Example · 3 days
AI engineering for a product team
Model APIs, retrieval over your own documentation, agents, MCP, security and evaluation, ending with a grounded assistant your team builds and demonstrates.
For developers and technical staff putting AI into an existing product.
Day 1
Working with LLM APIs
Quarter day · AI engineering · Intermediate
- API keys and authentication.
- Sending and receiving requests, structured JSON and streaming.
- Managing context and conversation state.
- Cost and token management.
- Enough Python to understand and change the examples. All code is supplied, with starting points and worked solutions.
LLM fundamentals
Quarter day · AI foundations · Foundation
- How an LLM actually produces text, at a practical level.
- Tokens, context windows, and what the model can and cannot see.
- Prompting, system instructions and structured outputs.
- Hallucination and reliability: why it happens and what reduces it.
- Known limits: arithmetic, recency, long documents and confident errors.
Choosing the right LLM and provider
Quarter day · AI engineering · Intermediate
- OpenAI, Anthropic, Gemini, open-weight models and small language models.
- Choosing on capability, cost, latency, security and use case.
- Enterprise plans vs direct API access.
- Self-hosted and local models as an option for confidential data.
Agents and tool calling
Quarter day · RAG and agents · Intermediate
- What an agent actually is, and when we need one.
- Function and tool calling.
- Letting an LLM work with your existing APIs and software.
- ReAct and Reflection concepts where useful.
- "Agentic first turns": the assistant opens the conversation with relevant context.
- When a conventional workflow is better than an autonomous agent.
Day 2
RAG and proprietary knowledge
Quarter day · RAG and agents · Intermediate
- Using your specifications, documentation and knowledge bases with an LLM.
- Embeddings, vector databases and hybrid search.
- Turning documentation into FAQs to improve retrieval.
- Citations and source grounding.
- Updating knowledge without retraining a model, and reducing hallucination.
MCP and integration architecture
Quarter day · AI architecture · Intermediate
- What MCP gives us in practical terms.
- Exposing existing company functionality and tools to an LLM. Example: finding the best-fit test script from a library using set criteria.
- How this could sit alongside your existing APIs and products.
- Lab: build a small MCP server over an existing API.
Security and commercial deployment
Quarter day · AI engineering · Intermediate
- Protecting proprietary and customer data.
- Data retention and privacy.
- Authentication, permissions and access control.
- Customer-facing versus internal AI.
- Guardrails and human decision boundaries.
AI-assisted software development
Quarter day · Software craft · Intermediate
- AI coding tools compared: Cursor, Claude Code and others.
- Plan mode: plan, review, then implement.
- Reviewing AI-generated code properly rather than "vibe coding".
- Reusable skills for repeated tasks.
- Agentic workflows: reviewing PRs, checking build pipelines, writing test plans and plain-English change summaries, and updating Jira tickets.
Day 3
Evaluation and production
Quarter day · AI engineering · Intermediate
- How to test objectively whether an AI solution works, using golden test sets and LLM-assisted scoring.
- Measuring accuracy and reliability.
- Logging, observability and human-in-the-loop.
- Cost and performance monitoring.
- Knowing when something is safe enough for production or customer use.
Use-case selection and architecture
Quarter day · AI for leaders · Intermediate
- Where AI provides real business value, rather than AI for its own sake.
- LLM vs RAG vs agent vs traditional software.
- Designing the right architecture for a given problem.
- Build vs buy.
Practical exercise: a grounded assistant
Quarter day · Labs and working sessions · Intermediate
- A scenario resembling your business.
- Take technical documentation and specifications.
- Build a grounded assistant around them.
- Ask technical questions and get answers with sources.
Practical exercise: tools, evaluation and a demo
Quarter day · Labs and working sessions · Intermediate
- Give the assistant access to an example API or tool.
- Evaluate whether its responses are reliable.
- Connect it to a simple front end.
- Demonstrate it to the group.