The missing layer between a scheduled prompt and an agent that learns.
A scheduled agent without state is a cron job with a language model attached. It scans the same sources, scores the same items, and hands you the same briefing it handed you yesterday. The fix is not a better prompt — it is a state file the agent reads on the way in and writes on the way out.
This pack is five such patterns, each with the YAML template and the JSON state schema that goes with it: delta detection for market and price scanners, carry-forward for briefings and to-do agents, topic lifecycle for research scanners, signal evolution for trend tracking, and baseline diff for security and health checks.
CRON-INTEGRATION.md covers wiring state reads and writes into an agent prompt you already have. COLD-START.md covers the first run, when there is no history to read yet — the case most stateful designs forget about.
Turn your AI agents from re-prompts into self-improving loops. 5 stateful loop patterns + 5 JSON schemas + cron integration playbook.
★ BEST VALUEEverything: Blueprint + 5 automation packs + Agentic Loops Pack. 7 packs, 124 files. $211 of packs for $149. Lifetime updates.

A complete guide + templates for building a multi-agent AI OS that thinks, researches, and acts for you — 24/7.
The complete guide to building a Personal AI OS — plus the stateful loop patterns that turn it from re-prompts into self-improving agents. Built from a real 11-agent system running 24/7.