Shiplog

Prompt coach

Grade a prompt before you send it. Your pasted text stays in this browser. It is not sent to a model or stored.

Prompt coach is a separate lab tool, not part of Shiplog, the decision and release log.

Example prompt and its score

The example prompt is graded against this page’s prompt rubric.

Paste a prompt or short conversation, then select “Grade this prompt” to get an overall score out of 100 and the first change to make. Revise it and grade it again to compare the results.

The overall score ranges from 0 to 100. Higher is better: your prompt more closely meets this page’s rubric for intent, efficiency, and model fit.

See how the overall score is measured and what to do first.

Example prompt, grading now

This result uses an example prompt written for this page, not your prompt or anyone else’s real prompt.

Compare a revision. A second grade sets the previous overall score beside the new one and shows what moved.

Label turns “User:” and “Assistant:” to grade an exchange, or paste one prompt on its own.

Model fit is one of the three component scores. Pick the tier by what the model is at its provider: Premium or frontier is the most capable model a provider sells, Standard is a provider’s general-purpose default, and Economy or small is a provider’s small or cheap model. Left as Not specified, the result makes no routing recommendation rather than assuming a tier.

Empties the prompt field and removes your grades from this page — the result, the previous and revised overall scores, and the coaching summary. There is no undo.

What the coach reads and keeps

The coach reads only the text you paste and the optional model tier. It does not access your accounts, files, or customer data.

It keeps your prompt and grades on this page, in this browser, until you press Delete prompt and grades. Leaving the page clears them too, and nothing is stored elsewhere.

See the example prompt’s own text and the counts read from it.

See all seven possible results — among them a graded prompt, a prompt that needs changes, and text the coach cannot grade — none taken from text you paste.

Loading the possible results.

Send a Shiplog follow-up request

Send a Shiplog follow-up request, and a person on the Wawalu team that operates it replies by email, usually within two working days.

Request a Shiplog demonstration Discuss a Shiplog pilot

Also on this site · Runs on your own work

Grading more than one prompt?

Both pages below read a file you choose in this browser tab, and neither uploads it.

Personal AI history runs the same rubric across your assistant export — weeks of your prompts — and names the single habit worth changing first.

Open Personal AI history

Asking where your AI spend goes instead? AI FinOps analyzes a provider export to find AI-spend savings opportunities.

AI FinOps reads a provider export from OpenAI, Anthropic, Azure OpenAI, Google Vertex AI, or AWS Bedrock, as CSV, TSV, JSON, or JSONL. No export to hand? The example data opens on a finished result, so you can read the whole analysis before you find a file.

Open AI FinOps