AI courses for engineers and teams
Build with AI. Understand what makes it work. Explore foundations, applications, agents and the engineering practices that connect them.
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 58 courses across 13 areas.
Contact us for full course details.
Featured courses
Retrieval-Augmented Generation
6 hours · 3 modules
Generated answers can omit or misrepresent relevant evidence. Build a retrieval pipeline and test whether its context supports answers to a defined set of questions.
Explore course →AI-Assisted Software Development
6 hours · 3 modules
Generated code still needs engineering judgment. Use AI assistance across a small change while keeping requirements, reviews, and tests under developer control.
Explore course →Human–AI Workflow Design
6 hours · 3 modules
Automation can obscure who must make a decision. Design human–AI collaboration with explicit authority, review, escalation, and opportunities to retain judgment skills.
Explore course →AI Security Foundations
4 hours · 2 modules
AI features introduce new paths for untrusted input and tool misuse. Threat-model a small application and design layered controls for data and execution boundaries.
Explore course →All AI courses, by category
Categories group related courses. Choose a course to see its modules, topics and practical exercises.
Course category · 3 courses
Software Engineering Foundations
The enduring engineering principles beneath reliable, AI-enabled systems.
Modern Software Engineering Foundations
4 hours · 2 modules
When software becomes difficult to change, design choices need explicit evaluation. Apply engineering principles to structure an application and assess its reliability.
View course outlineProgramming Language Concepts
4 hours · 2 modules
Language behavior can obscure performance and correctness problems. Examine how programs are parsed, checked, and executed to make informed implementation choices.
View course outlineFormal Methods for Software Engineers
4 hours · 2 modules
Tests alone may miss unexpected state transitions. Specify a small system, express its invariants, and explore formal checks before implementation.
View course outline
Course category · 4 courses
AI Foundations
Understand modern AI, how models work, and where their capabilities end.
Artificial Intelligence Foundations
4 hours · 2 modules
AI terminology can make solution choices difficult. Develop a practical model of how AI systems learn and generate outputs, then assess their suitability for a task.
View course outlineHow Large Language Models Work
6 hours · 3 modules
Unexpected model outputs are easier to investigate when their mechanisms are understood. Explore language model internals to interpret context, generation, and resource trade-offs.
View course outlineApplied Generative AI
6 hours · 3 modules
Useful AI outputs need more than a single prompt. Design structured, context-aware interactions and select models for practical generation and classification tasks.
View course outlineLocal and Small Language Models
4 hours · 2 modules
Hosted inference may not fit a workload's privacy or resource constraints. Evaluate small models and local runtimes to choose a workable deployment approach.
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
4 hours · 2 modules
A model demo does not provide application reliability. Build explicit interfaces, state handling, and review paths for a small LLM-powered application.
View course outlineRetrieval-Augmented Generation
6 hours · 3 modules
Generated answers can omit or misrepresent relevant evidence. Build a retrieval pipeline and test whether its context supports answers to a defined set of questions.
View course outlineAI Application Evaluation
4 hours · 2 modules
Anecdotal model outputs do not show whether an application is improving. Define representative tests and compare quality, retrieval, cost, and latency with explicit criteria.
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
Generated code still needs engineering judgment. Use AI assistance across a small change while keeping requirements, reviews, and tests under developer control.
View course outlineHarness Engineering
6 hours · 3 modules
Coding agents need controlled execution rather than unrestricted access. Design a harness with clear instructions, tool boundaries, recoverable state, and human approval.
View course outlineClaude Code Engineering
6 hours · 3 modules
Provisional courseTool-driven repository work needs explicit scope and verification. Explore Claude Code workflows to organize context, reusable instructions, and reviewable automation.
View course outlineCodex and OpenAI Coding Agents
4 hours · 2 modules
Provisional courseDelegating a coding task requires more than an instruction. Structure Codex-style workflows around repository context, bounded tools, and evidence-based review.
View course outlineOpenCode and Open Agentic Coding Tools
4 hours · 2 modules
Provisional courseOpen coding tools offer choices that need deliberate configuration. Examine OpenCode sessions, integrations, and model options to build a bounded repository workflow.
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
Not every AI task needs an autonomous agent. Compare agents with fixed workflows and design a bounded agent loop with clear human oversight.
View course outlineAgent Architecture and Orchestration
6 hours · 3 modules
Adding agents can increase coordination failures as well as capacity. Design explicit delegation, communication, and lifecycle rules for a multi-agent application.
View course outlineAgent Interoperability and Protocols
4 hours · 2 modules
Agent integrations use protocols with different responsibilities and maturity levels. Compare their interfaces and trust boundaries before selecting an integration approach.
View course outlineAgent Execution Environments
6 hours · 3 modules
Agents that execute code or interact with interfaces need isolation. Compare execution environments and define boundaries for a disposable, inspectable agent task.
View course outlineAgent Platforms and Frameworks
4 hours · 2 modules
Framework choices can introduce unnecessary coupling. Compare agent platform abstractions against a small task and determine when custom orchestration is simpler.
View course outline
Course category · 6 courses
Workflow Engineering
Understand work as a system. Design reliable execution and thoughtful human–AI collaboration.
Workflow Engineering Foundations
6 hours · 3 modules
Work can stall at handoffs even when individual tasks are efficient. Model a real process to expose state, queues, and improvement opportunities before automating it.
View course outlineEvent-Driven Workflow Design
6 hours · 3 modules
Processes that react to events can become difficult to trace. Design explicit commands, state transitions, and correlation rules for a long-running workflow.
View course outlineReliable Workflow Execution
6 hours · 3 modules
Failures and retries can duplicate work or leave processes incomplete. Design recoverable execution with explicit dependencies, idempotency, and compensation paths.
View course outlineHuman–AI Workflow Design
6 hours · 3 modules
Automation can obscure who must make a decision. Design human–AI collaboration with explicit authority, review, escalation, and opportunities to retain judgment skills.
View course outlineDynamic and Agentic Workflows
6 hours · 3 modules
Generated plans must be validated before they control execution. Combine agent planning with deterministic checks and human intervention in an adaptable workflow.
View course outlineWorkflow Performance Engineering
6 hours · 3 modules
Faster individual tasks do not necessarily improve the whole workflow. Measure flow, quality, and rework to identify constraints and test improvement hypotheses.
View course outline
Course category · 5 courses
Knowledge Engineering
Turn information into connected knowledge, useful context, and hybrid reasoning systems.
Knowledge Engineering Foundations
4 hours · 2 modules
Documents alone do not make relationships explicit. Model facts and concepts so that knowledge can be queried, reviewed, and maintained for practical use.
View course outlineSemantic Web and Ontology Engineering
6 hours · 3 modules
Integrating knowledge requires shared meanings as well as shared formats. Build a small ontology and query its facts while making reasoning assumptions explicit.
View course outlineKnowledge Graph Engineering
4 hours · 2 modules
Connected data can become inconsistent without clear identities and schemas. Construct a small knowledge graph with repeatable ingestion, queries, and maintenance checks.
View course outlineContext Engineering and Context Graphs
6 hours · 3 modules
An agent needs relevant situation-specific information, not every available fact. Model context with provenance and time, then retrieve the evidence needed for a task.
View course outlineNeuro-Symbolic AI
4 hours · 2 modules
Generated suggestions may violate explicit domain rules. Combine model outputs with symbolic representations and constraint checks for inspectable hybrid reasoning.
View course outline
Course category · 5 courses
Data Engineering and Databases
Design data systems and pipelines that support operational and AI workloads.
Modern Database Systems
4 hours · 2 modules
Database selection should follow access patterns and operational constraints. Compare database models using a small application's consistency, query, and deployment needs.
View course outlinePostgreSQL Development
4 hours · 2 modules
Application data needs correct schemas and predictable queries. Develop a PostgreSQL-backed feature and inspect its transactions, indexes, and query behavior.
View course outlineData Engineering Foundations
4 hours · 2 modules
Reliable analysis depends on repeatable data movement and transformation. Build a small pipeline with quality checks, scheduling rules, and traceable lineage.
View course outlineModern Data Platforms
4 hours · 2 modules
Data platforms combine storage and processing components with different responsibilities. Compare their roles and design a small batch-and-stream architecture for an analytical workload.
View course outlineVector and AI Data Infrastructure
4 hours · 2 modules
Semantic retrieval depends on indexing and filtering choices. Build and compare vector-backed retrieval paths with explicit relevance and metadata requirements.
View course outline
Course category · 6 courses
Cloud and Platform Engineering
Build the infrastructure, platforms, and environments modern applications need.
Cloudflare may become a standalone course if demand supports it.
Cloud Computing Foundations
4 hours · 2 modules
Cloud services need to be selected around workload constraints. Design a basic deployment with explicit identity, reliability, and cost assumptions.
View course outlineAWS Engineering
4 hours · 2 modules
AWS architectures need clear permissions and operating controls. Map a workload to services and define a repeatable deployment with observable behavior.
View course outlineCloud-Native Engineering
6 hours · 3 modules
Containerized applications need explicit configuration and operational behavior. Package and deploy a small service while inspecting discovery, scaling, and observability controls.
View course outlinePlatform Engineering
4 hours · 2 modules
Repeated infrastructure setup can slow development and create inconsistency. Design a small self-service platform path with versioned configuration and explicit operating responsibilities.
View course outlineAI Infrastructure
4 hours · 2 modules
Model deployment choices affect latency, cost, and data handling. Design serving and routing infrastructure around a defined workload and compare local and managed options.
View course outlineCloudflare for Modern Applications
4 hours · 2 modules
Provisional courseEdge workloads need clear state and execution boundaries. Examine Cloudflare application components and design a small request flow without assuming access to every platform feature.
View course outline
Course category · 3 courses
AI Operations, Evaluation and Observability
Make system behavior visible. Measure quality, reliability, latency, and cost.
Observability Engineering
4 hours · 2 modules
Troubleshooting requires evidence across service boundaries. Instrument a small application and connect logs, metrics, and traces to explicit reliability objectives.
View course outlineAI Observability
6 hours · 3 modules
AI failures can arise from prompts, models, or tools. Trace an application interaction to connect resource usage, execution steps, and decision evidence without exposing sensitive inputs.
View course outlineLLM and Agent Evaluation
6 hours · 3 modules
Agent completion claims need independent evidence. Design evaluation suites that distinguish answer quality, task execution, retrieval performance, and human judgment.
View course outline
Course category · 5 courses
AI Security, Governance and Trust
Protect systems, establish authority boundaries, and deploy AI responsibly.
AI Security Foundations
4 hours · 2 modules
AI features introduce new paths for untrusted input and tool misuse. Threat-model a small application and design layered controls for data and execution boundaries.
View course outlineAgent Security
6 hours · 3 modules
An agent's access must remain narrower than its ability to propose actions. Design identity, permission, and isolation controls for delegated tool execution.
View course outlineAI Governance
4 hours · 2 modules
AI adoption needs decision ownership and evidence, not policy statements alone. Develop a governance record that connects risk, controls, oversight, and review responsibilities.
View course outlineAI Risk, Compliance and Audit
4 hours · 2 modules
Risk controls need traceable evidence and a response process. Build a sample control matrix and audit trail while distinguishing technical evidence from jurisdiction-specific compliance conclusions.
View course outlineResponsible AI
4 hours · 2 modules
An AI system can affect people beyond its immediate task. Assess a use case for fairness, safety, privacy, and human agency before defining deployment safeguards.
View course outline
Course category · 5 courses
AI-Native Web and Application Development
Create modern web experiences for people, AI-enabled interfaces, and agents.
Modern Web Application Development
4 hours · 2 modules
A web feature spans browser interfaces and server responsibilities. Build a small application with explicit API contracts, access checks, and a reproducible deployment path.
View course outlineWeb Application Development in the AI Era
4 hours · 2 modules
AI interfaces need to communicate progress, uncertainty, and user control. Build a small AI-enabled web interaction with safe rendering and explicit backend boundaries.
View course outlineThe Agent-Accessible Web
4 hours · 2 modules
Agents need clear machine-readable interfaces rather than fragile page interactions. Design discoverable web capabilities with explicit identity and authorization boundaries.
View course outlineWeb Discovery in the AI Era
4 hours · 2 modules
Content needs to be understandable to both people and retrieval systems. Review website structure and provenance to improve clarity without promising search placement or AI citations.
View course outlineModern Web Deployment
4 hours · 2 modules
Deployment choices must fit application runtime and review needs. Compare static, serverless, and preview approaches and create a repeatable release plan with safe access boundaries.
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
4 hours · 2 modules
AI adoption should begin with a work problem rather than a tool purchase. Assess opportunities, design a bounded pilot, and define evidence for a scale-or-stop decision.
View course outlineOwning the AI Stack
6 hours · 3 modules
AI sourcing decisions shape control over data, costs, and operations. Compare hosted and self-managed options to make ownership and vendor trade-offs explicit.
View course outlineAI for the One-Person Company
6 hours · 3 modules
A solo business needs automation that preserves ownership of important decisions. Map repeatable work and design small AI-assisted processes with review checkpoints and clear limits.
View course outline