Learn
Learn concepts
Plain-language lessons on context windows, pricing references, hosted vs first-party, lifecycle, status, structured output, and benchmark limits.
Learn
Learn how to use AI models correctly
Follow role-based learning paths that teach AI model concepts, then apply them through source-backed shortlists, comparisons, evidence briefs, and freshness checks. AI usage curriculum powered by verified model intelligence.
The catalogue is a verified-data backbone. The lessons here explain how to read that data; the exercises walk you through producing concrete evidence artifacts using the existing selection, comparison, brief, and sources workspaces. Lessons never tell you which AI model to pick.
Curriculum
Learn → Apply → Verify → Test
Concept lessons explain the verified fields. Exercises route those concepts through the workspaces. Sources anchor every claim. The AI Usage Lab adds testing playbooks before integration. Every step of the curriculum stays auditable.
Apply
Apply with workflows
Practical exercises that route through the selection, comparison, and brief workspaces — ending with shortlist URLs, comparison URLs, Markdown briefs, freshness checklists, and test plans.
Verify
Verify with sources
Every claim in the catalogue is anchored to a primary-source citation with a retrievedAt date. The reverification queue surfaces what is due for re-check.
Test
Test before production
The AI Usage Lab adds six testing playbooks and three paste-ready Markdown templates. Playbooks teach how to test; they do not certify the model.
Choose your path
Role-based learning paths
Five sequenced curriculums (beginner, developer, product manager, governance, automation specialist). Same lessons and exercises — different sequence and emphasis.
- beginner45 min· 7 steps
Newcomer to AI model selection
AI model basics for careful users
Three foundational readings + four practical exercises. Walks from a use case to a paste-ready evidence brief plus a freshness checklist. Built for readers new to the catalogue.
Shortlist URLComparison URLMarkdown evidence brief+1 moreStart path →
- intermediate112 min· 11 steps
Engineer preparing an integration
Technical model evaluation before integration
Four readings + three exercises + two pre-seeded workflows. Walks the verified fields a developer needs (hosted creator vs host, modality channels, structured generation, the testing framework) and ends with a comparison URL, an evidence brief, and a written external test plan.
Hosted-provider mapping noteVerified comparison URLDecision evidence brief+1 moreStart path →
- intermediate46 min· 8 steps
Product manager / technical buyer
Model selection for product use cases
Four readings + three exercises + one pre-seeded workflow. Walks use-case framing, pricing references, lifecycle gates, and benchmark limits so the team can align on a defensible review — ending with a use-case shortlist, a pricing-reference note, a lifecycle risk note, and the evidence brief.
Use-case shortlist URLPricing-reference noteLifecycle risk note+1 moreStart path →
- intermediate57 min· 10 steps
Governance / risk / compliance reviewer
AI model governance and source review
Four readings + three exercises + three audit workflows. Walks lifecycle, status, benchmark limits, pricing, and source freshness so a reviewer can sign off with a defensible evidence trail — never a certification claim.
Source freshness checklistLifecycle review noteData gap list+2 moreStart path →
- intermediate141 min· 14 steps
Automation builder / SEO operator / technical consultant
Safe AI model use for automation workflows
Five readings + four exercises + three pre-seeded workflows. Built for people wiring AI models into automations: structured outputs, prompt cost projections, regression test plans, and a brief that ships with the automation runbook. Never an automation marketing pitch.
Safe model-use checklistStructured-output inspection notePrompt testing plan+2 moreStart path →
Concept lessons
Concept lessons
Plain-language reads that explain one verified catalogue field at a time. Every lesson ends with a workflow apply panel + related exercises.
Foundations
model fundamentals
How to choose an AI model
A workflow for picking which AI model to test next — start from your use case, inspect verified fields, export an evidence brief.
Read lesson →
model fundamentals
Context windows explained
What a context window means, what it does not guarantee, and which verified fields to inspect before assuming a model fits your prompt.
Read lesson →
pricing and hosted
Hosted vs first-party AI models
Why the model creator and the billing provider are usually different, and how the catalogue keeps the two separate.
Read lesson →
pricing and hosted
AI model pricing references explained
Why catalogue pricing rows are references, not quotes — and how to read them without ranking models by price.
Read lesson →
Going deeper
governance and sources
Model lifecycle: active, deprecated, retired
What active, preview, deprecated, and retired mean for a model — and why lifecycle should gate integration decisions.
Read lesson →
testing workflow
How to test an AI model before integration
After the shortlist: how to run your own prompt, latency, rate-limit, cost, and compliance tests — using the evidence brief as the pack you ship to reviewers.
Read lesson →
model fundamentals
Multimodal input: image, audio, video, PDF
How the catalogue records which models accept image, audio, video, or PDF input — and why marketing copy is not enough to assume support.
Read lesson →
model fundamentals
Structured output, JSON mode, and tool use
The difference between structured output, JSON mode, and tool/function calling — and what is currently verified in the catalogue.
Read lesson →
governance and sources
Status-aware model selection
Why vendor-reported status pages and independent probes are kept separate — and when status should gate a model decision.
Read lesson →
comparison methodology
Why benchmark scores can mislead
Contamination, prompt variance, version drift, and why the catalogue does not publish provider-reported benchmark scores casually.
Read lesson →
Practical exercises
Practise with exercises
Short, source-backed workflows that route through the catalogue and end with a concrete artifact. No quizzes, no scoring, no model picks.
- 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 →
- 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 →
- 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 →
Apply with workflows
Every lesson and every exercise routes the reader through the existing workspaces. Open any of these directly when you know the surface you want.
Selection workspace →
Filter the catalogue by use case, verification state, lifecycle.
Comparison builder →
Render up to four models against each other — verified fields only.
Decision brief builder →
Export a paste-ready Markdown or JSON evidence pack.
Citation registry →
Every primary-source URL the catalogue references, by provider.
Reverification queue →
Sources due for manual re-check, with last-verified dates.
Coverage audit →
Per-provider verified-field counts and source density.
No progress, no accounts, no certificates
- No accounts — the catalogue does not have a login surface.
- No progress tracking — the catalogue does not store which pages you have visited.
- No certificates — the catalogue does not issue completion credentials, badges, or scores.
- Completion is the artifact you produce: a shortlist URL, a comparison URL, a Markdown brief, a freshness checklist, or a written test plan.