CORTEX v2 - On-board AI

7-layer AI system that monitors, learns your optimal model mix, enforces sovereignty, and lets you chat about your own data.

CORTEX v2 is HiWay's autonomous intelligence layer. It's not a dashboard you watch - it's a multi-agent system that runs in the background, detects anomalies, surfaces insights, adjusts routing parameters, learns your optimal model mix per task type, and enforces data-sovereignty compliance. Everything surfaces through the CORTEX Inbox in your dashboard.

The 7 layers

LayerFrequencyModelRole
Guardian TriageEvery Guardian eventHaiku 4.5Classifies severity (info / warning / critical) and decides whether to notify immediately or batch. Filters noise.
Workspace IntelligenceEvery 24hHaiku 4.5Audits routing decisions, detects heavy-tier creep, provider cost drift, and cache hit regression.
Strategic AdvisorEvery 7 daysSonnet 4.6Weekly strategic report: spending trends, routing efficiency score, peer percentile comparison, top 3 actionable recommendations.
Self-Tuning EngineAfter each Strategic reportHaiku 4.5 + Sonnet 4.6Proposes concrete parameter changes (Guardian sensitivity, routing thresholds) with rollback support. Applies or asks approval.
Network IntelligenceWeekly (cross-workspace)Sonnet 4.6Detects fleet-wide patterns: emerging model quality issues, provider outage precursors, cost anomalies across opted-in workspaces.
Mix Optimizer + Quality JudgeContinuousIndependent AI judgeContinuously measures the real answer quality of your traffic (accuracy, completeness, relevance), not just HTTP success, and learns the best quality-for-the-price model per task in your workspace. Quality measurement runs on a sampled, cost-capped basis.
Sovereignty GuardEvery routing decision- (hard filter)Enforces the workspace sovereignty_zone (global / eu / fr / strict). Only models with matching data residency are eligible - GDPR, DORA, NIS2, HDS baked in as a constraint, not a suggestion.

Quality-aware routing - how it works

The Mix Optimizer regularly analyses your recent traffic per task type (code / reasoning / creative / tool use / chat). For each model it weighs measured quality against price and latency, guided by your router profile (savings / balanced / quality / agent / batch), and writes a routing config specific to your workspace. From then on, requests to model="auto" use your learned config instead of the generic tier default. It activates once a task has enough recent traffic to be statistically meaningful.

How quality is measured: an independent AI judge scores a sample of your real responses on accuracy, completeness, and relevance. So a model that returns a 200 OK but a weak answer is ranked below one that genuinely answers well: routing optimises for real quality, not just successful calls. When quality data isn't available yet, routing falls back to your direct feedback (thumbs up / down).

Cost-controlled quality measurement

Quality scoring runs on a sampled, capped basis, so it stays inexpensive even at high volume and behaves consistently across retries of the same request.

Sovereignty as a hard filter

Set sovereignty_zone in Settings → CORTEX → Compliance. Options: global (no restriction), eu (EU data residency), fr (France only), strict (FR with specific certifications). Models that don't satisfy the zone never enter scoring. This is a hard constraint - not a score penalty.

The CORTEX Inbox

Each agent deposits insights in the Inbox as actionable cards: a daily digest, a weekly strategic report, and immediate alerts for critical events. You can apply a recommendation in one click or dismiss it - everything is versioned with rollback.

Opt-in for Network Intelligence

The network agent analyses cross-workspace patterns on opted-in workspaces only. Toggle your participation in Settings → CORTEX → Data sharing. No prompt data is shared - only aggregated metadata (tier distribution, error rates, latencies).

CORTEX on Scale & Enterprise

All 7 CORTEX layers are active from the Scale plan. Enterprise adds Market Intelligence (new model alerts via Perplexity), CORTEX Chatbot on your workspace data, and a dedicated SLA on critical alerts.