Build & automate

Developers, technically curious learners and professionals implementing automations.

Before you start

Python basics, local files and running tests. General Intermediate lessons provide preparation.

Tools and access

A computer and Python 3.10+. The supplied standard-library lab needs no API key, network or purchase.

Your evidence of capability

A bounded offline workflow, negative-case tests, checked artifact and release note.

Planning estimate

4 hours 7 minutes of reading and practice. Authored estimate, not measured learner time. Shared foundations and optional deeper study add time.

Start your first focused lesson →

Six lessons, increasing independence

Each lesson includes a worked example, a separate task, acceptance criteria, review notes and a knowledge check. The capstone combines the skills in a new case.

1. 01
   Specify an application before choosing a model

   Define a bounded input/output contract and testable requirements.

   Get started · 9 min read + 20 min practice

2. 02
   Give coding assistants bounded context and inspect the diff

   Use AI coding help without confusing claimed work with tested work.

   Get started · 9 min read + 20 min practice

3. 03
   Handle structured output and provider failure states

   Validate syntax, fields, evidence and status separately.

   Apply independently · 9 min read + 30 min practice

4. 04
   Enforce tool permissions and preserve denial

   Implement a dispatcher that cannot turn a denied read into evidence.

   Apply independently · 9 min read + 30 min practice

5. 05
   Evaluate failures and bound repeated work

   Build negative-case checks and retry-safe workflow behavior.

   Handle complex work · 9 min read + 30 min practice

6. 06
   Capstone: deliver a bounded offline workflow

   Integrate controls and report actual execution evidence.

   Handle complex work · 12 min read + 60 min practice

Revisit shared foundations when needed

• Verify evidence and unsupported claims
• Distinguish model, harness and data paths
• Set up Python and local practice

These links open the existing general-course lessons; they do not create duplicate copies or completion records.

Adapt the work to your model and tools

Text-only assistant

Use supplied text. Ask for a plan or draft; do not claim browsing, code execution or file access that was unavailable.

Tool-enabled application or harness

Record which tools actually run, allowed files and actions, approval boundaries and observable results. Tools are optional unless the task needs them.

Local or cloud deployment

Inspect inference, retrieval, connectors, logs and storage separately. Use only authorized environments for real data; training fixtures are fictional.

Higher-capability or frontier model

Evaluate the exact task and configuration. Capability does not supply missing evidence or grant permission. No provider ranking or guarantee is implied.

Offline alternative

Use the supplied inputs and inspect the worked example manually. Builder exercises use local deterministic Python. No paid account or live model call is required.

Content revision 2026-10-03. Examples are authored fictional fixtures. Self-review is not independent grading, certification or operational approval.