Prove it works: a test set for your RAG app

An evaluation suite for the I1 Employment Code app that scores retrieval and answers separately, and runs on every change.

I4IntermediateLockedEvaluation and testingHuman in the loop and deployment

Why this build, here

“It seemed fine when I tried it” is how most AI apps ship, and how most fail. Employers want engineers who can show a number that goes up when the app gets better.

The build, step by step

  1. Write forty questions

  2. Score retrieval on its own

  3. Score answers

  4. Find out why it fails

  5. Run it on every change

The steps, checks and practice open with a code

You can see what this lesson builds. The detail of each step, the finished-when checks and interview scoring come with the K850 practice, along with weekly build sessions and code review.

Codes come with the K850 practice. Book a place

Read and run

Interview practice

Questions on this topic from AI Engineering Interview Questions, company-wise, with the companies it lists. Write your answer the way you would say it; Jev scores it and DeepSeek tells you what to add.

Scoring opens with an access code. You can still read the questions and prepare.

Chat on WhatsApp