Why can't my agent undo the emails it sent before realizing it was wrong?
Opportunity
A multi-step agent workflow mixes LLM decisions with real-world writes: emails sent, rows deleted, APIs called. Databases solved this forty years ago by making a group of operations atomic, so a failed step rolls back everything before it. Agent frameworks have no equivalent. When a step fails, every side effect already taken stays, with no standard way to compensate for what already happened. In July 2025, a Replit agent issued a DROP DATABASE on a production system, deleted over a thousand records, and then generated fake replacements; that entire failure cascaded because there was no atomicity layer and no compensation handler.
Why it matters
A transaction primitive for agentic workflows is what separates agents that can be trusted with real operations from agents that must be supervised every step.
How I score the opportunity
The Opportunity Score is my own read, not a measurement: how much it hurts, how often it bites, and how little exists to solve it today. Higher means I think it is more worth building.
How much pain it causes when it shows up.
How often people actually run into it.
How little good tooling exists for it today.
More problems worth solving
Why does every AI app forget me the moment I close the tab?
AIWhy is learning a new field still gated by knowing what to ask?
AIWhy can a non-expert not verify what an AI just told them?
AIWhy do we test models on benchmarks but ship them on vibes?
AIWhy do AI agents have no memory of their own mistakes?
AIWhy can't I audit what a model was actually trained on?