One Course
Every lesson, project and mock exam in Building with language models.
Billed monthly. Cancel any time.
Level 1: Newcomer
0 points
Sign in to save your progress across devices.
Courses / AI tools and development
Write the Python around a language model: validate an API response, retrieve the right source, run an approved tool and check the result. This AI engineering course runs your code against scripted mock replies in a browser notebook, with no live model calls.
Unit 1, Request contracts: 5 lessons and 26 checked exercises, with no account or card.
Start the free unitThe rest of the course opens with a One Course or All Access plan. See plans and prices
Choose access here. Your course is already selected.
Support routing requests with explicit authority and resource boundaries.
6 steps · 14 minCase study · BeginnerCase broken roundtripDefine narrow tools and return correlated results without granting unrequested actions.
6 steps · 14 minProject · IntermediateProject handbook indexBuild an original industrial-manual index with traceable chunks and deterministic vector fixtures.
8 steps · 22 minProject · IntermediateProject policy answersAnswer customer policy questions only from current authorized evidence.
8 steps · 22 minProject · IntermediateProject evaluation harnessCompare prompt revisions with frozen case identities and mandatory safety gates.
8 steps · 22 minProject · AdvancedProject dispatch agentPrepare a bounded dispatch workflow with exact-payload approval and reconstructable state.
8 steps · 22 minCase study · AdvancedCase tenant leakInvestigate a tenant leak while preserving safe incident evidence.
6 steps · 14 minProject · ExpertProject batch serviceBuild a batch report with safe cache identity, output correlation and supplied observation gates.
8 steps · 22 minMock exam · ExpertMock grounded featureTrace a grounded feature and prepare a reproducible release bundle.
12 questions · 40 minMock exam · ExpertMock unsafe run recoveryEnforce approved data policy and decide release or rollback from preserved evidence.
12 questions · 40 minBuild language-model features in a working Python notebook with an original local mock client. Construct current Responses-style requests, validate structured output and correlate tool results. Build traceable retrieval, compare prompt revisions, bound agent loops and preserve tenant and approval boundaries. Projects accumulate actual learner functions into checked reports. Practice sets, interviews and two timed job screens use original fictional data and synthetic observations. The mock performs no live inference or external tool execution. Its documented API subset, fake vectors and fake token units teach integration behavior without claiming model quality, provider prices or complete cloud certification preparation.
Beginner
Support routing requests with explicit authority and resource boundaries.
Validate output shape, response state and business rules before accepting an answer.
Define narrow tools and return correlated results without granting unrequested actions.
Intermediate
Build an original industrial-manual index with traceable chunks and deterministic vector fixtures.
Answer customer policy questions only from current authorized evidence.
Compare prompt revisions with frozen case identities and mandatory safety gates.
Advanced
Prepare a bounded dispatch workflow with exact-payload approval and reconstructable state.
Investigate a tenant leak while preserving safe incident evidence.
Recover transient and uncertain outcomes without repeating unauthorized work.
Expert
Build a batch report with safe cache identity, output correlation and supplied observation gates.
Trace a grounded feature and prepare a reproducible release bundle.
Enforce approved data policy and decide release or rollback from preserved evidence.
A support feature should not parse the first returned item as if it were always text. Inspect the Responses API output items, distinguish a tool request from a message and handle an incomplete result. The structured output exercises add a schema, then require business validation. Valid JSON can still be wrong.
Build a RAG pipeline for fictional policy documents. Filter before ranking. Use only the requesting customer’s sources at the current revision. Check that every citation belongs to the retrieved evidence and abstain when the sources do not support an answer. The vector search guide explains what the local fixture simplifies.
Use held-out evaluations to compare a candidate with a fixed baseline. Keep the cases used to improve the code separate from those used to report its result. A higher average does not excuse a failed mandatory safety case.
Correlate function results by call ID, validate arguments and reject unknown tools. Add a step budget and require approval for the exact write payload. The prompt injection exercises include hostile source text; the application must enforce access even when the assistant reply is wrong.
Compare RAG and fine-tuning and MCP and function calling before choosing a live architecture. These concept guides do not install a protocol server or train a model.
Practice original engineering questions in the Interview Hub. The AI-103 guide explains the current Azure credential and the retirement of AI-102. The AWS AI Practitioner guide separates foundational certification knowledge from coding a model application. Our timed job assessments do not reproduce either exam.
No. Your Python runs against an original mock client with prepared outputs. No API key or paid model account is needed, and a passing task does not measure a live model.
No. You build deterministic fixture vectors and calculate similarity locally. They teach indexing and ranking behavior; they do not reproduce the quality of a learned embedding model or a managed vector database.
It is practical engineering training. The certification guides map selected concepts and explain the gaps. The timed assessments are original job tasks, not vendor exam simulations.
You should be able to write functions, use dictionaries and lists, and handle exceptions. Start with the Python course if those tasks are new.