Lab
Small working versions of the problems I deal with when I ship agents for real users. Play with them; they run in your browser.
What are you preparing for?
You've tried 0 of 16
Forward deployed work
Scoping with customers and wiring agents into their systems.
- In your browser
Discovery call simulator
A first call with a customer who says "we need AI". Choose your questions; the notes you leave with show how well you listened.
Open - In your browser
Scope a vague problem
Pick a fuzzy request, answer the discovery questions I'd ask on site, and get a scoped first week.
Open - In your browser
MCP analyzer
Connect to any MCP server, this site's included, and get a graded list of what's wrong with its tools and how to fix it.
Open - In your browser
MCP inspector
Browse a sample MCP server's tools, schemas and annotations, call them, and read the JSON-RPC.
Open
AI engineering
Tools, guardrails, retrieval, evals and context: what makes an agent safe and useful.
- Your API key
Live agent with an approval gate
Claude answers questions about my work by calling tools over this site, and stops for your approval before it acts.
Open - In your browser
Tool gate playground
Write tool definitions, set the harness policy, and watch which agent calls run, wait or get denied.
Open - In your browser
Prompt-injection spotter
Documents with hidden instructions meet an agent. Switch guardrails on and off and see which attacks land.
Open - In your browser
RAG chunking visualizer
Change chunk size and overlap, ask a question, and see which chunks retrieval would hand the model.
Open - In your browser
Eval bench
Score two versions of an agent against a golden set and find the regressions before your users do.
Open - In your browser
Agent trace debugger
Four recorded agent runs, each with a classic failure. Read the trace, diagnose it, and see the fix.
Open - In your browser
Prompt caching simulator
Reorder the parts of a request and watch cache hits and cost change over a conversation.
Open - In your browser
Context window budget
See how system prompt, tools, history and documents fill a context window, and what compaction buys you.
Open
Interview prep
Practise the questions FDE and AI engineering interviews actually ask.
- In your browser
AI engineer interview, beginner path
Four rounds: core-concept flashcards, system design (including an MCP server), coding you can run, and STAR behavioural answers.
Open - In your browser
Behavioural interview coach
A question bank with what interviewers are really asking, a story bank, timed practice, conflict resolution with the LEAD method, and a weak-vs-strong example.
Open - In your browser
Interview drill, experienced
Timed FDE and AI engineer questions, the rubric a strong answer covers, and optional feedback from Claude.
Open
Winning customers
Turn "AI could help" into a pilot someone signs.