No fabrication
Every quantified claim on this site traces to the CV or a project record. Where evidence does not exist, the claim is left out — the same rule binds the assistant.
Governance
How this site controls its claims
The Ask my CV assistant is a live sample of governed AI: grounded answers, deterministic controls, cited sources. This page states how it works, where it stops, and how crawlers may use the site.
The assistant answers strictly from the CV and case-study records published on this site. It is retrieval-grounded: it can only cite what the record contains, and it refuses what the record does not support.
Ask my CV
How an answer is produced
-
01 — Retrieve
The question is scored against the record corpus. If nothing relevant matches, the assistant refuses immediately — no model is called.
-
02 — Answer from the record only
The model receives the retrieved records and nothing else. It is instructed to answer strictly from them.
-
03 — Check the answer
A deterministic classifier inspects the output. An empty or refusal-shaped answer is replaced with the standard refusal and is never presented as grounded.
-
04 — Cite
Each grounded answer carries citation chips linking the top-matched records on this site, so every claim can be checked at its source.
Cost and abuse controls: each visitor has a request rate limit, the assistant has a daily budget it refuses beyond rather than exceeds, and repeat questions are served from a cache keyed on a content hash of the question. Crawlers are excluded from the assistant endpoint entirely.
Claim controls
The rules the whole site runs under
CV parity gate
An automated check compares the site data records against the published CV PDF on every build, so the two surfaces cannot drift apart silently.
Regression gates
Editorial, narrative and assistant test batteries run before every deployment, including grounding questions the assistant must answer and out-of-scope questions it must refuse.
Single source of truth
The assistant reads the same typed data records the pages render. Every fact it can cite is also published as ordinary crawlable HTML on this site.
Limitations
Where the assistant stops
- The assistant paraphrases. Where its wording and a cited record differ, the record is correct.
- Retrieval is keyword-based and prompt-sensitive: a rephrased question may surface records a first attempt missed.
- It refuses anything outside the published record by design — including questions a conversation with me could answer.
- It answers one question at a time from the record; it does not hold a conversation history or learn from visitors.
- Answers are generated by a hosted language model and wording varies between runs; only the cited records are stable.
This page records intent and known limits; it does not assert formal compliance with any standard. Anything the record cannot answer, I can — email me directly.
Crawler policy
How machines may read this site
Search-engine crawlers and AI search or user-fetch agents (services that fetch a page to answer a person and cite it) are welcome across the public site. AI training crawlers are currently permitted. No crawler may call the assistant endpoint: automated traffic must never consume the assistant’s budget.
The machine-readable version of this policy, listing each agent explicitly, is /robots.txt.