All courses
33 published courses. Narrow by subject, role, level or format, or search by the outcome you are after.
Filter2
Filter courses
DoneSubject
For your role
Competency1
Format1
Several filters in one group widen the results; filters in different groups narrow them.
Matching courses
foundationalAI for Business
How to Tell If Your AI Is Any GoodFor non-technical leaders who sponsor or review AI products, this course cuts through eval jargon and vendor hype.
foundationalAI Literacy
LLM Guardrails, Evals and Agentic MemoryLearn to take LLM applications from prototype to production.
intermediateTechnical AI
Building Your First Production AgentA hands-on course for engineers who already call LLM APIs and want to ship a tool-using agent that survives production: recovering from failed tool calls, capping runaway spend, extending itself with an MCP server, passing task-completion evals, and deploying with logging enabled.
intermediateAI for Business
Prompt Patterns for Product DiscoveryAn intermediate, no-code course for product managers who already prompt chat-based LLMs and know discovery frameworks like JTBD.
foundationalAI Governance
What an Agent Actually Is (and What It Cannot Do)A foundational course for non-technical leaders who need to tell a genuine agentic system apart from a relabeled chatbot, recognize the concrete ways agents fail in production, judge when a task is too risky or irreversible to hand to an agent, and interrogate a vendor's 'agent' claim before sign…
intermediateAI Literacy
Evaluating LLM Output QualityHow to tell whether an LLM feature is actually working.
Matching modules
14 modules- Module 3Failure-Resilient Agent Loopsin Building Your First Production Agent · 4 lessonsai-for-engineersagentic-aiai-evalsworkflowsquickintermediate
- Module 6Evaluation for Task Completionin Building Your First Production Agent · 3 lessonsai-for-engineersai-for-data-analystsagentic-aiai-evalsquickintermediate
- Module 1Why LLM Outputs Break: Understanding Prompt Driftin Evaluating LLM Output Quality · 3 lessonsai-for-engineersai-for-product-managersai-for-data-analystsprompt-engineeringai-evalsquickfoundational
- Module 2Structured Output as a Contractin Evaluating LLM Output Quality · 3 lessonsai-for-engineersai-for-data-analystsprompt-engineeringai-evalsquickfoundational
- Module 3Corrective Retries: Recovering from Validation Failuresin Evaluating LLM Output Quality · 3 lessonsai-for-engineersai-for-data-analystsprompt-engineeringai-evalsworkflowsquickintermediate
- Module 4Measuring What Matters: Evaluation Metricsin Evaluating LLM Output Quality · 4 lessonsai-for-engineersai-for-product-managersai-for-data-analystsprompt-engineeringai-evalsquickintermediate
- Module 5Putting It Together: A Production-Ready Evaluation Pipelinein Evaluating LLM Output Quality · 3 lessonsai-for-engineersai-for-product-managersai-for-data-analystsprompt-engineeringai-evalsworkflowsquickadvanced
- Module 1Start Herein How to Tell If Your AI Is Any Good · 1 lessonai-for-leadersai-evalsquickfoundational
- Module 2Reading the Benchmark Landscapein How to Tell If Your AI Is Any Good · 3 lessonsai-for-leadersai-evalsquickfoundational
- Module 3From Score to Production Signalin How to Tell If Your AI Is Any Good · 3 lessonsai-for-leadersai-evalsquickfoundational
- Module 4Interrogating the Vendorin How to Tell If Your AI Is Any Good · 4 lessonsai-for-leadersai-evalsquickfoundational
- Module 2LLM Evaluation (Evals): Building Rigorous Testing Pipelinesin LLM Guardrails, Evals and Agentic Memory · 4 lessonsai-for-engineersai-for-data-analystscontext-ragai-evalsquickintermediate
- Module 4Evaluating AI-Generated Personasin Prompt Patterns for Product Discovery · 3 lessonsai-for-product-managersprompt-engineeringai-evalsresponsible-aiquickintermediate
- Module 3How Agents Fail in Productionin What an Agent Actually Is (and What It Cannot Do) · 4 lessonsai-for-product-managersai-for-leadersai-for-foundersagentic-aiai-evalsresponsible-aiquickfoundational