Sample report

What you get back.

Everything on this page is invented. “Example Parcels API” does not exist, and no number below comes from a real client, company or test. It only shows the layout of the reports.

01 Risk report (example)

Every operation in the spec gets a class and a recommended safety label, so risky calls are flagged for your review before anything is built.

OperationClassSuggested labelDecision
GET /parcelsRead-onlyread-onlyInclude
GET /parcels/{id}Read-onlyread-onlyInclude
GET /ratesRead-onlyread-onlyInclude
GET /parcels/{id}/labelAction disguised as a GET (creates a label and may charge)costly, not read-onlyHold; needs approval
POST /parcelsCreate (costly)writeHold; not in pilot
DELETE /parcels/{id}DeletedestructiveExclude

02 Spec completeness (example)

CheckOperations
Has an operation ID5 of 6
Has a description4 of 6
Has a success response schema6 of 6
Has an example2 of 6

03 Before and after (example)

30 invented test prompts, 3 repeats of each run. Real reports also list every case whose result changed.

MeasureBefore tuningAfter tuning
Right tool chosen17 of 3026 of 30
Right arguments14 of 3024 of 30
Correct refusal or question (4 cases)1 of 44 of 4
Calls to a risky tool on a read-only request30

Thirty prompts is a small sample, so I report counts rather than headline percentages. Agents vary from run to run, which is why each run is repeated three times.

Next step

Not sure yet? Send a link to your public OpenAPI file for the free spec check. See what the pilot includes on the Pricing page. Ready? Request a pilot.

The pilot is $350: up to 5 tools from your OpenAPI file, plus a 30-prompt before and after report, setup guide, and you own the code. Not included: user login, custom workflows, production hosting.