Learn · Practice
Practical AI model selection exercises
Use short, source-backed workflows to practise building shortlists, comparing verified fields, checking sources, and creating decision evidence. Each exercise ends with a concrete artifact you can share with the rest of the team.
Learning path
Step 1
Read lessonStep 2
Complete exerciseStep 3
Build shortlistStep 4
Compare fieldsStep 5
Export brief
Beginner exercises
5 exercises
Short workflows that produce a shortlist URL, a comparison URL, a pricing note, or a freshness note.
- beginner8 min
Build your first source-backed shortlist
Pick a use case, filter the catalogue by verified fields, and end with a shortlist URL you can share with the team.
Primary route:
/use-casesStart exercise →
- beginner7 min
Compare context windows without ranking models
Use the comparison builder to render verified context window + max output tokens for 3–4 candidate models side by side.
Primary route:
/compare/buildStart exercise →
- beginner6 min
Review a pricing reference safely
Open a verified pricing row, read its unit semantics + retrieval date, and walk the reverification queue if it is stale.
Primary route:
/pricingStart exercise →
- beginner5 min
Inspect lifecycle before integration
Pull lifecycle state for a candidate model, check for retirement date, and add a migration target to your notes if one exists.
Primary route:
/select?lifecycle=activeStart exercise →
- beginner5 min
Check source freshness and reverification state
Open the sources hub for a provider, identify any stale citations, and walk the reverification queue to see what is due for re-check.
Primary route:
/sourcesStart exercise →
Intermediate exercises
3 exercises
Longer workflows that produce a hosted-provider trace, a decision brief, or a written test plan.
- intermediate10 min
Map a hosted provider relationship
Pick a hosted model in the catalogue, trace creator vs billing provider, and read the hosted pricing reference's source citation.
Primary route:
/use-cases/hosted-inferenceStart exercise →
- intermediate10 min
Create a decision evidence brief
Use the decision brief builder to generate a paste-ready evidence pack from your shortlist, then export it in Markdown.
Primary route:
/briefs/buildStart exercise →
- intermediate12 min
Plan an external model test
Use the brief and the testing lesson to plan your own prompt, latency, rate-limit, and cost validation work for the shortlist.
Primary route:
/briefs/buildStart exercise →
Exercises by path
Which path uses which exercise
Every role-based learning path stitches a subset of these exercises into a sequenced curriculum. Open a path to see the full reading + practice order.
- AI model basics for careful users →Newcomer to AI model selection · 45 min
- Technical model evaluation before integration →Engineer preparing an integration · 112 min
- Map a hosted provider relationship · 10 min
- Create a decision evidence brief · 10 min
- Plan an external model test · 12 min
- Model selection for product use cases →Product manager / technical buyer · 46 min
- AI model governance and source review →Governance / risk / compliance reviewer · 57 min
- Safe AI model use for automation workflows →Automation builder / SEO operator / technical consultant · 141 min
- Build your first source-backed shortlist · 8 min
- Review a pricing reference safely · 6 min
- Create a decision evidence brief · 10 min
- Plan an external model test · 12 min