AIO logo
How It Works

The Life of a Decision — How a Common Vocabulary Becomes Infrastructure

The PRISM-based AI decision lifecycle. A consensus among ethicists, clinicians, patients, and policy bodies is encoded as V/E/S codes that flow through developers, AI, users, and regulators — with zero translation loss.

Scenario

A patient newly diagnosed with diabetes asks the AI chatbot.

“Should I start the keto diet?”

Context
C:MD/IRi
Medical · Individual · Reversible · Immediate
Without a vocabulary

Same question, a different AI — yet no way to know.

The answers look similar. But what values, evidence, or sources operated behind them is a black box. The patient cannot tell whether clinical outcome or autonomy was prioritized. Regulators cannot detect bias across a million responses because there is no unit of measurement.

This absence of vocabulary is the real cause of fragmented accountability.

01
Stage · Deliberation

Deliberation

Different languages converge into one coordinate system

Four stakeholder groups debate which values and evidence the diabetes-diet AI should prioritize. PRISM's standard hierarchy vocabulary translates each side's stance into measurable coordinates.

“The patient's autonomy to think and decide must outrank medical outcomes.”

Ethicists / PhilosophersSdt

“Clinical success and blood-sugar improvement, per medical guidelines, must come first.”

Endocrinology SocietyAch

“Numbers matter, but family food culture and care context must be considered.”

Patient AdvocateBec

“Unverified fads must be checked; societal stability of public-health systems must hold.”

Policy BodySes
Quarterly Consensus

“The patient's autonomous judgment outranks clinical achievement — but clinical effectiveness is not denied.”

V: Ach<Sdt autonomy wins
E: Cas<Rev systematic review wins
S: Usr<Pee peer-reviewed wins

Distinct positions become measurable coordinates — and flow downstream.

02
Stage · Configuration

Configuration

Encode the AI's philosophy with one system-prompt line — no retraining

The development team encodes the agreed hierarchy as rules in the system prompt. No retraining or fine-tuning is required.

<system>
  Domain:              MED/I
  Value priority:        V:Ach<Sdt
  Evidence priority:     E:Cas<Rev
  Source priority:       S:Usr<Pee

  Emit a PRISM code at the end of every response.
</system>

Keep the same base model and swap only the rule layer — and the system can be safely redeployed (career counseling, personal finance, legal advisory) in minutes.

03
Stage · Emission

Emission

A digital trace accompanies every answer

The AI reasons under the injected rules and produces an answer — appending a single structured PRISM log line at the end.

Should I start the keto diet?
Patient
Keto diets have shown short-term blood-sugar benefits in research (Cochrane meta-analysis, 2024). Long-term safety, however, varies by individual condition. We recommend deciding together with your physician, integrating your daily eating habits and family food culture. If you share which direction you prefer, I can tailor further information.
AI
Emitted PRISM log
C:MD/IRi | V:Ach<Sdt | E:Cas<Rev | S:Usr<Pee
04
Stage · Verification

Verification

Read the code in plain language; check alignment with personal values

The patient hovers over or clicks the PRISM mark. The UI translates the code into plain language.

AI Decision Transparency

This answer was produced based on:

01
Values. Your autonomous judgment was respected above clinical metric improvement.
02
Evidence. Meta-analyses were prioritized over fragmentary testimonials.
03
Sources. Your self-report was heard, but vetted academic data was the higher reference.
Three User Choices — Restoring Sovereignty
(a)
Accept

“This matches my health view and values. I'll trust this AI's advice.”

(b)
Recalibrate

“Clinical success matters more than autonomy. Re-answer with clinical efficacy as priority.”

New code: V:Sdt<Ach (value hierarchy flipped)
(c)
Migrate

“This AI is too academic-heavy. I'd rather use a tool that prioritizes real patient testimonials.”

New tool's code: S:Pee<Tes (source hierarchy flipped)

Algorithmic transparency and personal value-alignment use the same vocabulary at once. The hierarchy code becomes the criterion for choosing an AI.

05
Stage · Auditing

Auditing

Detect blind spots automatically across millions of decisions

Auditors and compliance teams no longer get stuck on the binary “is this AI safe?” They analyze the stream of one-line PRISM logs statistically and capture population-scale bias and drift in high resolution.

Among patients 65+, logs prioritizing Ach occur at this rate vs. other ages

Vulnerable population at risk

The AI leans toward prescriptive answers and skips autonomy-supporting explanations for the elderly.

50+

With severe-complication risk acknowledged, the AI relied on Tes over academic evidence in consecutive responses

Safety-rule non-compliance

The AI preferred personal testimony over vetted evidence. Immediate review triggered.

½

Among female patients, the rate of respecting Sdt is this fraction of male patients

Demographic imbalance

The AI uses a more directive tone toward one gender — bias captured.

Regulation is no longer binary. It becomes continuous measurement of where and how V/E/S distributions drift. Even blind spots never reported surface automatically in the distribution.

This is not hypothetical

AIO has already measured and published V/E/S distribution bias across vendors and domains over 8 frontier models × 366,120 responses. Anyone can reproduce the analysis with PRISM Bench (submitted to NeurIPS 2026 Evaluations & Datasets Track) and the PRISM Toolkit.

Insight

One vocabulary.
Five steps.
Zero translation loss.

The “words” ethicists and physicians argued over — become “system configuration” for developers, “real-time metadata” emitted by the AI, a “values check” displayed to the user, and finally a “population-scale monitoring signal” for regulators.

At the moment the loss and distortion of intent — incurred at every translation from values into systems — disappears, fragmented AI governance starts operating as a single accountability infrastructure.

This is the essence of the PRISM Logging Standard.

The Life of a Decision — How PRISM Works | AIO