
Production Engineer Track
From feature builder to system owner.
The third rung. The on-call mindset, observability for AI systems, reliability and fallback chains, security in AI-built systems, compliance for regulated environments, documentation that survives, and team practices in the AI-native era. Capstone: each student leads a multi-service project with three to five other students through to production deployment with monitoring, runbooks, and an incident playbook.
- Price
- £2,999
- Length
- 10 weeks
- Prerequisite
- AI Native or equivalent
- Cohort size
- Capped at 15
- Time commitment
- 20-25 hours per week
What you could build
Production graduates lead a multi-service project to production, with monitoring, runbooks, and an incident playbook. This is the kind of system that takes.
Live
Monitoring and runbooks
Curriculum
- Week 1 · System ownership mindset
- What changes when you move from "ships features" to "owns the system in production". The on-call mindset, the incident-response mindset, the post-mortem discipline.
- Week 2 · Observability for AI systems
- Logs, metrics, traces. PostHog, Sentry, OpenTelemetry, LangSmith, Helicone. What to alert on, what to leave as a dashboard. Cost monitoring. Error budgets and SLOs.
- Week 3 · Reliability and fallback chains
- Multi-provider fallback chains in depth using Marktrader's cascade as the worked example. Circuit breakers, retries with backoff, idempotency. Graceful degradation when the AI fails.
- Week 4 · Security in AI-built systems
- Prompt injection. Data leakage through model context. Authorisation: the AI is not a permission boundary. Input/output validation. Secrets management, KMS, BYOK patterns. Provider-side compliance posture.
- Week 5 · Architecture decisions and trade-offs
- Monolith vs services vs serverless. Edge vs origin. Database choice. Queues, jobs, workers. Caching layers. The build-vs-buy decision tree for AI applications.
- Week 6 · Compliance and regulated environments
- GDPR. EU AI Act high-risk classifications. UK FCA expectations. NHS DSPT. CQC framework. WCAG 2.2. Age-verification and consent flows.
- Week 7 · Documentation that survives
- READMEs that match the code. Architecture Decision Records. OpenAPI specs. Runbooks the on-call engineer can actually use at three in the morning.
- Week 8 · Working with legacy code via AI
- Adding features to codebases you did not write. Using AI to summarise, navigate, refactor. Migration patterns: the strangler fig, parallel build, big-bang cutover.
- Week 9 · Team practices
- Code review when everyone has an AI assistant. Pair-programming patterns. Leading a team where every engineer works with AI. Sharing CLAUDE.md/AGENTS.md context across a team.
- Week 10 · Capstone
- Each student designs an architecture, leads a team of three to five other students implementing it, and ships the result to production with monitoring, runbooks, and an incident playbook.