Developing with AI
For developers and technical teams who build software with AI, and build AI into software.
What you’ll learn.
AI coding assistants
GitHub Copilot, Claude Code, Cursor and Codex in the editor and the terminal, including agentic multi-file changes.
Working practices
Spec-first prompting, small reviewable diffs, tests before trust, and project instruction files such as CLAUDE.md and AGENTS.md.
Calling model APIs
The OpenAI and Anthropic APIs: structured JSON outputs, streaming, tool calls, error handling and retries.
Prompts as code
Versioned system prompts, templates and examples, reviewed and tested like any other code.
RAG and agents in products
Vector stores, retrieval quality, citations and permission-aware search inside your own applications.
Evaluation and observability
Eval suites, golden datasets, careful use of model-graded checks, tracing and monitoring for drift.
Security and privacy
Secrets management, PII redaction, Australian data residency and the OWASP Top 10 for LLM applications.
Deployment and cost
Rate limits, caching, model routing and budgets that hold up in production.
You’ll leave able to
- Use coding assistants without lowering quality
- Build reliable features on model APIs
- Measure quality with evals and tracing
- Ship AI features that meet security and privacy rules
Train your team.
In person or online, for any organisation. Tell us who needs training and which tools they use, and we will tailor the course.
Thank you. Request received.
We will be in touch within two business days.