CATOCATO

Release Notes

Customer-facing history of CATO capabilities, reliability improvements, and important behavior changes.

How to read these notes: dates group related customer-visible changes. Feature availability can depend on plan, account configuration, data type, and the controls shown in CATO.

2026.07.23

Major updateCurrent

July 23, 2026

A redesigned, user-controlled memory system with stronger account and administrative reliability.

Capabilities

  • Separated project memory from global memory so study context and durable personal preferences have explicit scopes.
  • Added user controls to review, edit, pin, and delete memory entries and to control recall, automatic learning, and cross-project use.
  • Grounded automatic memory learning in user messages; generated findings are not promoted into memory as scientific facts.
  • Added memory consolidation to keep long-running accounts useful without treating repetition as evidence.

Reliability, security, and operations

  • Hardened administrative user, subscription, usage, support, and audit data paths.
  • Improved retention and referential-integrity behavior for account and operational records.

2026.07.21–22

Major update

July 21–22, 2026

Complete figure workbenches, broader scholarly discovery, and improved capacity for scientific analysis.

Capabilities

  • Completed figure workbenches with interactive state, artifact versions, supported editing, and export-oriented visual QA.
  • Expanded Literature Intelligence to 18 open scholarly sources: PubMed, PMC, Europe PMC, Unpaywall, CORE, Crossref, OpenAlex, DataCite, Semantic Scholar, arXiv, bioRxiv, medRxiv, ChemRxiv, SSRN, Research Square, OSF, Zenodo, and HAL.
  • Kept ClinicalTrials.gov and patent discovery as purpose-built specialized connectors.
  • Improved literature-result normalization, open-access resolution, and durable research-artifact handoff.

Reliability, security, and operations

  • Improved capacity during concurrent scientific analyses.
  • Fixed authenticated plan-checkout return behavior and improved availability monitoring.

2026.07.18–20

Major update

July 18–20, 2026

Durable background execution, Fast mode, restored workspace state, and end-to-end cancellation.

Capabilities

  • Added Fast mode for lower-latency questions, summaries, transformations, and iterative editing.
  • Added durable background sandbox jobs whose cards, progress, artifacts, failure state, and cancellation survive navigation and reload.
  • Persisted open workspace artifacts and the selected artifact version across reloads and return navigation.
  • Added unsaved-edit protection for history navigation, version changes, and workspace state transitions.
  • Restored durable literature search results across navigation and made large result restoration more responsive.

Reliability, security, and operations

  • Propagated cancellation from the conversation through queued and running sandbox execution.
  • Recovered artifacts after temporary application or storage interruptions.
  • Prevented duplicate composer submission while stream-recovery checks are active.
  • Queued concurrent sandbox work rather than reporting avoidable capacity failures.

Important notes

  • Fast mode uses the usage multiplier shown in the product. Standard remains the balanced default; Research remains the extended-depth mode.

2026.07.15–17

Major update

July 15–17, 2026

Reconnectable chat, long-context scientific recovery, durable artifacts, and stronger security boundaries.

Capabilities

  • Made active chat responses reconnect after navigation, transient disconnections, or application updates.
  • Scoped streams and composer drafts to each conversation and preserved submissions while switching conversations.
  • Added hierarchical compaction for oversized scientific turns while preserving evidence needed by response review.
  • Persisted generated datasets and restored same-turn files reliably in the Workspace.
  • Opened fetched papers and interactive scientific figures in the Workspace while preserving reasoning and reviewer evidence.
  • Added usage and plan-aware context handling plus warm persistent analysis kernels.

Reliability, security, and operations

  • Verified completion before advancing downstream workflows and recovered malformed or truncated tool calls safely.
  • Strengthened durable file availability during application updates.
  • Hardened sandbox execution, storage boundaries, vendor data boundaries, and authentication logging.
  • Updated privacy, data-processing, and subprocessor disclosures and aligned legal pages with the operating entity.

Important notes

  • A reconnecting response should be reopened in the same conversation; do not immediately submit a duplicate.

2026.07.09–14

Major update

July 9–14, 2026

Scientific artifact workbenches, persistent kernels, unified visualization, and evidence-aware literature review.

Capabilities

  • Built the scientific artifact workbench and persistent Python/R kernel workflow.
  • Unified inline and workspace visualizations and kept figure tabs synchronized with streamed output.
  • Opened retrieved papers in the Workspace and gave the reviewer access to prior conversation evidence.
  • Honored selected figure versions in follow-up work and improved figure editing and semantic discovery.
  • Added resilient molecular-structure viewing, domain validation, pathway fallbacks, and exact-paper preservation through ranking.
  • Required rendered visual QA for figures and preserved editable figure sources through long runs.
  • Unified literature search with the agent tool path while keeping requested papers and review evidence visible.

Reliability, security, and operations

  • Correlated concurrent tool provenance so artifacts can be traced to the correct run.
  • Added strict reviewer-output validation and better recovery for scientific and biomedical edge cases.
  • Applied dependency security updates across the frontend toolchain.

2026.07.01–03

Major update

July 1–3, 2026

The versioned Artifact Workspace and manuscript/reviewer foundation.

Capabilities

  • Introduced versioned files with provenance, a persistent viewer panel, reviewer workflows, and annotations.
  • Added manuscript drafting with Markdown/LaTeX preview, session forking, and DOCX/PDF export.
  • Added PDF text annotations, HTML element annotations, transcript annotations, and visible pending-annotation state.
  • Added CodeMirror editing, custom reviewer criteria, and registration for large artifacts.
  • Opened figures and manuscripts as workspace tabs and stored artifact bytes durably.
  • Consolidated product-facing chat choices into Standard and Research before the later addition of Fast mode.

Reliability, security, and operations

  • Preserved message-stream order and stopped runs cleanly before generation when requested.
  • Fixed sandbox authorization and connected generated code runs to readable code blocks.

2026.06.30

Feature update

June 30, 2026

A new visual identity and faster project navigation.

Capabilities

  • Redesigned the frontend with the current neutral and sky-blue visual system and updated typography.
  • Enabled the command palette throughout project pages and narrowed sidebars to make more room for research work.
  • Refined Chat, Literature, resume banners, scroll progress, and navigation icons for a consistent workspace.

2026.04.15–21

Major update

April 15–21, 2026

Open full text, expanded scientific formats, reliable streaming, and enforceable billing boundaries.

Capabilities

  • Added open-access full-text retrieval across literature connectors with abstract fallback when the complete article is unavailable.
  • Expanded scientific format handling, including SPSS, BIOM, 10x Matrix Market, Loom, and compressed archive members.
  • Improved the figure editor, scientific package environment, and analysis capacity.
  • Added pay-as-you-go upcoming charges, transparent Helper usage, and billing meters that reconcile AI activity.
  • Added preprint exclusion controls and corrected literature search metrics.

Reliability, security, and operations

  • Improved stream reconnection and made stalled-response feedback actionable.
  • Enforced upload size, mid-stream budgets, concurrent stream caps, and rate limits consistently.
  • Preserved prompt drafts and showed actionable banners when an account hits a limit.
  • Redesigned administration and hardened complete user-data deletion paths.

Important notes

  • Historical fixed execution-time wording has been removed from Help. CATO now governs execution according to the workload and current capacity controls.

2026.03

Feature update

March 7–24, 2026

Peer-review workflows, no-code figures, broader research data, and stronger stream handling.

Capabilities

  • Split peer review into Search & Plan, Execute, Verify, and Revise stages.
  • Introduced the no-code figure editor and improved large 3D structure delivery.
  • Expanded ingestion to more than 40 research-oriented formats and added analysis libraries.
  • Added citation export and improved systematic-review retry behavior.
  • Improved analysis access to project datasets and repaired recurring file-resolution failures.

Reliability, security, and operations

  • Decoupled response delivery from persistence, fixed stream races, and improved completion rendering.
  • Added retry and backoff for transient scholarly-source failures.
  • Aligned usage tracking and feature access with then-current billing controls.

2026.02

Major update

February 1–26, 2026

The account, isolated execution, billing, and Literature Intelligence foundation.

Capabilities

  • Added isolated code execution, R support, archive uploads, biomedical tools, persistent chat, and report output.
  • Added subscription billing, pay-as-you-go metering, account settings, password reset, notifications, and administrative analytics.
  • Launched Literature Intelligence with multi-source retrieval, evidence workflows, and result persistence.
  • Added project tours, docs/help, activity history, document preview, global notifications, and account deletion.
  • Introduced the warm visual design system that preceded the current July identity.

Reliability, security, and operations

  • Improved durable account and project storage for concurrent use.
  • Hardened concurrent-user isolation, archive extraction, file paths, authentication, browser security policy, and error reporting.
  • Improved multi-user response handling and added conversation, usage, rate, and support safeguards.
  • Removed datasets and tools whose licenses were not compatible with customer use.

Important notes

  • Earlier plan names, chat-mode labels, trials, and account-access descriptions in historical drafts are not current. See Settings → Billing and the FAQ for present behavior.

2026.01

Feature update

January 26–30, 2026

Initial CATO research-analysis platform.

Capabilities

  • Created the first data-analysis, agent, project, dataset-presentation, authentication, and conversation-resume flows.
  • Added early Python/R analysis support, user isolation, logging, data access, and reliable saved progress.

Reliability, security, and operations

  • Established project-scoped storage and authentication boundaries that later security updates expanded.

Need help after an update?

Check Troubleshooting for migration, reconnection, workspace, literature, and billing guidance. If the issue persists, send support the relevant IDs, timestamps, and redacted error.

Open Troubleshooting