Will an AI agent understand your email?
Paste an email and what you want the recipient to do. A representative recipient AI agent reads it blind; we grade what it understood against what you meant and email you the scorecard.
Core ask survived, but the specific deliverable was lost.
Snag: "touch base on the thing" → Name the deliverable: 'approve the Q3 budget draft'.
| ||
The agent logged no concrete action — 'circle back' read as optional.
Snag: "maybe circle back when you can" → State the action directly: 'Please reply with approval by Thu'.
| ||
You needed this urgently; the agent filed it as low.
Snag: "no rush at all" → Drop the softener if it's actually time-sensitive.
| ||
'Next week' left no concrete date for the agent to schedule.
Snag: "sometime next week" → Use an explicit date: 'by Thursday, Aug 14'.
| ||
Appropriately unsure — the agent didn't over-commit on a vague ask.
|
We email a confirmation link first (double opt-in), run the score only after you confirm, and delete your pasted email once scored. One score per email address per day. See Privacy.
Agent Comprehension Score FAQ
What is an Agent Comprehension Score?
Your email's first reader is now often a machine — Gmail, Copilot, Apple Intelligence and inbox agents summarize, triage and even draft replies before a human sees it. The ACS shows how a representative recipient AI agent reads the email you're about to send, and grades whether it will understand what you actually meant across five dimensions.
How does it work?
You paste your email plus what you want the recipient to do. A representative AI agent reads the email BLIND — without your stated intent — and reports what it understood and would do. We then grade that blind read against your intent and email you a scorecard with the exact phrase that caused each miss and a one-line fix.
What are the five dimensions?
They follow an agent's pipeline: Summary fidelity (did your core point survive), Action clarity (did it get the single ask), Priority match (did it triage urgency as you meant), Deadline/thread coherence (did it pin the when and context), and Confidence calibration (did it act with appropriate certainty).
Do I have to say what I want the recipient to do?
It's optional but it unlocks the full graded score. Without it you still get the blind read plus legibility and injection-hygiene flags — useful on its own. With it you get the five-dimension comparison and your single highest-leverage fix.
Do you store my email?
We email a confirmation link first (double opt-in) and run the score only after you confirm. Your pasted email is deleted as soon as it's scored — we never keep the body. We hold only your email address and the scorecard briefly to run the service, then delete the record. See our Privacy page.
Why a confirmation link instead of scoring instantly?
Two reasons: it stops the tool being used to score forged addresses, and it means we only run the model after you opt in. One score per email address per day.
Isn't this just a spam or deliverability check?
No. Our /audit and /headers tools check whether your email arrives and authenticates. The ACS checks whether the AI agent between you and your recipient will act on it correctly — machine-actionability, a different axis that didn't matter five years ago and now decides outcomes.