AI courses for engineers and teams
Become an AI engineer who can build, test, and operate useful systems—not just call a model. Learn AI capabilities alongside the software, data, workflow, and cloud foundations that make them reliable.
Start with the work you want to do
Ground answers in evidence. Design reliable agents. Build and test software with AI. Choose a starting point below, or explore all 59 courses across 13 areas.
Contact us for full course details.
Featured courses
Retrieval-Augmented Generation
8 hours · 4 modules
Build a question-answering application that retrieves relevant document passages before generating an answer. Prepare documents, create embeddings and an index, compare retrieval methods, and construct useful model context. Generate cited answers and investigate failures by separating retrieval performance from answer support. Compare graph-assisted retrieval without making a graph database the starting requirement.
Explore course →AI-Assisted Software Development
6 hours · 3 modules
Revisit the software development lifecycle from C01 and examine how AI changes the way teams plan, implement, review, test, and integrate software. Use AI on a real change, revise effort estimates, and compare automated and human review. Explore an issue-to-merge workflow and decide where fuller automation improves delivery, where it shifts work, and where human decisions remain necessary.
Explore course →Human–AI Workflow Design
8 hours · 4 modules
Design people, technology, and work practices together. An agent deployment changes who reviews, decides, learns, and recovers when something fails. Study actual work, assign roles and authority, and test human review. Preserve the skills needed to supervise and recover automation through manual rotation, escalation practice, and incident drills. Design adoption and trust repair too.
Explore course →AI Security Foundations
6 hours · 3 modules
Untrusted retrieved text can try to turn an AI suggestion into a privileged tool action. Trace that path in a small mock application and define controls at input, data, and mutation boundaries. Test prevention, detection, and response evidence with harmless fixtures rather than relying on a defensive prompt alone.
Explore course →Why engineering foundations belong here
A model can propose an answer or action. Your application still owns validation, data, permissions, and effects. These foundations teach enduring concepts through AI-focused examples, not a separate generic technology syllabus.
- Software and language foundations: Validate generated outputs, design typed tools, and keep model suggestions separate from deterministic rules.
- Workflow and knowledge foundations: Assign work to rules, models, and people. Preserve evidence, approval, and review capacity.
- Data foundations: Prepare trustworthy datasets, prevent evaluation leakage, and separate authoritative records from retrieval indexes.
- Cloud and delivery foundations: Build around services such as Amazon Bedrock, compare managed AI offerings, and control access, capacity, cost, and release changes.
Use supplied model responses and local exercises to learn the foundations without paid AI or cloud accounts. Specialist courses add deeper model integration, retrieval, agent design, and operations.
Find your starting point
Follow the preparation for your chosen course, not the whole catalog. Bring equivalent experience where you already have the skills. Courses at the same level are parallel options, not a compulsory block.
Levels follow required-course preparation, not a universal difficulty rating. Entry skills still apply: an independent entry point is not always a beginner course.
Level 1 12 courses
- Software Engineering Foundations for AI Engineers
- Programming Language Concepts for AI Engineers
- Formal Methods for Reliable AI Systems
- Artificial Intelligence Foundations
- Workflow Foundations for AI Automation
- Knowledge Engineering Foundations for AI Systems
- Database Systems for AI Applications
- Cloud Foundations for AI Engineers
- Cloud-Native Engineering for AI Workloads
- Observability Foundations for AI Systems
- Web Application Foundations for AI Engineers
- Web Discovery in the AI Era
Level 2 20 courses
- How Large Language Models Work
- Applied Generative AI
- Local and Small Language Models
- Human–AI Workflow Design
- Workflow Performance Engineering
- Semantic Web and Ontology Engineering
- Knowledge Graph Engineering
- Neuro-Symbolic AI
- PostgreSQL Development
- Data Engineering Foundations for AI Systems
- AWS Engineering for AI Applications
- Platform Engineering for AI Teams
- Cloudflare for AI Applications and Agents · Provisional
- AI Security Foundations
- AI Governance
- Responsible AI
- Deployment Foundations for AI Web Applications
- AI Adoption for Organizations
- Owning the AI Stack
- AI for the One-Person Company
Level 3 9 courses
Level 4 16 courses
- Harness Engineering
- Claude Code Engineering · Provisional
- Codex and OpenAI Coding Agents · Provisional
- OpenCode and Open Agentic Coding Tools · Provisional
- Agent Architecture and Orchestration
- Agent Interoperability and Protocols
- Agent Execution Environments
- Agent Platforms and Frameworks
- Event-Driven Workflow Design
- Context Engineering and Context Graphs
- AI Infrastructure
- AI Observability
- LLM and Agent Evaluation
- Agent Security
- Web Application Development in the AI Era
- The Agent-Accessible Web
Level 5 1 courses
Level 6 1 courses
Choose a learning path
These suggested routes include useful depth beyond the minimum prerequisites. Skip skills you already have, and choose optional branches only when they serve your goal.
Build grounded AI applications
A grounded prototype with validated outputs, evaluation evidence, observable behavior, and bounded authority.
- Artificial Intelligence Foundations
- Applied Generative AI
- Software Engineering Foundations for AI Engineers
- AI Security Foundations
- Programming Language Concepts for AI Engineers
- Building Applications with LLMs
- Retrieval-Augmented Generation
- AI Application Evaluation
- Observability Foundations for AI Systems
- AI Observability
Engineer reliable agent workflows
A validated agent workflow with recovery, approval, and independent task-effect checks.
- Artificial Intelligence Foundations
- Applied Generative AI
- Software Engineering Foundations for AI Engineers
- Workflow Foundations for AI Automation
- Programming Language Concepts for AI Engineers
- Agentic AI Foundations
- Building Applications with LLMs
- Event-Driven Workflow Design
- Reliable Workflow Execution
- AI Security Foundations
- Agent Security
- Harness Engineering
- Agent Architecture and Orchestration
- Agent Platforms and Frameworks
- AI Application Evaluation
- Dynamic and Agentic Workflows
- LLM and Agent Evaluation
Build and review software with AI
A scoped, independently tested repository change using the selected coding tool.
- Artificial Intelligence Foundations
- Software Engineering Foundations for AI Engineers
- Programming Language Concepts for AI Engineers
- Applied Generative AI
- AI-Assisted Software Development
Choose one coding tool
- Claude Code Engineering · Provisional
- Codex and OpenAI Coding Agents · Provisional
- OpenCode and Open Agentic Coding Tools · Provisional
Optional depth
Harness depth
Formal verification depth
Application-evaluation depth
Build knowledge and context systems
A source-qualified knowledge/context model and a bounded hybrid decision prototype.
- Knowledge Engineering Foundations for AI Systems
- Database Systems for AI Applications
- Semantic Web and Ontology Engineering
- Knowledge Graph Engineering
- Artificial Intelligence Foundations
- Applied Generative AI
- Software Engineering Foundations for AI Engineers
- Programming Language Concepts for AI Engineers
- Building Applications with LLMs
- Agentic AI Foundations
- Retrieval-Augmented Generation
- Context Engineering and Context Graphs
- Neuro-Symbolic AI
Operate AI infrastructure
A workload-driven inference decision with resource, recovery, and operational checks; select platform/data specializations only when needed.
- Cloud Foundations for AI Engineers
- Observability Foundations for AI Systems
- Artificial Intelligence Foundations
- How Large Language Models Work
- Programming Language Concepts for AI Engineers
- Applied Generative AI
- Building Applications with LLMs
- AI Infrastructure
Optional depth
Local-model operations
AWS specialization
Cloud-native and developer-platform specialization
Data-platform specialization
- Database Systems for AI Applications
- PostgreSQL Development
- Data Engineering Foundations for AI Systems
- Data Platforms for AI Workloads
Vector-infrastructure specialization
Build AI-enabled and agent-accessible web systems
A web feature with explicit interaction states, capability descriptions, access checks, and controlled release.
- Web Application Foundations for AI Engineers
- Deployment Foundations for AI Web Applications
- Artificial Intelligence Foundations
- Applied Generative AI
- Software Engineering Foundations for AI Engineers
- Programming Language Concepts for AI Engineers
- Building Applications with LLMs
- Agentic AI Foundations
- Web Application Development in the AI Era
- The Agent-Accessible Web
Optional depth
Cloudflare specialization
Content discovery
Protocol depth
Agent-security depth
Redesign and govern organizational work
A noncoding pilot dossier with ownership, authority, measurement, and scale-or-stop criteria.
Design a controlled solo-business workflow
A repeatable business workflow with draft-only actions, reviewed rules, and total-owner-effort evidence.
All AI courses, by category
Categories connect engineering foundations with AI practice. The cloud courses include Bedrock-centered AWS work and comparisons of Microsoft Foundry, Google Cloud managed AI, and Cloudflare AI services. Choose a course to see its scope, modules, and exercises; these are not interchangeable provider implementations.
Course category · 3 courses
Software Engineering Foundations
Follow the software lifecycle, compare programming and software-design approaches, and use precise models and checked proofs. Build foundations for later AI engineering.
Software Engineering Foundations for AI Engineers
6 hours · 3 modules · Level 1
Follow a software change from an initial requirement to a maintained release. Learn how teams plan work, use version control, review code, test changes, and automate delivery. Distinguish development, QA, staging, and production environments and understand how releases, monitoring, and feedback connect the software development lifecycle. The course concerns delivering software, not programming paradigms.
View course outlineProgramming Language Concepts for AI Engineers
8 hours · 4 modules · Level 1
Learn how programs represent data, organize behavior, and execute. Compare procedural, object-oriented, and functional approaches using the same small task. Explore types, scope, references, memory lifetime, errors, and shared-state concurrency through runnable examples. Connect these ideas to readable, testable programs before considering generated code.
View course outlineFormal Methods for Reliable AI Systems
6 hours · 3 modules · Level 1
Tests check selected executions. Formal methods make requirements and assumptions precise so that behavior can be explored or claims proved. Specify a small shared resource controller, find and correct a counterexample with TLA+ and TLC, and complete a small checked proof in Lean. Connect these methods to reliable software and AI-system control without claiming to prove generated answers true.
View course outline
Course category · 5 courses
AI Foundations
Understand modern AI, how models work, and where their capabilities end.
Artificial Intelligence Foundations
8 hours · 4 modules · Level 1
Explore how AI solves problems through explicit rules, statistical learning, neural networks, and generation. Learn the difference between supervised and unsupervised learning and between regression, classification, and clustering. Compare linear models, decision trees, and classic text-processing techniques before placing deep learning and generative AI in the broader picture. Use small experiments to distinguish deterministic execution, probabilistic prediction, and sampled generation, then choose and check an appropriate approach.
View course outlineHow Large Language Models Work
6 hours · 3 modules · Level 2
Follow a short text request through tokenization, learned representations, attention, and next-token generation. See how a decoder-style transformer uses context and why sampling changes its output. Connect these mechanisms to context limits, inference memory, reasoning-style models, and multimodal inputs through worked examples and controlled experiments rather than usage-accounting exercises.
View course outlineApplied Generative AI
6 hours · 3 modules · Level 2
Use generative AI to summarize, extract, transform, and draft useful content. Develop prompts, provide relevant context, request structured results, and check what the model produces. Try a text-and-image task and observe a complete tool exchange. Compare task results to choose a model or a simpler non-model approach.
View course outlineLocal and Small Language Models
6 hours · 3 modules · Level 2
Run a language model on a machine you operate rather than relying on a hosted model API. Choose a model that fits the task and hardware, load it with Ollama, and call it from a terminal and a small client. Compare configurations and understand quantization, formats, memory, licensing, and data-handling trade-offs.
View course outlineModel Adaptation and Fine-Tuning
8 hours · 4 modules · Level 3
A house style lives in the weights, not in the prompt. Build forty instruction pairs, train a small adapter on one GPU, and score it against a prompt baseline. Then serve the merged model locally and write when to tune and when to prompt.
View course outline
Course category · 3 courses
AI Application Engineering
Build grounded, useful AI applications—and evaluate how well they work.
Building Applications with LLMs
8 hours · 4 modules · Level 3
Build one useful application that combines a language model, an external service, structured outputs, conversation context, and retrieved documents. Learn the underlying request and tool flow, then use LangChain to connect the components. Keep memory and stored application data explicit and test the application's behavior when a service, model output, or retrieval result fails.
View course outlineRetrieval-Augmented Generation
8 hours · 4 modules · Level 3
Build a question-answering application that retrieves relevant document passages before generating an answer. Prepare documents, create embeddings and an index, compare retrieval methods, and construct useful model context. Generate cited answers and investigate failures by separating retrieval performance from answer support. Compare graph-assisted retrieval without making a graph database the starting requirement.
View course outlineAI Application Evaluation
6 hours · 3 modules · Level 3
Determine whether an AI application meets its task requirements and whether a change genuinely improves its measured behavior. Create datasets and rubrics, implement evaluators, compare human and model judgments, and run a regression suite. Consider quality, latency, cost, and user effort together rather than accepting a fluent answer or a single average score as sufficient evidence. Distinguish exact-result correctness, uncertain predictive performance, and the quality and reliability of outputs that can legitimately vary.
View course outline
Course category · 5 courses
AI-Assisted Software Engineering
Use AI to build better software, from requirements to tested implementation.
Tool-specific courses are provisional. Depending on demand, they may instead become modules within AI-Assisted Software Development.
AI-Assisted Software Development
6 hours · 3 modules · Level 3
Revisit the software development lifecycle from C01 and examine how AI changes the way teams plan, implement, review, test, and integrate software. Use AI on a real change, revise effort estimates, and compare automated and human review. Explore an issue-to-merge workflow and decide where fuller automation improves delivery, where it shifts work, and where human decisions remain necessary.
View course outlineHarness Engineering
10 hours · 5 modules · Level 4
Start with existing agent environments such as Claude Code, OpenCode, and ChatGPT Desktop. Study how they expose tools, supply context, retain information, and control actions through documented interfaces and observable behavior. Create an Agent Skill and investigate progressive disclosure. Then use what you learned to assemble a small custom harness with tools, explicit state, permission checks, and a bounded execution loop.
View course outlineClaude Code Engineering
10 hours · 5 modules · Level 4
Provisional courseUse Claude Code to explore, change, test, and review a repository. Shape its behavior through project instructions, commands, skills, hooks, and integrations. Manage context and permissions, delegate bounded work, and run a dynamic workflow. Turn a recurring task into repeatable automation with independently checked results.
View course outlineCodex and OpenAI Coding Agents
10 hours · 5 modules · Level 4
Provisional courseUse Codex to explore, change, test, and review a repository. Shape its behavior through project instructions, commands, skills, hooks, and integrations. Manage context and permissions, delegate bounded work, and build a repeatable workflow. Learn the Codex-specific steps for the same engineering concepts taught in the Claude Code and OpenCode courses.
View course outlineOpenCode and Open Agentic Coding Tools
10 hours · 5 modules · Level 4
Provisional courseUse and customize OpenCode for repository engineering. Configure models, instructions, commands, skills, tools, and MCP integrations. Manage context, permissions, and delegated work, then automate a repeatable task. Inspect the client/server boundary through CLI queries and extend a small local plugin. Apply the same engineering concepts as C13 and C14 through OpenCode-specific steps.
View course outline
Course category · 5 courses
Agentic Systems
Design agents that plan, use tools, collaborate, and operate within clear boundaries.
Agentic AI Foundations
6 hours · 3 modules · Level 3
Build a small agent with LangChain and see how it selects a next step from a goal, tools, and observed results. Compare this with a fixed workflow. Add simple planning and memory, inspect actual tool calls, and check proposed corrections. Keep the agent bounded through human oversight and enforced execution limits without assuming that reflection guarantees success.
View course outlineAgent Architecture and Orchestration
12 hours · 6 modules · Level 4
Design how agents divide work, communicate, and share only the context each task needs. Compare supervisors, hierarchical teams, handoffs, parallel workers, and shared-conversation systems. Build a small coordinated team, then extend it into an event-driven service that continues across sessions. Keep durable task state separate from each model's limited context window.
View course outlineAgent Interoperability and Protocols
10 hours · 5 modules · Level 4
Learn which interfaces connect agents to tools, other agents, coding clients, user interfaces, and websites. Build a small MCP interaction and examine each other mechanism through its own concrete example and guided activity. Compare execution, context, identity, payment, and ecosystem governance without treating them as interchangeable protocols.
View course outlineAgent Execution Environments
10 hours · 5 modules · Level 4
Choose where agent code and browser actions run and what they can access. Operate a disposable environment with real file, network, and resource limits. Use a dedicated browser session and inspect its authority. Compare containers, microVMs, isolates, and hosted sandboxes. Share code and data across agents without uncontrolled writes, then verify termination, revocation, and cleanup.
View course outlineAgent Platforms and Frameworks
16 hours · 8 modules · Level 4
Learn the common building blocks of agent frameworks, then implement one small task in each major framework through a dedicated module. Work with OpenAI Agents SDK, Microsoft Agent Framework, Google ADK, LangChain, LangGraph, and n8n. Compare real tool use, state, execution flow, inspection, and failure behavior before choosing a framework or simpler custom controller.
View course outline
Course category · 6 courses
Workflow Engineering
Model work before adding AI. Assign rules, models, and people clear responsibilities; design reliable execution and measure total work, review capacity, and outcomes.
Workflow Foundations for AI Automation
8 hours · 5 modules · Level 1
Model work before choosing automation. Follow cases through tasks, events, state, handoffs, decisions, and queues. Distinguish fixed rules, uncertain predictions, and stochastic generation. Choose among classical machine learning, specialized or general language models, explicit decision rules, and human judgment. Connect these choices in a BPMN workflow and test whole-process consequences.
View course outlineHuman–AI Workflow Design
8 hours · 4 modules · Level 2
Design people, technology, and work practices together. An agent deployment changes who reviews, decides, learns, and recovers when something fails. Study actual work, assign roles and authority, and test human review. Preserve the skills needed to supervise and recover automation through manual rotation, escalation practice, and incident drills. Design adoption and trust repair too.
View course outlineWorkflow Performance Engineering
6 hours · 4 modules · Level 2
Measure useful completed outcomes across the whole work system before adding AI. Trace waiting, handoffs, quality, review, rework, cost, and human capacity. Test whether a local speedup improves the total result or merely moves the bottleneck. Compare constraint-focused redesign and simpler non-AI options. Design a bounded improvement test with feedback and stop criteria.
View course outlineEvent-Driven Workflow Design
10 hours · 5 modules · Level 4
Build workflows that react to events, including events that start or resume agents. Follow repair requests through triage, investigation, and parts arrival. Separate fixed event routing from agent-selected work. Implement durable messages, state, history, and a bounded agent activation. Test duplicates, stale evidence, restarts, and feedback loops without replaying actions during history rebuild.
View course outlineReliable Workflow Execution
16 hours · 8 modules · Level 5
Choose what the model and harness coordinate and what an external orchestrator must track. Design branches, joins, loops, and completion checks. Execute work across worker failures, uncertain effects, and restarts. Then build a controlled improvement loop that tests proposed workflow changes before adopting them. Longer agent runs and more iterations do not guarantee completion or improvement.
View course outlineDynamic and Agentic Workflows
10 hours · 5 modules · Level 6
Generate a typed plan and operate it interactively through a coding-agent harness. Inspect dependencies, run selected eligible stages, pause, check results, and re-evaluate the remaining work. When new evidence changes the required work, revise the plan and determine which artifacts remain valid. Keep model-selected stages bounded and compare the adaptive result with a simpler fixed workflow. Approval constrains execution but does not replace planning, compilation, or adaptation.
View course outline
Course category · 5 courses
Knowledge Engineering
Turn source-qualified claims into useful AI evidence. Connect representation, retrieval, context, and explicit reasoning without treating generated text as verified knowledge.
Knowledge Engineering Foundations for AI Systems
6 hours · 3 modules · Level 1
Turn a domain description into information that people and software interpret consistently. Define entities, relationships, categories, and rules. Distinguish what a source says from what follows from accepted facts. Answer new questions and maintain the model when meanings or evidence change. Apply these foundations to reviewing model-extracted claims only after the representation is clear.
View course outlineSemantic Web and Ontology Engineering
10 hours · 5 modules · Level 2
Make datasets share identities and explicit meanings. Encode RDF, query it with SPARQL, and express a small ontology in RDFS and OWL. Run a reasoner and explain its conclusions. Validate data separately with SHACL. Compare ontology versions without confusing absent facts, inconsistent axioms, and invalid records.
View course outlineKnowledge Graph Engineering
10 hours · 5 modules · Level 2
Build a graph that answers useful relationship questions. Choose entity identities, model edges, load a graph database, and write multi-hop queries. Resolve duplicates without silently merging ambiguous entities. Make ingestion repeatable and maintain source-qualified assertions through correction and retirement.
View course outlineNeuro-Symbolic AI
12 hours · 6 modules · Level 2
Combine a model's ability to interpret text with explicit facts, rules, and checks. Reason forward from known facts and backward from a goal. Run both strategies, a real model extraction, and a small symbolic reasoner. Track premises through the decision and withhold unsupported conclusions. Compare model-only, rules-only, and hybrid behavior without assuming that correct deduction repairs false inputs.
View course outlineContext Engineering and Context Graphs
10 hours · 5 modules · Level 4
Give an agent the evidence it needs for the current task without sending every available record. Model knowledge, activities, decisions, users, and workflow state. Distinguish short-term and long-term memory from episodic, semantic, and procedural information. Implement memory lifecycle, source, time, access, and size rules. Test what a new agent session can recover from the resulting package and what it must leave unresolved.
View course outline
Course category · 5 courses
Data Engineering and Databases
Choose authoritative stores, prepare trustworthy AI datasets, and maintain derived retrieval indexes. Connect consistency, provenance, split isolation, and recoverable updates to AI application needs.
Database Systems for AI Applications
12 hours · 6 modules · Level 1
Choose a database from the questions and updates an application must support. Start with inventory records, relationships, queries, transactions, and recovery. Run SQLite queries and compare four data representations. Add ordinary indexes and full-text search, then compare vector search in PostgreSQL with a dedicated vector database. Apply these foundations to assistant documents and agent state without assuming that every application needs a vector store.
View course outlinePostgreSQL Development
16 hours · 8 modules · Level 2
Build and query a PostgreSQL application feature from a sound relational schema. Use constraints, transactions, functions, and JSON deliberately. Inspect actual plans for ordinary indexes, full-text search, and pgvector similarity queries. Compare exact neighbors with an approximate index without confusing distance with relevance. Finally record an offer change and its outbox event atomically without confusing persistence with delivery.
View course outlineData Engineering Foundations for AI Systems
10 hours · 5 modules · Level 2
Move ordinary changing records from sources to trustworthy outputs. Implement extraction, transformation, loading, quality checks, orchestration, and lineage. Test reruns, late arrivals, corrections, and schema changes. Then apply the same contracts to an AI dataset with explicit split isolation and sensitive-field rules.
View course outlineData Platforms for AI Workloads
12 hours · 6 modules · Level 3
Operate a small batch and stream platform before choosing a larger architecture. Transform records with Spark, produce and consume events with Kafka, and test restart, replay, lag, and retention assumptions. Connect storage, table formats, and analytical queries to clear responsibilities. Compare the platform with a simpler batch and apply the result to AI dataset refresh.
View course outlineVector and AI Data Infrastructure
14 hours · 7 modules · Level 3
Build a searchable document collection with actual embeddings and PostgreSQL vector queries. Choose relational queries, full-text search, or vectors for the same questions. Combine eligible candidates and run actual reranking when useful. Use independently judged questions to measure relevance rather than treating a short distance as a correct answer. Maintain compatible embedding generations through correction, deletion, and cutover.
View course outline
Course category · 6 courses
Cloud and Platform Engineering
Operate AI applications with explicit identity, data, capacity, and cost boundaries. Learn Bedrock-centered AWS engineering, compare managed AI offerings, and build repeatable cloud-native and developer-platform workflows.
Cloudflare may become a standalone course if demand supports it.
Cloud Foundations for AI Engineers
10 hours · 5 modules · Level 1
Explain how a small booking application uses compute, storage, networks, and identity. Compare infrastructure, platform, and software services by what the customer controls and operates. Shortlist ways to run one AI feature, compare their quiet and busy costs, then justify a choice. Restore actual local application data and compare the result with recovery targets set before the drill.
View course outlineCloud-Native Engineering for AI Workloads
14 hours · 7 modules · Level 1
Package an ordinary HTTP service with Docker, then operate it in a local Kubernetes cluster. Connect services, supply configuration and dummy secrets, set resources, and observe real rollout and failure behavior. Measure scaling against a dependency bottleneck before transferring the same reasoning to AI workers. The final worked map connects these foundations to model serving without requiring a model or GPU.
View course outlineAWS Engineering for AI Applications
10 hours · 5 modules · Level 2
Make authorized model requests on Amazon Bedrock and read actual source objects from Amazon S3. Connect a small local retrieval step to the model response. Inspect identity and network paths, handle errors with bounded retries, and remove lab resources. Compare managed model access with SageMaker AI and Knowledge Bases without claiming to deploy those additional services.
View course outlinePlatform Engineering for AI Teams
14 hours · 7 modules · Level 2
Build a small supported path that helps a developer start, test, and release an ordinary service. Begin with user needs, ownership, and support boundaries. Operate Terraform on safe local files and run a real local delivery workflow. Complete a self-service request, route an exception, and measure developer waiting and support work before proposing an improvement. Compare an AI-team extension through Kubeflow and KServe after the general developer path works.
View course outlineCloudflare for AI Applications and Agents
12 hours · 6 modules · Level 2
Provisional courseBuild a small Cloudflare application that answers support questions and stores bounded job state. Run a Worker, coordinate requests through a Durable Object, and make a real Workers AI exchange. Test duplicate requests, concurrent work, dependency failure, and data boundaries before comparing other execution choices.
View course outlineAI Infrastructure
12 hours · 6 modules · Level 4
Operate, measure, size, and choose inference infrastructure. Start a vLLM service on a prepared GPU host. Change its serving configuration and measure the effects on memory, latency, and useful throughput. Establish a bounded operating envelope. Choose compute from workload, data, persistence, availability, and effective cost.
View course outline
Course category · 3 courses
AI Operations, Evaluation and Observability
Make system behavior visible. Measure quality, reliability, latency, and cost.
Observability Foundations for AI Systems
12 hours · 6 modules · Level 1
Find why an ordinary order-status service is slow or failing. Collect structured logs, metrics, and distributed traces from running services. Query real data and build a dashboard. Define a reliability objective, diagnose an unseen fault, make one correction, and retest before transferring the method to AI stages.
View course outlineAI Observability
10 hours · 5 modules · Level 4
Instrument a support assistant that retrieves facts, calls a real model, and proposes a bounded local action. Generate observable records rather than starting with completed ledgers. Diagnose quality and execution failures, reconcile usage and costs, and connect a proposed action to independently checked application state.
View course outlineLLM and Agent Evaluation
20 hours · 9 modules · Level 4
Build an evaluator for a small support assistant with answer-only and permitted action tasks. Construct held-out data, generate real outputs from two configurations, and compare quality with independently checked outcomes. Contrast human ratings with actual automated judge calls. Separate small-sample evidence from reliability claims and simulated online monitoring from real user experiments. Use Jev in two roles: a bounded rubric evaluator and an evaluated assistant decision component. Keep retrieval, end-state, tool-trace, and human checks separate.
View course outline
Course category · 5 courses
AI Security, Governance and Trust
Protect systems, establish authority boundaries, and deploy AI responsibly.
AI Security Foundations
6 hours · 3 modules · Level 2
Untrusted retrieved text can try to turn an AI suggestion into a privileged tool action. Trace that path in a small mock application and define controls at input, data, and mutation boundaries. Test prevention, detection, and response evidence with harmless fixtures rather than relying on a defensive prompt alone.
View course outlineAI Governance
6 hours · 3 modules · Level 2
A policy has little operational value when nobody owns its exceptions or verifies its use. Create a fictional AI pilot dossier that links risk, delegated authority, human oversight, and evidence. Walk a policy change through distinct proposal, approval, deployment, observation, and revision responsibilities.
View course outlineResponsible AI
6 hours · 3 modules · Level 2
An AI recommendation can harm people who never chose to use the system. Review a fictional feature for unequal effects, unsupported claims, data exposure, and meaningful human choice. Define a reachable challenge process and a bounded deployment decision that leaves unresolved harms visible.
View course outlineAI Risk, Compliance and Audit
4 hours · 2 modules · Level 3
An action log can show what happened while leaving its approval and control effectiveness unproven. Reconstruct a fictional send incident using versioned policy, input, approval, and final-state evidence. Separate an established unauthorized action from an action whose approval record is missing. Produce a control review that separates design, observed operation, missing evidence, and legal questions.
View course outlineAgent Security
6 hours · 3 modules · Level 4
An agent may discover a tool or possess a credential without permission to commit an action. Build a delegated-action contract and enforce approval against exact parameters and object versions. Test escalation, stale approval, and changed scope in a local permission gate.
View course outline
Course category · 5 courses
AI-Native Web and Application Development
Create modern web experiences for people, AI-enabled interfaces, and agents.
Web Application Foundations for AI Engineers
6 hours · 3 modules · Level 1
An AI-generated action proposal must follow the same server rules as a browser submission. Build a small approval feature with an accessible frontend, typed tool API, and server-owned transitions. Inspect streamed progress without confusing it with a committed action, then test duplicate, stale, and unauthorized requests in a reproducible local preview.
View course outlineWeb Discovery in the AI Era
4 hours · 2 modules · Level 1
A retrieved page can be easy to find yet fail to support an answer or contain outdated claims. Audit a sample website for clear facts, stable identifiers, source attribution, and freshness. Test fixed questions locally and improve evidence availability without promising rankings, AI citations, or answer-engine inclusion.
View course outlineDeployment Foundations for AI Web Applications
4 hours · 2 modules · Level 2
An AI web preview can pass while the release changes its model configuration or exposes provider credentials. Compare static hosting with server-side AI backends and track application, prompt, and model-configuration versions together. Test exact-release approval, recovery, and exposure cleanup in a local simulator without creating paid resources.
View course outlineWeb Application Development in the AI Era
6 hours · 3 modules · Level 4
Stopping visible text does not necessarily stop backend work or undo a committed action. Build a mock AI-enabled web feature that separates generated proposals, validated artifacts, user approval, and actual effects. Keep rendering and authority on the application side, and report cancellation truthfully at each state.
View course outlineThe Agent-Accessible Web
6 hours · 3 modules · Level 4
An agent can discover a website capability without having permission to invoke it. Describe and expose one local capability with typed preconditions, side-effect declarations, and explicit access checks. Compare supplied protocol material with direct APIs and browser interaction without claiming universal client support or protocol conformance.
View course outline
Course category · 3 courses
AI Strategy and Adoption
Make deliberate adoption decisions, starting with workflows and real value.
AI Adoption for Organizations
6 hours · 3 modules · Level 2
Faster generation can increase review queues and make a workflow slower overall. Start with an organizational work problem and compare manual, deterministic, purchased, and hybrid improvements. Design a bounded pilot with ownership, total-effort measures, and scale-or-stop criteria rather than treating AI adoption as the outcome.
View course outlineOwning the AI Stack
6 hours · 3 modules · Level 2
Possessing model weights or business context does not mean an organization can operate or migrate its AI system. Compare sourcing options for one task while separating harness, provider, model, and portable work artifacts. Exercise an outage or exit scenario and make lifecycle responsibility, export rights, and unresolved dependencies explicit.
View course outlineAI for the One-Person Company
6 hours · 3 modules · Level 2
A solo business can lose scarce owner attention to checking and repairing its automations. Organize reusable business context and simulate one rules-first, draft-only workflow using synthetic records. Measure total owner effort and keep changes to routines, customer communications, and financial actions under explicit review.
View course outline