Analysis / Business automation and AI evaluation
Compare prompt and model alternatives fairly
Compare AI prompts and models in Proforma with fixed evaluation cases. Review quality, measured latency and available cost evidence without test-set tuning.
AI product lead
Bring this question into Chat
Your starting prompt.
Compare [candidate prompts and models] using [quality rubric] and the same fixed evaluation cases. Use development cases for revisions and keep final evaluation cases untouched until the comparison. Record actual outputs, run failures, latency and available cost evidence, separating reviewer judgments from automated checks. Report trade-offs and uncertainty. Do not invent run costs, imply statistical significance from a small set or silently change the rubric after seeing results.
Copy this starting point, then replace the placeholders with your own inputs.
Method and review
Keep the assumptions visible.
Define inputs, outputs, permissions and failure conditions before implementing an Action. Evaluate AI against representative labeled examples and retain human approval for consequential steps.
For this task, check
An independent reviewer should inspect rubric consistency, leakage and meaningful quality differences before choosing a candidate.
This starting prompt has no published worked example yet. Begin with a small sample and check the calculations before relying on the result.
Before you begin
- Configured candidate models and permitted evaluation cases
- Preserved development and evaluation subsets
- Agreed quality and cost assessment rules
Work with permitted files or queryable data. Verify the result against the original records.
Take the next step
Make it your investigation.
Copy the prompt above, create or open your Workspace, and paste it into Chat. Add the inputs you have permission to use and adapt the assumptions with your agent.
Start exploringYour prompt is carried by copy and paste. Signing up does not submit it or start this work automatically.
Or start with your own agent
The setup prompt includes this public task. Your agent will help you connect when needed and use the access you approve.