Lab
Try it yourself.
Small, interactive simulations of problems I spend time on. They run entirely in your browser and are educational models, not benchmarks or running systems.
Interactive simulation
A demo is the beginning.
Explore what changes when an AI application meets the real world.
- Application
- Gateway
- Provider
Interactive explainer
Same question. Different words.
See how exact-match and semantic caching decide when an earlier answer can be reused.
- Question
- Cache?
- Answer
Interactive visualiser
One request, eight plugins.
Follow a single AI request through an ordered chain of gateway plugins, switch any of them off and see what changes.
- Request
- Plugins
- Model
Calculator
Price the workload before the invoice does.
Estimate monthly AI token cost, see what caching, routing, compression and output caps save, and check peak traffic against rate limits.
- Traffic
- Savings
- Cost
Interactive playground
No single guard stops every injection.
Try curated prompt injection attacks against a mock support agent and see which layered defences stop each one.
- Attack
- Defences
- Verdict
Interactive explainer
Agents call tools. Someone should check.
Step through how an AI agent discovers and calls tools with the Model Context Protocol, and see what a gateway adds between the client and remote MCP servers.
- Agent
- Gateway
- Tools
Live comparison
Same prompt. Three clocks.
Send one curated prompt to several LLM providers at once and compare time to first token, total time, tokens per second and cost.
- Prompt
- Models
- Timings