Discovery: Be on every shelf agents search
Listed, current and described in each directory and registry an agent reads.
“The first principle is that you must not fool yourself, and you are the easiest person to fool.”
The InvokeRank method
Agent distribution comes from knowing where in the funnel agents pass you over, why, and what to change. This is our system.
Selection: Win the shortlist comparison
Names, descriptions and schemas that make you the right choice for the job.
Invocation: Calls that go out cleanly
Valid arguments, clear auth, nothing blocked or refused on the way out.
Execution: Answers, not errors
Your server returns a real result: no timeouts, empty pages or stack traces.
Completion: The task actually done
Checked mechanically and by a calibrated judge, never by the agent’s own word.
Outcome: Revenue, not just calls
The signup, order or booking that followed, joined from your own telemetry.
Principles
Agent distribution is full of accepted wisdom that doesn’t hold up. Here’s what we’ve learned.
Principle 01
Listing is not distribution
A directory listing puts you on the shelf. It says nothing about whether an agent reaches for you when a customer asks for the job your product does.
Distribution happens at the moment an agent compares every tool that could do the work and picks one. That moment is what we measure, request by request.
Principle 02
A description is not a decision
Agents read your tool names, descriptions and schemas, then weigh them against every competitor that could do the same job. None of that shows up in your own analytics.
So we run the requests your customers actually send, and record which tool each agent considered, chose, called and finished the task with.
Principle 03
One run is not a measurement
Ask an agent the same question twice and it can pick a different tool. A single demo proves nothing either way.
We repeat every request, report a probability with an interval, and call overlapping results a tie. Every number on InvokeRank says how sure we are, and where it came from.
Principle 04
One host is not the market
ChatGPT, Claude, Cursor and Codex each find and rank tools their own way, and each changes on its own schedule.
Winning on one tells you little about the others, so each host is measured on its own terms and never blended into a single flattering score.
Principle 05
Gaming the model does not work
Copy written to trick a model into choosing you gets caught by directory review and by the next model update, and it makes agents worse for everyone.
We only recommend changes that make your tool genuinely easier to choose correctly. Rankings are never for sale, and we never automate consumer chat apps.
Approach
How we work with you from the first baseline onwards.
Discovery and baseline
We map where your product is listed across hosts, agree the requests that matter to your business, and run a baseline. By the end you know your InvokeRank on each host, with intervals, and which competitors agents choose instead.
1.Find the stage you lose at
Every request is followed from shortlist to finished task, so the drop has an address: not found, found but not chosen, chosen but failed. The biggest lever goes first, with the evidence that points to it.
2.Change one thing, measure again
A new description, a clearer schema, a fixed error. Each change runs against the same prompts as the baseline, and it ships only when selection moves beyond the interval, not when it merely looks better.
3.Watch for drift and competitors
Models update and competitors ship new tools. InvokeSignal re-runs on a schedule and alerts you when your share drops beyond normal noise, with the change most likely to have caused it.
4.Each phase builds on the one before. The baseline points to the lever, the experiment proves the change, and monitoring keeps the gain. That’s the method.
Let InvokeRank get you chosen everywhere
If we’re a fit, we’ll run a free baseline and show you exactly where agents choose someone else, before you commit to anything.
Get early access Read the scoring methodology