A situation we handle
How do I stop AI undoing decisions we already made?
The decision was made weeks ago — argued out, settled, written down. Then the agent rebuilt the thing the other way. Not malice, and not a lapse: the decision never reached it as a decision.
When an agent undoes a decision you already made, the miss is structural: your call existed as text in a doc — maybe — never as authority in the agent's reasoning. Unlimitless (Unl) holds each settled decision with its why and hands it into the agent's reasoning before it acts — unprompted. It's just-in-time context; the human stays in command. Works across Claude, Claude Code, ChatGPT and Cursor over MCP. Free at launch.
Why this matters
The agent never had your decision as authority. At best it had it as text.
You settled it in review. Everyone moved on. Three sessions later the agent has quietly reintroduced the exact pattern you ruled out, and you're re-litigating a closed question with a machine. It reads like sabotage. It's plumbing.
A decision that lives in a document is just more text — one paragraph among thousands, with nothing that marks it as settled and nothing that carries why. For a decision to hold, it has to reach the model before it acts, as a decision: what you chose, what you ruled out, and the reasoning that closes the question.
The way through
With Unl, decisions arrive before actions: when a step touches something you decided, that decision and its why are in the agent's reasoning before it acts — unprompted. Decisions that hold.
With Unl you author the brief, hand it off, and the agent executes inside what you settled — full speed on the mechanical work, your decisions arriving in its reasoning before it acts on the parts that need them. And done stays yours to say.
Questions people ask
Why does my AI keep reopening decisions we closed?
Because it never had the decision as authority — only, at best, as text somewhere in its context. Text carries the what, not the why, and nothing marks it as settled; so the model re-derives its own answer. Unl holds the decision with its reasoning and hands it into the agent's reasoning before it acts, so the question stays closed.
We write decisions in our docs — why doesn't that work?
A doc is read at most once, at the start of a session, and a decision in it is one paragraph among thousands. What makes a decision hold is arriving at the moment it bears on the work, marked as settled, with its why attached. That's the part a static document structurally can't do — and the part Unl does.
Which AI tools does this work with?
Unl is one connection over MCP, so it hands your settled decisions to Claude, Claude Code, ChatGPT and Cursor alike. The call you settle on one surface is inherited on the others.
What this is
Think inside your AI world — you stay in command
Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.
It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.
Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:
Alpha is invite-only · free at launch.