Example · 3 days
AI for leaders and architects
A shared, accurate picture of the technology, the decisions that matter, the risks, and a ranked list of where to start.
For technical leaders, architects and senior managers.
Day 1
What generative AI is, and is not
Quarter day · AI foundations · Foundation
- Language, image, speech and code models, and what each is good for.
- Where generative AI fits next to search, analytics and conventional software.
- Chat assistants, copilots, APIs and agents: the same models behind different products.
- Common claims, and how to tell a demonstration from a dependable capability.
Current AI: a working picture for leaders
Quarter day · AI for leaders · Foundation
- What today’s models can reliably do, and where they still fail.
- The vendor landscape: frontier labs, open models and cloud platforms.
- Assistants, RAG and agents in plain terms.
- Signals worth watching over the next year, and noise to ignore.
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.
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.
Day 2
Production risk and operating cost
Quarter day · AI for leaders · Intermediate
- What changes between a pilot and a production service.
- Security, privacy and the failure modes that reach customers.
- Running cost: tokens, hosting, people and evaluation.
- Questions to ask a team before approving a launch.
The LLM threat model
Quarter day · AI engineering · Advanced
- Why a model is neither a trusted component nor a simple input.
- Assets, trust boundaries and attackers for an LLM-backed system.
- The OWASP Top 10 for LLM applications.
- Exercise: threat-model a real feature.
Identity, security and governance for AI
Quarter day · AI architecture · Advanced
- Acting on behalf of a user: identity through to tools and data.
- Data classification and what may reach which model.
- Audit, retention and regulatory obligations.
- Governance that teams can follow without a committee.
From pilot to platform
Quarter day · AI for leaders · Intermediate
- Why pilots stall, and what gets them out of the lab.
- Shared services: model access, retrieval, evaluation and policy.
- Teams, skills and ownership.
- A first-year plan the organisation can fund.
Day 3
Discovery: map the work
Quarter day · Labs and working sessions · Foundation
- Walk through the work of each team.
- Find repetitive, document-heavy and judgement-heavy tasks.
- Capture volumes, pain and data available.
- Output: a long list of candidates.
Discovery: score the candidates
Quarter day · Labs and working sessions · Foundation
- A scoring framework: value, feasibility, data, risk.
- Score as a group, and argue about the outliers.
- Spot dependencies and shared foundations.
- Output: a scored list.
Discovery: test the top candidates
Quarter day · Labs and working sessions · Foundation
- Try the top ideas with real examples and a capable assistant.
- What worked, what did not, and why.
- Rough cost and effort for each.
- Output: evidence beside each score.
Discovery: rank and commission
Quarter day · Labs and working sessions · Foundation
- A ranked shortlist.
- A brief for each: problem, users, measures and owner.
- What to stop or not start.
- Output: work ready to commission.