AI and Agents
How an MCP request flows
A walk through one Model Context Protocol request, from the client through authentication, memory and the model to a server that coordinates tools.
8 steps 8 parts Simplified view
Workflows
How things work, step by step
Interactive diagrams of the systems and ways of working I write and talk about. Play one through, or step at your own pace. Every step is also written out.
Featured
NL2Test, from a sentence to a Playwright test
How NL2Test turns a plain-language description into an executable Playwright test, with a model planning the test and an MCP server driving a real page.
10 stepsPress play, or use next and previous to follow the flow one step at a time.
Read all 10 steps
All workflows
Pick one to follow
AI and Agents
Multi-agent supervisor
A supervisor agent receives a request, hands sub-tasks to specialist agents one at a time, keeps shared memory, and combines their results into one answer.
8 steps 7 parts Simplified view
AI and Agents
RAG pipeline
How retrieval-augmented generation works end to end, from loading documents into a vector store to answering a question with the closest passages.
8 steps 7 parts Simplified view
Services
How I work with clients
How an engagement runs, from a client sharing a challenge to a tailored solution that draws on consulting, mentorship, development, speaking and digital transformation.
7 steps 7 parts Simplified view
Test Automation
Playwright AI Reporter pipeline
What happens when a Playwright test fails with the AI Reporter enabled, from capturing the failure to an AI fix suggestion, a bug, a draft pull request, stored history and notifications.
7 steps 7 parts Documented behaviour