A situation we handle
How do I stop an AI agent making changes I didn't approve?
One morning the agent has 'improved' something you never asked it to touch. The reflex is a gate on everything — and now you approve every step and the speed is gone. Neither end works. The answer is authority the agent inherits.
Blanket gates make you the bottleneck; no gates make the agent the risk. The working middle is authority the agent inherits: free inside what you settled, and when a step genuinely crosses a decision you made, the choice surfaces to you first instead of being made for you. Unlimitless (Unl) holds your settled decisions with their reasoning and hands them into the agent's reasoning before it acts. 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
Free inside what you settled. A genuine crossing surfaces the choice — to you, first.
You've seen both failure modes. Approval-on-everything, where you become the slowest component in your own pipeline and the agent's speed is wasted. And open throttle, where you wake up to changes nobody authorised and spend the morning working out what moved.
Gates belong only on the load-bearing. Inside what you've settled, the agent should run free — that's the whole point of it. What makes that safe isn't surveillance; it's that your decisions and their boundaries are in the agent's reasoning before it acts, so a step that would cross one is visible as a crossing — a choice for you, not a surprise from it.
The way through
And whatever a run does, your last good decision is always intact: settled decisions are never edited and never overwritten, so the agent re-anchors on what you settled, not on its last mistake. That's the decision layer — your files are your version control's job; your decisions are ours.
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
Isn't the fix just requiring approval on everything?
That fixes the surprise and kills the value — you become the bottleneck and the agent's speed goes to waste. Gates belong only on the load-bearing: the agent runs free inside what you settled, and a step that genuinely crosses one of your decisions surfaces as a choice for you first.
Does Unl undo what an agent broke?
No — that's the decision layer, not file recovery. Your files are your version control's job. What Unl keeps intact is the layer above: your settled decisions and their reasoning are never edited and never overwritten, so after a bad run the agent re-anchors on what you settled rather than on its own last mistake.
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
Save the thoughts, decisions and targets worth keeping, each with its reasoning, carried into every AI session the moment they matter. A new unit of exchange between you and your AI: the Settled Why with standing that travels. Unprompted.
Your whole AI world. What you decided at the epicentre. It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector — quick to connect, in a couple of steps.
MCP native·Human settled·Model agnostic·Your data
Accurate Autonomy
Connect Unl to run agent fleets without an orchestrator.
Inherited Initiative in each agent, Unlimitless Agent Stigmergy across the fleet — your frame does the coordinating.
The full product, open. Free at launch.