product log · NO QUIET CORPSES
Changelog
What changed. What got stronger. What keeps watching.
Zombify tracks AI model lifecycle risk. This page tracks Zombify itself.
Reliability upgrades, lifecycle improvements, dashboard changes and product hardening live here.
14 June 2026 · v1.3.0
Provider newsroom and sharper signal review
Newsroom upgrade A newsroom update for tracking provider announcements before they become model incidents. Zombify now gives teams a clearer public feed of model risk context, availability warnings and lifecycle signals.
Newsroom
- Added a public Newsroom for provider announcements, lifecycle signals, access restrictions and API changes.
- Added recent Newsroom signals to the homepage so important model-risk context is easier to find.
- Added clearer source links, affected-model tags and Zombify takeaways for published announcements.
Signal review
- Improved how Zombify separates provider news, weak availability signals and confirmed lifecycle evidence.
- Added review controls so public announcements can be checked before they appear on the site.
- Improved the internal workflow for catching relevant provider changes without turning the Newsroom into a generic AI news feed.
27 May 2026 · v1.2.4
Cleaner lifecycle confidence and safer registry signals
Trust upgrade A trust and clarity update for developers using Zombify to check production AI model risk. This release improves how lifecycle evidence, source confidence and provider signals are surfaced across the checker and admin review flow.
Model confidence
- Improved source-confidence handling so model checks show cleaner, more consistent trust signals.
- Cleaned up older registry records where lifecycle notes were useful but confidence data was incomplete.
- Improved handling for unknown or missing confidence values so they do not create confusing results.
Provider signals
- Tightened how Zombify separates official provider lifecycle notices from weaker discovery signals.
- Improved safeguards so product-level retirement notes are not treated the same as confirmed API shutdowns.
- Kept low-confidence provider availability changes in review instead of turning them into automatic status changes.
Customer clarity
- Improved the registry health review so risky records are easier to understand before they affect customer-facing checks.
- Improved lifecycle wording for deprecated, retired and replacement-model states.
- Kept Claude Sonnet 4 and Claude Opus 4 replacement guidance clear for teams planning production migrations.
26 May 2026 · v1.2.3
Stronger model lifecycle review
Reliability upgrade A reliability upgrade to the model lifecycle registry behind Zombify. This release makes provider changes easier to review, improves lifecycle accuracy and gives the product stronger safeguards before model status changes reach customers.
Lifecycle review
- Improved the internal review flow for provider model changes before they appear in public checks.
- Added clearer review states for model records that need attention, verification or cleanup.
- Improved source-status visibility so provider updates are easier to trust before they affect monitored stacks.
Lifecycle accuracy
- Improved how Zombify moves models through active, deprecated and retired states when reliable provider dates are available.
- Improved matching for short model names and provider-versioned model IDs so teams see the same lifecycle risk either way.
- Added stronger checks for missing lifecycle dates, replacement guidance and source evidence.
Anthropic accuracy
- Improved Claude Sonnet 4 and Claude Opus 4 lifecycle coverage, including shutdown timing and recommended replacements.
- Improved checks for Claude model aliases so common names resolve to the right lifecycle record.
- Improved replacement handling so missing provider guidance falls back gracefully instead of confusing the checker.
13 May 2026 · v1.2.2
Smarter lifecycle intelligence and migration guidance
Lifecycle upgrade A lifecycle intelligence update that improves how Zombify tracks provider announcements, model risk and safer migration paths across OpenAI and Anthropic models.
Lifecycle intelligence
- Improved lifecycle tracking for OpenAI and Anthropic model records.
- Expanded coverage across active, deprecated, retired and zombie model states.
- Improved date handling for provider-announced deprecations and shutdowns.
- Strengthened confidence checks before lifecycle changes are surfaced to users.
Migration guidance
- Improved replacement guidance for deprecated, retired, zombie and at-risk models.
- Improved recommendations when provider announcements do not include a clear migration path.
- Updated OpenAI migration guidance to favour current GPT-5.5 family models where suitable.
- Updated Anthropic migration guidance to favour current Claude Sonnet, Opus and Haiku options where suitable.
Model checker
- Model checks now provide clearer next-step actions when a model is deprecated, retired or otherwise risky.
- Improved replacement display so users can understand the suggested migration path more quickly.
- Added stronger safeguards so replacement guidance avoids models that are themselves deprecated or retired.
- Improved response consistency across OpenAI and Anthropic model checks.
7 May 2026 · v1.2.1
Clearer dashboard status and watchlist visibility
Dashboard upgrade A dashboard upgrade that gives users a clearer view of their watched model stack, including legacy models that may still be running in production while teams plan safe migrations.
Dashboard
- Added an inline stack status panel so users can review model health from the dashboard.
- Improved the dashboard action for sharing watched model status with others.
- Added copy-link support for shareable status pages.
- Kept public status pages available for clients, collaborators and stakeholders.
Watchlists
- Expanded watchlist support for models across active, deprecated, zombie and retired states.
- Added clearer lifecycle labels to watched models so risk is easier to spot.
- Improved model selector labels so users can better understand model state before adding it.
- Improved support for real-world stacks where older models may stay in place during migration planning.
Status visibility
- Improved watched-stack risk summaries inside the dashboard.
- Made lifecycle status easier to read across active, deprecated, zombie and retired models.
- Improved shareable status pages for external updates and team visibility.
4 May 2026 · v1.2.0
Lifecycle, authentication and delivery hardening
Reliability upgrade A major reliability update across Zombify’s model monitoring, dashboard access and email delivery systems. This release strengthens the parts of the product that matter most: trusted lifecycle data, reliable alerts and secure account access.
Access
- Added secure magic-link dashboard authentication for paid users.
- Tied dashboard access to control of the paid checkout email inbox.
- Improved session handling across dashboard and watchlist actions.
- Added stronger server-side checks for account access and watchlist activity.
Email delivery
- Improved transactional email delivery using a verified domain sender.
- Moved login emails to a dedicated Zombify sender address.
- Updated authentication email copy so dashboard login feels branded and clear.
- Improved sender authentication so login links arrive more reliably.
Lifecycle accuracy
- Strengthened lifecycle verification for monitored AI models.
- Improved handling of provider lifecycle announcements.
- Improved lifecycle confidence across public and provider-backed model signals.
- Expanded lifecycle visibility across active, at-risk, deprecated, zombie and retired models.
Recommendations
- Improved replacement recommendation safeguards.
- Replacement suggestions now favour models that are currently suitable for migration.
- Refined migration guidance for legacy OpenAI and Anthropic models.
- Added stronger checks so replacement guidance stays aligned with live model status.
Watchlists
- Tightened watchlist rules for monitored model stacks.
- Improved model validation before a model can be added to a watchlist.
- Improved support for tracking production model stacks over time.
- Kept the public model checker broad so users can still search both current and legacy models.
Status pages
- Improved public status page summaries so watched stacks report lifecycle risk more clearly.
- Improved public status page handling for newly watched models.
- Improved attention counts so active models are not included in risky model totals.
- Improved status-card handling for zombie, deprecated and retired models.
Transparency
- Added a public changelog for clearer product updates.
- Improved release visibility for reliability, lifecycle and product changes.
- Added this page so Zombify’s own evolution is easier to follow.
28 April 2026 · v1.1.0
Stronger model lifecycle records
Registry upgrade Introduced a stronger lifecycle record system so Zombify can track, classify and update model status as providers change their model line-ups.
Lifecycle records
- Added internal tools for reviewing model lifecycle records.
- Added provider, status and model search filters for lifecycle management.
- Improved lifecycle status handling across active, deprecated, zombie and retired models.
- Improved source notes and proof links for model lifecycle records.
Model discovery
- Improved provider-model handling across OpenAI, Anthropic, Google and OpenRouter.
- Added clearer separation between discovery signals and user-facing lifecycle status.
- Improved official-source notes for model lifecycle data.
- Strengthened the foundation for ongoing lifecycle monitoring.
24 April 2026 · v1.0.0
Zombify launch build
Initial launch The first public version of Zombify: a model lifecycle checker, live Graveyard, paid watchlist and shareable status page for developers who do not want to learn about model deprecations from their users.
Core product
- Launched the public model checker.
- Launched the model Graveyard.
- Added paid watchlists for up to 10 models.
- Added shareable status pages for monitored model stacks.
- Added Stripe checkout for lifetime access.
Brand
- Launched the Zombify visual system, homepage, dashboard and mobile navigation.
- Added the undead model monitoring positioning across the homepage and product UI.
- Introduced the first version of Zombify’s lifecycle monitoring experience.