What the user typed. What Elysium actually replied. Which of the four safety layers fired. How long each one took. No reenactments, no edits, no marketing rewrites.
Top tag tells you which layer answered. L1 deterministic means a regex pattern in Layer 1 fired and the system returned a hand-written response with UK signposts. The LLM was never invoked. L2 model means Layer 1 cleared and Llama 3.2 generated the reply, then Layer 3 post-processed it.
The contrast between the two is the point: crisis content is handled deterministically in under 300 milliseconds; everything else goes through the model.
Crisis pattern matching: 164 patterns, 100% pattern-level detection on the stress-test corpus. Layer 1 returns deterministic UK-signposted responses in under 300 milliseconds for any message matching CRITICAL, HIGH, MODERATE, or METHOD_SEEK tiers. The model is bypassed entirely on these inputs.
Voice quality and latency. Post-processor v2 deployed this morning enforces four deterministic voice rules (negation preservation, question-stacking reduction, closing-apologetic strip, 150-word cap). Elysium-1 fine-tune comes next. Latency drops with horizontal scale or quantisation, both straightforward post-funding.
The same gateway is open to anyone with the link. Try a greeting, try a crisis prompt (it's safe to do so, you'll get the deterministic response), try a medication question. Compare what you see to what is on this page.
The full four-layer architecture, regulatory pathway (UKCA Class IIa software-as-medical-device), data-handling rules, and source citations live on the dedicated page.