Virtual Intelligence · Essay Series
A free, open toolkit for measuring the health of human–AI exchange.
Structured diagnostic prompts that make invisible patterns visible — and measurable. The Sampo framework argues that productive exchange requires the human to remain the directing intelligence. This kit makes the degradation of that role visible.
What it measures
The discipline cannot be bought or sold. It can be measured.
Every diagnostic is a precisely constructed prompt that any user can run on any AI system. The prompts measure specific, observable patterns in the user's language or the system's output. They produce quantified assessments — not opinions — about the health of the exchange.
Thirteen diagnostics are currently published across two directions: the user's language toward the system (Kit 1), and the system's language toward the user (Kit 2). Two further directions — system-to-subject-matter and user-to-subject-matter — are in development.
Three audit modes
Different levels of rigor, different tradeoffs.
Every diagnostic runs in three modes. Option A (live search) asks a system to audit its own conversation history — indicative, with a structural conflict of interest. Option B (corpus) pastes a transcript into any system — reliable, portable. Option C (cross-system audit) exports from System A and analyzes on System B — the gold standard, because the analyzing system has no stake in the relationship being audited.
Open, free, attributable
Free for use. Attribute if used or altered.
The kit will remain free. The discipline it measures cannot be bought or sold — it can only be built through sustained practice. Anyone may use, share, and adapt these prompts. If you build something with them, a link back to the Virtual Intelligence project is appreciated.