Annotation, quality & human feedback

Write labeling guidelines and evaluation rubrics

Turn a vague quality goal into a rubric with examples and edge cases that others can apply.

~8 focused hours·intermediate

Tools: rubric templates, golden/reference examples, scoring rubrics (Likert/pass-fail)

Market relevance — share of job ads asking for this
What employers mean

You should be able to…

  1. Turn a vague quality bar ('good customer support response') into scored, checkable criteria
  2. Provide 2-3 worked examples per score level so raters apply the rubric consistently
  3. Cover edge cases explicitly instead of leaving them to individual judgment
  4. Pilot a rubric on a small sample and revise it before rolling out to a full annotation team
  5. Balance rubric strictness with practical rater throughput
  6. Version and document rubric changes so historical ratings stay interpretable
  7. Write rubrics usable by both human raters and automated LLM-judge pipelines

Needs first: Evaluate and rank model responses (RLHF / preference data)

Learn — free, link-checked

The few resources that matter

Read · beginner · 30 min · huggingface.co

Evaluate

Official docs for standard NLP quality metrics — vocabulary you need to write rationales that cite concrete numbers, not vibes. — Hugging Face
Read · beginner · 60 min · guidelines.raterhub.com

Search Quality Rater Guidelines

The actual rubric Google trains its own quality raters on — the closest thing to a real take-home for the 'AI Quality Evaluator' roles flooding Indian job boards. — Google
Read · intermediate · 30 min · docs.claude.com

Develop test cases

Anthropic's own guide to writing test cases and grading criteria for evaluating model outputs at scale. — Anthropic
Build from · intermediate · 90 min · github.com

OpenAI Evals

Open-source framework with real eval examples showing how pairwise and rubric-based model grading is actually implemented in code. — OpenAI
Course · intermediate · 90 min · deeplearning.ai

Automated Testing for LLMOps

Free short course on building automated eval pipelines and rubrics for LLM applications, from prompt to production. — DeepLearning.AI
Build from · intermediate · 120 min · github.com

Anthropic courses

Anthropic's own hands-on notebooks for tool use, structured extraction, and grading model output quality. — Anthropic
Practice

Rubric + golden set for grading AI customer-support replies

Write a 4-criterion rubric (accuracy, helpfulness, tone, policy compliance) with a 1-5 scale and 2 worked examples per score level for grading AI-generated customer support replies (include a Hindi-language example). Build a 20-item golden set with your own scores and rationales, then have the rubric scored by an LLM-as-judge and compare.

Done when
  • Rubric has 4+ criteria, each with a 1-5 scale and at least 2 worked examples per level
  • A 20-item golden set is scored manually with rationales referencing specific rubric criteria
  • An LLM-as-judge is run against the same rubric on the golden set and results are compared to manual scores
  • A short revision log documents at least one rubric change made after piloting, and why
Prove it

Evidence a recruiter can check

  • Public repo with the rubric doc, golden set, manual scores, and LLM-judge comparison
  • Agreement/correlation number between manual and LLM-judge scores on the golden set
  • Revision log showing the rubric was piloted and iterated, not written once and shipped
Interview

Questions you'll get asked

  1. Turn 'the response should be helpful' into a concrete, scoreable rubric with 3+ criteria.
  2. How do you pilot-test a new rubric before rolling it out to 20 annotators?
  3. What do you include in a rubric so two different raters reach the same score on a borderline case?
  4. How would you version a rubric so old ratings remain interpretable after you update it?
  5. How is a rubric for a human rater different from one designed for an LLM-as-judge pipeline?
  6. Give an example of a rubric criterion that sounded clear but caused disagreement in practice — how did you fix it?
  7. How do you balance a rubric being thorough vs. annotators being able to apply it quickly?
See where you stand for AI Data Annotator / Labeling QA