IndexHalo
CHANGELOG · ENGINE MODEL LOG

What changed,
in public.

No customer logos yet — so the proof is the work itself. Every material product and measurement change is logged here, the engine models below are read live from the adapter configuration, and the studies the numbers come from are linked and dated.

Engine model log

Answer-engine sweeps record the exact modelVersion each engine returns on every run. When an engine's version changes between two runs of the same prompt set, the model-version radar compares presence and sentiment across the transition and flags statistically significant shifts — correlation, dated and labelled, never causation. These are the models the adapters currently target:

Engine adapterCurrent model targetInterface
ChatGPT (API)gpt-5.6-terraProvider API, per-call pricing
Claude (API, web search)claude-sonnet-4-20250514Provider API, per-call pricing
Google Gemini (API, grounded)gemini-2.5-flashProvider API, per-call pricing
Perplexity (Sonar API)sonarProvider API, per-call pricing
Manual observation (any surface)manual-observationHuman-observed answers, pasted from any surface

Targets are configuration, pinned per deployment; the versions recorded on archived runs are observed values returned by the engines themselves. When a target changes, the transition appears here and in every workspace running sweeps against that engine.

Proof you can check

Product changelog

DateChangeWhat it means
2026-08-12Design review implemented end to endThe landing page split into focused URLs (/method.html, /sample-report.html), the signed-in workspace gained real routes (/app, /app/reports/:id, /app/sites/:id, /app/studio), the dashboard went delta-first with an activation checklist and actionable failure rows, and reports now lead with the fix, keep the score on screen while scrolling, and print self-explanatory.
2026-08-12Shared design tokens and view primitivesOne token file now feeds the marketing pages, the workspace, and the editorial pages, so a colour or type change cannot drift between copies.
2026-08-12Agency deliverable and plan lifecycleWhite-label report exports for Agency accounts, plan gating that names the limit before you hit it, and failed-payment recovery.
2026-08-1187 measured AI crawler reports publishedFifteen AI user-agents resolved against the live robots.txt of 87 well-known websites — every verdict dated and traceable to the deciding rule. Public at /ai-crawler-report/.
2026-08-11Sourced competitor comparisonsThree head-to-head pages that state where the competitor is the better choice and link every claim to the vendor's own pricing page.
2026-08-10Citation StudioBlock-based composer for citation-ready pages: fourteen measurement-backed block types, live scoring as you type, and export to semantic HTML, JSON-LD, llms.txt and robots stance.
2026-08-10Answer-engine intelligence panelPersona stress tests, defensive probes, citation poaching and parentage, cross-language drift, fair-use audit, and the model-version regression radar across four measurement phases.

Measurement-affecting changes — scoring weights, signal definitions, evidence classes — are called out in the entry itself, because a score that moved because the ruler changed says nothing about your content.

SEE THE DELIVERABLE

Judge the output, not the logo wall.

The sample report is the complete Professional deliverable with fictional data, end to end.

Read the sample report →