. Facio's orchestration discipline gives agents structured mechanisms to coordinate multi-step workflows reliably: workflow declaration with explicit steps, state tracking through execution, process enforcement against the declared definition, branching and parallelism for complex workflows, and recovery via checkpoints and compensation actions. The work gets done.