AI HOT (Curated Pool)Jul 8, 2026, 08:00 UTC+8

The AI Preflight Check: A Working Memory Architecture for Agents

AI预检检查：智能体工作记忆架构

Tomasz Tunguz describes a memory architecture for AI agents built around a preflight check. When a query arrives, the agent retrieves only the relevant skills from a long-term library and loads them into the context window. A local Ornith 35B model executes routine tasks about 80% of the time, routing hard cases to frontier models. A watchdog logs every decision and runs overnight asynchronous inference to suggest new skills or convert parts of existing skills into deterministic code. Yesterday was the first day the watchdog suggested no improvements, hinting the system may plateau where only genuinely new exceptions need human help. The post does not disclose latency, cost, or accuracy figures.

Why it matters: Tomasz Tunguz shares a hands-on agent memory architecture with concrete numbers—not a product launch but a named first-person experiment. Score capped because the body is truncated and the watchdog's async reasoning details aren't fully shown.

Read the original ↗Export Markdown

Take

This is worth reading because it's a real architecture someone built and runs in their own workflow, not a diagram. Tunguz breaks memory into three steps: a preflight check that retrieves only the relevant skills from a library of about 90 into the context window; a local Ornith 35B model that handles roughly 80% of routine tasks, routing hard cases to frontier models; and a watchdog that reads the full decision trail overnight, asynchronously suggesting new skills or converting parts of existing ones into deterministic code. Yesterday was the first day the watchdog suggested nothing, which he takes as a hint the system may be plateauing—only genuinely new exceptions would need human help from here.

I'd discount this a bit: no latency, cost, or accuracy numbers are disclosed. 80% local execution sounds like it saves API spend, but we don't know the actual response time of Ornith 35B on Apple Silicon. The skill library uses intent-match retrieval across ~90 files, and match precision isn't mentioned. This reads more like an engineering log for a personal productivity tool than a generalizable product. The concrete bit I like is the direction: turning LLM work into Rust code where it doesn't belong—calendar scheduling really shouldn't use a model to compare free and busy slots.

Source: AI HOT (Curated Pool) · tomtunguz.com
Published: Jul 8, 2026, 08:00 UTC+8 · Jul 8, 2026