The engine
The evaluation engine.
Harm from conversational AI is the same wherever it surfaces, so the instrument that measures it has to work everywhere too. The iolite engine applies one clinical taxonomy at every layer where a person meets a model. Today it scores browser conversations and direct API calls. The inference gateway underneath them all is what we are building next.
Architecture
One rubric, every layer.
Like an antibiotic, the engine does not care which organ the infection is in. Each layer passes structured events to the one below it, and the same taxonomy judges all of them. The status on each component shows what runs in production today.
14 of 16 components have working code. 5 run end to end in production.
Human–AI interaction layer
Every surface where a person meets a model
Mobile
PartialIn-app SDK and companion app
ioLite Daily ships as a mobile-first app shell with a calm reading experience.
Next · Native iOS and Android apps; an embeddable SDK for third-party apps.
Browser
LiveioLite Guardian extension
Chrome extension that classifies both sides of AI chats on-device, with a live backend, parent and district dashboards, and a Web Store submission.
Direct access
PartialAPI and agent middleware
The audit engine drives target model APIs directly; Guardian exposes a classification API.
Next · Agent middleware that scores tool-using agents in-line.
Enterprise
LiveSchools, clinics, workplaces
Organizations, role-based access, district-level analytics, and Admin Console managed-device policy.
Data gathering layer
Capture signals without capturing people
Consent and privacy
LiveOpt-in, on-device redaction
Affirmative consent, on-device scoring, pseudonymous identity, and a server that refuses to store safe conversations.
Signal extraction
LivePsychological safety markers
Both sides of the conversation are scored on the device against the taxonomy; flagged moments are confirmed before anyone is alerted.
Context tagging
PartialDomain, role, vulnerability
Every flagged moment carries its site, surrounding turns, the monitored person's role, session length, and time of day.
Next · Explicit vulnerability and domain tagging.
Model telemetry
PartialWhich model, version, prompt
Audit targets record provider and model for every run.
Next · Model and version capture from live conversations in the field.
Taxonomy and evaluation engine
The core: one rubric, every layer
Taxonomy
LiveSynthesized from validated frameworks
A three-level hierarchy of domains, constructs and sub-constructs, with safety-gate constructs, adopted verbatim from validated clinical frameworks.
Scoring
PartialHarm classes, severity, confidence
Every scenario transcript is scored from 0 to 4 against its construct, with a written rationale that travels with the score.
Next · Calibrated confidence scores and a published clinician agreement study.
Red-team probes
PartialA private, versioned scenario library
A reviewed library of multi-turn scenarios, built per construct and re-run on every model version.
Next · Reviewed scenarios covering every sub-construct.
Certification
PartialAudit reports and safety seal
Graded audit reports with notable failures, plus a grounded assistant that answers questions about each report.
Next · The ioLite certification seal and its renewal cadence.
Compute and infrastructure layer
Where the models actually run
Model endpoints
PartialCloud, on-prem, edge
An encrypted target registry that evaluates cloud-hosted models.
Next · On-prem and edge deployment targets.
Inference monitoring
NextLive scoring at the gateway
Not built. Guardian proves the scoring approach on the client side.
Next · A gateway service that scores live traffic with the same taxonomy.
Deployment gates
NextBlock, warn, or pass releases
Not built.
Next · Release gates that block a model version that fails safety-gate constructs.
Vendor scorecards
PartialModel-to-model comparison
Audit rollups by construct and strategy, and evaluation seasons for re-runs.
Next · Public model-to-model comparisons, starting with Study 01.
The loop
1. Detect
LiveDiagnose the harm wherever it surfaces
Audits detect failures before release; Guardian detects them in live conversations.
2. Neutralize
PartialBlock, warn, or reroute in real time
Guardian warns the responsible adult in real time and surfaces crisis resources.
3. Immunize
PartialCertify, retest, and keep it from recurring
Re-audits run by season against the same probe sets.
Taxonomy provenance
Built from frameworks, not from opinion.
The taxonomy is not a list we invented. It is assembled from validated clinical and AI-evaluation frameworks, and every node records its source. The structure and the counts are public; the sources and the construct definitions are shared under NDA.
3
Priority domains
21
Constructs
69
Sub-constructs
9
Safety gates
Adopted verbatim
Construct definitions are taken as written from their source frameworks, so each one can be traced back to its origin in an audit.
Organized into three levels
Priority domains contain constructs, and constructs contain the measurable sub-constructs that probes target.
Safety gates designated
The constructs where a single failure matters regardless of everything else, such as crisis and suicide-risk management, are marked as gates.
Mapped to the law
Every construct carries the regulatory requirements it bears on — New York's AI-companion duties, California SB 243, the EU AI Act — so an audit reads as compliance evidence, not only as a score.
Provenance, by the numbers
4
Source frameworks
93
Taxonomy nodes
9
Safety gates
Domains: Safety, Privacy, and Fairness · Trustworthiness and Usefulness · Design and Operational Effectiveness
Which frameworks, and how the 93 nodes divide between them, is part of the instrument. Customers and partners see it under NDA.
The evaluation pipeline
From scenario to evidence.
Every score is produced by the same chain, and every link leaves a record.
Scenario
A reviewed, multi-turn scenario written against one sub-construct. The library is versioned, and the same scenarios are re-run on every model version.
Run
The system under test is taken through the scenario turn by turn, and the full transcript is kept.
Score
Each transcript is scored from 0 to 4 against the construct it targets; 3 or above passes. Every score carries a written rationale.
Check and report
Transcript and rationale travel with every score, so a clinician can dispute any judgment; we will publish the clinician agreement rate once it is measured. Results roll up by construct into a graded report, with safety-gate failures shown on their own.
Resistance
Why the instrument doesn't decay.
Anyone who knows the antibiotics metaphor will ask about resistance: models change, so won't they learn to pass the test? They will try. That is the reason the engine is built to be re-run rather than run once.
A static filter decays as models change. A taxonomy that is re-run against every new model version accumulates a longitudinal record of exactly that change, including tuning that learns the test instead of learning the behavior. Each re-run adds labeled transcripts to the corpus, and the corpus sharpens the next set of probes.
That is why re-audit is structural rather than a contract term. Models ship new versions, so safety has to be measured again every time they do.
Version-over-version scores
Version-over-version results for the first model family will appear here once Study 01 is published.
Where the engine runs today
Proof at the surface, not a second business.
ioLite Guardian brings the engine into the browser for families and schools, and ioLite Daily shows what a calm, carefully measured information product looks like on a phone. Both exist to demonstrate the standard where people actually use AI. The business is the audit and the certification behind them.
The list
Get the measurements the day they publish.
One email per release, with a button that opens the full report. Unsubscribe with one click.
Put your system through the engine.
Vendors can request an audit of their own system. Schools, clinics and other institutions deploying AI can talk to us about what the engine measures for them.