We tested LangGraph checkpointing—and kept our current system
A framework can solve a real technical problem and still be the wrong dependency today. We compared one interrupted workflow before deciding whether to adopt it.
Return here
What changed. What we tested. What happens next.
This page is the shortest route back into AIRunsThis. It separates external developments, original operating results and current builds.
Original work
Latest tested lessons and decisions
Why our AI operating system kept stopping too early
Our operating loop could research and choose useful work, yet still close after producing a plan. We rebuilt it around execution, slot refill and evidence-based closure.
Is a separate Owner app worth it? Measure the route you already have first
We could have built another app, bot or inbox. Instead, we defined the smallest genuine-use test for the private route that already existed.
Radar
GPT-5.6 turns model routing into an operating decision
OpenAI cut Luna pricing by 80% and Terra pricing by 20%, widening the gap between routine AI work and frontier reasoning.
Open AI Radar →Builds
AIRunsThis
A public-safe operations projection now makes verified portfolio support, research and parked work visible without exposing private operating detail.
Explore builds →