AI engineering learning path

Project laboratory

Connect concepts through independently designed requirements, models, and acceptance checks.

8 chapters · Read in order
Suggested background: Understand APIs, data models, and access control; start with services and data, then choose a project. Offline examples check core mechanisms; full platforms and projects require the implementation and acceptance steps described in each guide.
Break down a project and verify its important failure paths.

Chapters

  1. Project: a product-description review workspace

    Design versioned drafts, reviewer authority, and evidence checks so AI suggestions require approval before export, with tenant boundaries and stale-version handling.

  2. Project: a document-processing workflow editor

    Connect graph validation, node contracts, immutable task snapshots, and recovery in a document project, separating model extraction from authorized external effects.

  3. Project: a training exercise and answer-record system

    Freeze question and grading versions and design drafts, final submissions, and result access in a training system with retry and answer-protection checks.

  4. Project: a teaching-illustration job queue and asset library

    Design owned illustration jobs with budgets, a quota ledger, R2 assets, and human review, then handle cancellation and repeated execution.

  5. Project: a reading recommendation and explanation service

    Build a synthetic book catalog and rule-based ranking before grounded explanations, handling cold starts, preference access, empty results, and evaluation.

  6. Project: an inventory reservation and fulfillment service

    Connect inventory reservation, confirmation, expiry, and compensation through transactions, conditional transitions, and an outbox, handling repeated messages.

  7. Project: a device-sampling data and trend dashboard

    Define events, quality, and windows for synthetic device samples, then design Go ingestion and charts that handle duplicates, missing data, and staleness.

  8. Project: a travel-constraint and candidate-itinerary workflow

    Separate itinerary evidence, candidate generation, constraint checks, and review, with bounded tool access and budgets that prevent untrusted content from authorizing bookings.

Keep exploring