How it works
This site is a case study of its own. Each topic explains one part of the system, and what it cannot do.
Topics
- Site topic
Analytics and observability
The owner can see what each question cost, which layer answered it, which tools failed and which topics had no answer, from one record per question made only of ids, fixed values and numbers. A printed metric sheet and four alerts do the rest.
- Site topic
Guardrails, privacy and security
Most of this site's defences are things it cannot do. An answer cannot contain a link, the assistant has no tool that sends a message, and no record it keeps has a field that could hold your words.
- Site topic
Knowledge layer
Everything the pages, the assistant and the crawlers say about Francesco comes from one compiled file, kb.json, built from Markdown and YAML kept in a private repository and published as /kb.json.
- Site topic
Known limits and design decisions
What this site has not proved, and what it gave up on purpose, knowing the cost.
- Site topic
Memory and personalisation
For now the site remembers no visitor. The conversation lives in your browser tab and is gone when you close it. Memory comes later, off until you turn it on, as a few fields with no text in them.
- Site topic
Model routing and cost control
A question stops at the cheapest layer that can deal with it. Rules come first, one small classifier second and the answering model last, and the whole agent runs inside a $20 monthly ceiling that the providers enforce.
- Site topic
Real metrics after launch
No number on these pages comes from real visitors yet. After launch, published metrics come from the metric sheet with their denominators and the date they were read, and until then every figure is a measurement on test sets written for the purpose.
- Site topic
Retrieval and context engineering
The assistant does not search. The published portfolio fits in its prompt, so every answer is written with all of it in view, and every citation is checked against the list of real ids before it reaches you.
- Site topic
SEO/GEO and static representation
Every page is static HTML built from the same file the assistant reads, with no JavaScript on content pages beyond a 2 KB script that animates the layout, one structured-data graph per page, and the whole corpus published for any machine that wants it.
- Site topic
Tool calling and UI control
The assistant can look facts up and propose where to go next. It cannot navigate, cannot rearrange the page and cannot send a message, and every destination it proposes is checked against the site's routes twice.
The data
Every page, and every answer the assistant gives, comes from one compiled file. It is published with its schema.
/kb.json: the knowledge base/kb.schema.json: its JSON Schema