Test Plan from the Prompt is a free prompt. Paste the prompt you used to vibe-code a feature. Get the checks to run before merge, including the case that prompt forgot.
It is not always the right tool. Here is when something else wins, and when it does not.
Plain chatbot
Asking your coding agent to "add tests"
Pick it if
You trust it to pick the cases and only need coverage numbers.
Pick Test Plan from the Prompt if
You want the cases the original prompt forgot, decided before any test code exists.
By hand
A QA checklist template
Pick it if
Your team has a standard checklist for every feature.
Pick Test Plan from the Prompt if
You want cases specific to this feature, like the empty state and the user who is not the author.
0:00The evidenceSupport ticket prompt. Wanted JSON for the on-call engineer. Got four friendly paragraphs and no severity.
0:08Bug 1: rules that fight'Be concise' vs 'cover everything the customer said'. The model picks 'everything' and writes four paragraphs.
0:16Bug 2 and 3'Always be friendly!!' outranks the format, so it writes to the customer. 'Output JSON' has no schema and no example.
0:24Fixed promptReader named, friendliness rule cut, JSON schema with one filled example, and a 'no prose outside the JSON' line. Each change tied to a bug.
No daily video for this drop yet. The in and out lines above are the preview.
0:08What actually shippedLogin on staging, pricing table render, stripe package installed. Plan change is still a stub. PayPal left alone on purpose.
0:16What is brokenWebhook 400, missing signature check, BillingForm customerId null, receipt email not wired. Ranked by what blocks the rest.
0:24Tomorrow's first promptA paste-ready prompt that starts at the webhook 400, forbids touching PayPal, and asks for a signature check plus a failing test.
No daily video for this drop yet. The in and out lines above are the preview.
0:00The diff that 'works'A Next.js DELETE handler reads an id from JSON, concatenates it into SQL, and returns a live-looking secret key in the response.
0:08What it should catchA secret in source. SQL built with string concatenation. No check that this caller owns the note. The key echoed back to the client.
0:16Severity, then the fixHigh: move the key to an environment variable and rotate it. High: parameterize the query. High: derive the user from the session and filter the delete by owner.
0:24What it will not doIt will not hand you a working exploit. The sample key is fake. The output is the safer handler, not a payload.
No daily video for this drop yet. The in and out lines above are the preview.
Questions
What are the alternatives to Test Plan from the Prompt?
Asking your coding agent to "add tests" (plain chatbot); A QA checklist template (by hand). On One Agent a Day, Diff Risk Reviewer, Prompt Debugger, Session Handoff, Vibe-code Security Checker do a similar job.
When is asking your coding agent to "add tests" better than Test Plan from the Prompt?
Asking your coding agent to "add tests" is the better pick when you trust it to pick the cases and only need coverage numbers. Test Plan from the Prompt is the better pick when you want the cases the original prompt forgot, decided before any test code exists.
When is a QA checklist template better than Test Plan from the Prompt?
A QA checklist template is the better pick when your team has a standard checklist for every feature. Test Plan from the Prompt is the better pick when you want cases specific to this feature, like the empty state and the user who is not the author.
Tomorrow's drop
Get tomorrow's agent in your inbox
One email when the drop goes up. No digest, no course. Unsubscribe from the beehiiv email whenever you want.
Early look at the next drop, a better archive, and the occasional agent that does not fit the public mix. The daily agent stays free. A custom build is €49–199. Nothing is charged from this form.