Score it before you automate it.
An AI agent doesn't fail like software. It fails like a confident intern who says the job is done when it isn't.
These are the five criteria I score every workflow against in the Agent Readiness Audit. Run your own workflows through them below and you'll get a verdict, a score, and a ranked fix-list for each one.
Everything is scored in your browser. Your workflow names and answers are never sent anywhere — there is no request to score, and nothing is stored except in this tab. If you ask me to keep your map, the only thing that leaves is your email address. The map itself is built right here.
Your workflows
1 of 5
Agent Readiness Map
Scored against the five criteria of the Agent Readiness Audit · timraysby.com/scorecard
Your readiness map
Keep your map
This disappears when you close the tab.
Save it as a PDF you can hand to whoever owns these workflows — and I'll send you the one-page version of how I'd close the gaps you just scored.
Your email is the only thing that gets sent. The PDF is generated in this tab from the results above — your workflow names never leave your browser. No trackers, and no list I don't write myself.
This is the shape of the Audit — run against everything, not five.
The real thing scores every candidate workflow you have, digs into the ones you scored generously, and hands you a ranked fix-list you own. Two weeks, fixed scope. Paste your results straight into the form — the more concrete you are, the faster I can tell you whether an Audit is worth your money.
See the full deliverable — the Audit run at full depth on the five workflows I operate myself.
Or read the manual these five gates come from — the reasoning, four failures of my own, and six worksheets. Free.
Or something smaller first
Scorecard review
$199 · five a month
Send me up to three of your completed sheets. You get back a recorded walkthrough: where I would score them differently and why, which bucket each workflow belongs in, and what to fix first. If the honest answer is “don’t automate this yet”, that is what you will hear.
Ask for a review →One-workflow review
$1,200 · about a week
The Audit, run on a single workflow rather than all of them. I do the scoring instead of reviewing yours, and hand back the same scored map and ranked fix-list, walked on one call. The right size when one workflow matters more than the rest.
Ask about one workflow →What the five criteria mean
Documented
Could someone new run this from a written description, without asking anyone?
Agents automate descriptions of work. No description, no agent.
Deterministic
Are the judgment calls written as rules, or is it “it depends”?
Every “it depends” is a place the agent guesses — and guesses confidently.
Verifiable
Is there an automatic check that the work was done right?
If the only check is “a customer eventually complains,” the agent fails silently for weeks.
Recoverable
If the agent gets it wrong, what does undo cost?
Cheap undo, automate freely. Expensive undo, a human stays in the loop. No exceptions.
Delegatable
Does a named human own the output, and can the agent earn trust gradually?
You onboard a new hire in stages. Same rule here — nobody gets the keys on day one.
Two of these are hard stops rather than scores. If there is no way to check the work, the agent will fail silently for weeks. If undo is expensive, a human stays in the loop no matter how good the rest looks.