The Re-verification List
Volatile facts carry an as-of date of August 2026. This list is reviewed quarterly, and every item names what to check and where the claim is used. Staleness is the main threat to a reference guide in this category.
Added for the memory architectures section, September 2026
- Item
- Context windows, long-context price tiers and cache rates for every model family on the long-context page
- Why volatile
- Prices change quarterly; one Flash line changes price on 2027-01-01; one provider re-routed its Pro model on 2026-09-14
- Where used
- /memory/long-context-is-not-memory
- Re-check
- December 2026, against first-party pricing pages
- Item
- Status of the four managed memory services (one still in preview as of 2026-06-02)
- Why volatile
- Preview to GA transitions
- Where used
- /memory/six-architectures
- Re-check
- December 2026
- Item
- Every vendor benchmark row: LoCoMo, LongMemEval and BEAM scores reported by memory vendors
- Why volatile
- Vendors re-publish monthly under new judges
- Where used
- /memory/what-the-benchmarks-measure, /memory/the-ten-million-token-question
- Re-check
- December 2026
- Item
- Whether an independent evaluation of any commercial memory system on BEAM has appeared
- Why volatile
- Would change the section's open question
- Where used
- /memory/the-ten-million-token-question
- Re-check
- December 2026
- Item
- The MemPalace benchmark file and history page
- Why volatile
- The project has retracted claims before
- Where used
- /memory/what-we-have-measured
- Re-check
- December 2026
Completed for the August 2026 release
- Item
- Joint agentic-AI cyber guidance date
- Result
- Verified as May 1, 2026 on the CISA release bulletin and Australian Cyber Security Centre publication page
- Item
- FINRA AI recordkeeping language
- Result
- RN 24-09 preserves existing technology-neutral obligations and creates no new interpretation. RN 25-07, published April 14, 2025, asks for comment on AI-generated communications and recordkeeping; it is not a final interpretation
| OpenAI self-serve fine-tuning wind-down | Announced 7 May 2026. New organisations blocked 7 May 2026; organisations without fine-tuned inference in 60 days blocked 2 July 2026; all remaining customers blocked 6 January 2027. Used on /ladder/adapters-and-fine-tuning. Re-check before the January 2027 date passes | https://developers.openai.com/api/docs/deprecations |
Added 15 October 2026: industry estates and the capabilities frame
- Item
- AWS Bedrock AgentCore component list (Runtime, Gateway, Memory, Identity, Policy, Evaluations, Observability) and GA dates
- Why volatile
- Vendors rename and add components
- Where used
- /architecture/system-view, vocabulary audit
- Re-check
- Quarterly, AWS what's-new
- Item
- Microsoft Agent 365 as "the control plane for agents" (GA 1 May 2026) and Entra Agent ID sponsor rules (updated 3 September 2026)
- Why volatile
- Product wording and sponsor hand-over behaviour change
- Where used
- /architecture/system-view, /architecture/agent-lifecycle
- Re-check
- Quarterly, Microsoft Learn
- Item
- Google Agent Engine components (runtime, sessions, memory bank, evaluation, observability, identity)
- Why volatile
- Preview to GA moves
- Where used
- /architecture/system-view
- Re-check
- Quarterly
- Item
- AEMC final rule on payment difficulty and disconnection, 10 September 2026, effective 30 March 2027; the payment-plan standards rule still open
- Why volatile
- A second rule is pending; effective dates can move
- Where used
- /use-cases/billing-exceptions, /use-cases/utilities
- Re-check
- Before each use of the hardship design; AEMC rule page
- Item
- SAP S/4HANA Utilities release confidence on implausible reads (in product); SAP Joule billing-exception agents planned Q2 and Q3 2026, not confirmed shipped on 15 October 2026
- Why volatile
- GA announcements expected
- Where used
- /use-cases/billing-exceptions, /layers/r07-agent-platform
- Re-check
- Monthly until shipped; ASUG and SAP release notes
- Item
- IBM AI Lighthouse Council for SAP utilities (11 September 2026): co-build, no results
- Why volatile
- Results may be published
- Where used
- /use-cases/billing-exceptions
- Re-check
- Quarterly
- Item
- Itron IEE Cloud AI (announced 16 September 2026); January 2027 availability from an aggregator, not Itron
- Why volatile
- GA date unconfirmed
- Where used
- /use-cases/billing-exceptions
- Re-check
- Before citing availability
- Item
- IBM Maximo 9.2 MCP server for work-order actions (12 August 2026) and Maximo Condition Insight (5 December 2025), GA wording not stated
- Why volatile
- GA status unclear
- Where used
- /use-cases/vegetation-inspection, /use-cases/energy-asset-investigation, /layers/r07-agent-platform
- Re-check
- Quarterly
- Item
- LiveEO Treeline Agent and MCP connector, early access (2 July 2026)
- Why volatile
- Early access to GA
- Where used
- /use-cases/vegetation-inspection
- Re-check
- Quarterly
- Item
- Kraken Bill Editor in development; Kraken and Sierra agents live at one unnamed utility (June 2026)
- Why volatile
- Named results may appear
- Where used
- /use-cases/utilities
- Re-check
- Quarterly
- Item
- Health NZ Heidi scribe licences (1,000 plus 100; later "about 1,250 staff"); Metro South rollout announced 31 August 2026
- Why volatile
- Counts conflict across sources
- Where used
- /use-cases/healthcare
- Re-check
- Before citing a count
- Item
- Heidi II agents for chart prep, referrals, follow-ups and recalls (launched 28 September 2026), primary care first, no public hospital site
- Why volatile
- Rollout status changes
- Where used
- /use-cases/healthcare, /use-cases/referral-coordination
- Re-check
- Quarterly
- Item
- Epic agents (Art, Emmie, Penny, Agent Factory), Oracle Health Clinical AI Agent and Microsoft Dragon Copilot: not confirmed available in Australia or New Zealand on 15 October 2026
- Why volatile
- Regional availability changes
- Where used
- /use-cases/healthcare and the four healthcare worked examples
- Re-check
- Quarterly
- Item
- Logan ENT ReferralAI (validation stage; 53.8 percent agreement in a 2023 study) and Oxford TrustedMDT pilot (approved December 2025)
- Why volatile
- May move to clinical use
- Where used
- /use-cases/referral-coordination, /use-cases/consult-briefing
- Re-check
- Quarterly
- Item
- Honeywell Experion Cognition (promised Q3 2026, not confirmed), Experion Operations Assistant (19 March 2026), Emerson AspenTech AVA (11 May 2026), Siemens Industrial Copilot and Eigen agent, AVEVA MCP for Operations Control (planned), Seeq Agent Q, Cognite Atlas AI
- Why volatile
- Vendor GA status moves; three vendor claims cross the information-path rule
- Where used
- /use-cases/energy, /use-cases/energy-asset-investigation
- Re-check
- Quarterly
- Item
- Aker BP with Cognite (16 September 2025; "more than 70 percent" engineering time, vendor) and with ABB (21 May 2026); Chevron with DataRobot Safe Start (2 June 2026); Shell with C3 AI (unverified)
- Why volatile
- Operator results and stages change; one source is machine-written
- Where used
- /use-cases/energy-asset-investigation, /use-cases/energy
- Re-check
- Before citing a figure
- Item
- ISO/IEC 42001 Annex A and ISO/IEC 22989 lifecycle stage names, read from secondary summaries
- Why volatile
- Standards texts are paywalled; wording may differ
- Where used
- /architecture/agent-lifecycle crosswalk
- Re-check
- When a licensed copy is available
- Item
- EU AI Act dates (Annex III 2 December 2027; Annex I 2 August 2028 per the tracker)
- Why volatile
- The amending act may move them
- Where used
- /layers/r11-governance-risk-sovereignty, /layers/r10-security-and-identity
- Re-check
- Quarterly against the Official Journal
- Item
- In Australia and New Zealand retailers bill households; Victoria's distributors own smart meters; NZ market parties exchange EIEP files over the registry SFTP hub
- Why volatile
- Market structure and file standards change slowly but do change
- Where used
- /use-cases/utilities, /use-cases/billing-exceptions
- Re-check
- Yearly, AEMO and Electricity Authority pages
- Item
- The Google Satellite Embedding dataset is built with Google DeepMind's AlphaEarth Foundations model (Earth Engine catalog, read 15 October 2026)
- Why volatile
- Dataset versions and model names change
- Where used
- /memory/sources, /memory/location-and-satellite-data
- Re-check
- Yearly
- Item
- Open Semantic Interchange published a v1 specification in January 2026 (CD-8)
- Why volatile
- A young specification; versions and adopters change
- Where used
- /decisions, /layers/r02-data-platform
- Re-check
- Quarterly
- Item
- Microsoft Entra Agent ID: sponsorship "should be maintained to ensure succession" when a sponsor moves or leaves, and a group can be a sponsor (learn.microsoft.com, agent owners, sponsors and managers, updated 3 September 2026, read 15 October 2026); no automatic hand-over is documented
- Why volatile
- Microsoft may add automatic succession
- Where used
- /architecture/agent-lifecycle
- Re-check
- Quarterly
- Item
- Google now calls its runtime "Agent Runtime" (the Agent Engine page redirects) and describes Agent Gateway as a policy enforcement point (Google Cloud docs, updated 13 October 2026)
- Why volatile
- Product names change
- Where used
- /architecture/system-view
- Re-check
- Quarterly
- Item
- Microsoft Foundry Toolboxes sit behind one managed MCP endpoint (Microsoft Learn, 11 October 2026)
- Why volatile
- Preview wording
- Where used
- /architecture/system-view
- Re-check
- Quarterly
- Item
- AWS AgentCore release dates: platform GA October 2025; Policy and Evaluations GA March 2026; Optimization GA July 2026; Agent Registry GA 31 August 2026
- Why volatile
- Vendor release notes
- Where used
- /architecture/system-view, /architecture/agent-lifecycle
- Re-check
- Quarterly
- Item
- Cemri et al., "Why Do Multi-Agent LLM Systems Fail?", arXiv 2503.13657, 17 March 2025 (v3 26 October 2025): 14 failure modes in 3 groups, more than 1,600 annotated traces, 7 frameworks (verified 15 October 2026)
- Why volatile
- Preprint; later versions may change counts
- Where used
- /ladder/tools-and-the-loop
- Re-check
- Yearly
- Item
- IEC 61511 governs safety instrumented systems; ISO/IEC TR 5469 places AI outside the safety function. The earlier claim that IEC 61511 "requires" no AI could not be confirmed and was removed
- Why volatile
- Standards texts are paywalled; TR 5469 may be revised
- Where used
- /layers/r10-security-and-identity, /layers/r05-lob-and-ot
- Re-check
- When a licensed copy is available
- Item
- EU AI Act Article 50 transparency dates (2 August 2026; 2 December 2026) and the Colorado AI Act start date (1 January 2027), read from law-firm notes
- Why volatile
- Amendments and delays are common
- Where used
- /layers/r10-security-and-identity
- Re-check
- Quarterly
- Item
- Microsoft agent identity: the July 2026 identity mandate and the cap of 250 identities per blueprint come from Microsoft documents; Okta, SailPoint, CyberArk (Idira) and Ping release claims are second-hand
- Why volatile
- Vendor pages and dates move
- Where used
- /layers/r10-security-and-identity, /architecture/agent-lifecycle
- Re-check
- Quarterly
- Item
- SAP Maintenance Planner Agent (GA planned Q4 2025, not confirmed shipped); Seeq Agent Q (3 March 2026); Emerson AspenTech AVA (11 May 2026); Protex AI with Bendix, 84 percent (14 January 2026) [vendor]; Intelex with COMET (27 October 2025)
- Why volatile
- Vendor GA status and figures move
- Where used
- /use-cases/energy-asset-investigation, /use-cases/safety-coaching, /use-cases/production-measurement
- Re-check
- Quarterly
- Item
- No mining agent deployment found at BHP, Rio Tinto or Fortescue on 15 October 2026; AusIMM metal accounting summary (23 April 2026); NAMUR NE 175, the NSW Workplace Surveillance Act 2005 and GISTM (August 2020) not re-checked against primary texts
- Why volatile
- A named deployment may appear; standards texts not read directly
- Where used
- /use-cases/energy, /use-cases/production-measurement, /use-cases/safety-coaching, Related analysis
- Re-check
- Quarterly
- Item
- My Health Record: reports shared by default from 1 July 2026, within 24 hours, reports not images (Australian Digital Health Agency, read 15 October 2026); short notice assessment with at least 24 hours' warning since 1 July 2023; the interoperability plan at 33 of 44 actions complete (January to March 2026 report)
- Why volatile
- Policy dates and progress counts change
- Where used
- /use-cases/healthcare, /use-cases/consult-briefing, /use-cases/compliance-evidence
- Re-check
- Quarterly
- Item
- Referral figures: Queensland 362,886 waiting in May 2026 (AMA Queensland, August 2026); Queensland 30, 90 and 365 day categories; Logan ENT about 700 referrals a month; ReferralAI 17,378 referrals at 53.8 percent agreement (PMC10642163, 2023); Waikato more than 8,000 e-referrals in 2023
- Why volatile
- Waiting lists and study figures move
- Where used
- /use-cases/referral-coordination
- Re-check
- Quarterly
- Item
- Scribe and agent deployments: Health NZ 1,000 plus 100 licences (HINZ, 26 November 2025) against about 1,250 staff (minister); Metro South, 92 percent less admin time (31 August 2026) [vendor]; Healthdirect 1.55 million triage encounters (April 2023 to March 2025); NSW single record go-live March 2026, all districts by end 2028; Epic Art 69 against 46 percent (10 March 2026) [vendor]; Tampa General call abandonment 34 to 14.9 percent [vendor]; Oxford TrustedMDT announced 16 December 2025
- Why volatile
- Vendor figures and rollout dates
- Where used
- /use-cases/healthcare and the four healthcare worked examples
- Re-check
- Quarterly
- Item
- Utilities rules and figures on the billing, vegetation and water pages: substituted meter data carries a quality flag (AEMO metering procedures); the AEMC payment-plan rule (consultation 18 June 2026, feedback due 22 October 2026); Red Energy penalty A$474,600 (February 2025); NZ EIEP1 files due by 5pm on the 5th of each month; Victorian line clearance plans due 31 March and Energy Safe Victoria infringements since 27 June 2022; span counts (Powercor 570,000, Utility Magazine 400,000, AusNet 314,000); Victoria Water Industry Standard clauses 18 and 20 and the five-hour trigger; the Arizona docket (24 March 2026) against its press release (27 March 2026)
- Why volatile
- Several are search excerpts or unchecked rules
- Where used
- /use-cases/billing-exceptions, /use-cases/vegetation-inspection, /use-cases/water-operations, /use-cases/utilities
- Re-check
- Before each use; AEMC, AEMO and ESV pages
- Item
- Self-hosting a model does not pay below about 100 to 250 million tokens a month or under 60 percent utilisation (CD-6, R01 findings 19 August 2026)
- Why volatile
- Model prices and hardware costs move
- Where used
- /decisions, /layers/r01-infrastructure
- Re-check
- Quarterly
Added 14 October 2026: corrections round
- Item
- Agent identity GA states: Okta (scheduled 30 Apr 2026, unconfirmed), SailPoint (trade press 4 Aug 2026), CyberArk now Idira (vendor blog Jan 2026), Ping (announced 27 May 2026); Microsoft Agent 365 parts still in preview at GA (agent user accounts, cross-cloud registry sync); AWS Agent Registry GA date given as 31 Aug and 6 Aug 2026
- Why volatile
- Preview to GA transitions; vendor pages change
- Where used
- R10 target-state table and identity mechanics; identity chain
- Re-check
- January 2027, against each vendor's own release notes
- Item
- Microsoft FIDES status (experimental, Python-only, no code-execution support as of 7 Oct 2026)
- Why volatile
- A framework feature can graduate in one release
- Where used
- R10 policy decision point; enforcement page
- Re-check
- January 2027
- Item
- gVisor host code-execution flaw reported in 2026 on one aggregator page
- Why volatile
- Unconfirmed against the project's advisories
- Where used
- R01 sandbox section and evidence
- Re-check
- Before the next R01 edit
- Item
- ASD ISM agent controls ISM-2133 to ISM-2135 and amended ISM-2113 (September 2026)
- Why volatile
- Control numbers taken from a compliance firm's walkthrough; the ISM release notes timed out
- Where used
- R10 threat canon
- Re-check
- Against cyber.gov.au before quoting a number
- Item
- MAS AI risk management guidelines phasing (12 and 24 months from 7 Oct 2026)
- Why volatile
- Transition dates from the response-to-feedback paper
- Where used
- R10 and R11
- Re-check
- On the MAS page before the first milestone
- Item
- OAIC automated-decision transparency rule start, 10 Dec 2026, and the Commonwealth AI impact-assessment deadline, 15 Dec 2026
- Why volatile
- Read through law-firm summaries and search excerpts; government pages timed out
- Where used
- R11 regulatory geometry
- Re-check
- On the OAIC and DTA pages before December 2026
- Item
- Queensland FAIRA: policy says required, framework page says non-mandated
- Why volatile
- The agency may reconcile the two pages
- Where used
- R11 regulatory geometry
- Re-check
- December 2026
- Item
- Card-network agent dispute and liability rules (none binding as of Oct 2026; one forecast says April 2027 at the earliest) and Coinbase x402 agent-wallet budget design
- Why volatile
- Network rules are being written
- Where used
- R10 payment stack; deterministic zones
- Re-check
- April 2027
- Item
- SAP utilities agents dated Q2 and Q3 2026 in user-group coverage
- Why volatile
- Dates slipped once already; shipped status unconfirmed on 14 Oct 2026
- Where used
- Utilities use cases (pending rebuild)
- Re-check
- Before the utilities pages publish
- Item
- AER automated-bidding guideline update (bulletin of 5 Aug 2026 read through a law-firm alert)
- Why volatile
- The guideline deadline was delayed
- Where used
- Utilities use cases (pending rebuild)
- Re-check
- Before the utilities pages publish
- Item
- Model-based approvers as defaults: Codex Auto-review (30 Apr 2026) and Claude Code auto mode as default (14 Aug 2026); AWS guardrail scores feeding AgentCore Policy
- Why volatile
- Vendor defaults and figures (99.1 percent auto-approved; 13.6 against 89 percent) change with releases and are unreplicated
- Where used
- Deterministic zones; enforcement; risk profile
- Re-check
- January 2027
- Item
- Agentic payment stack: AP2 spec version, Visa TAP, Mastercard Verifiable Intent (co-development with Google read through search summaries), Stripe shared payment tokens, Coinbase x402 agent wallets
- Why volatile
- Protocols are months old and liability rules are unwritten
- Where used
- Deterministic zones, movement of money
- Re-check
- April 2027
- Item
- CSA agentic autonomy levels v2.0 (18 Mar 2026) and the Agentic Universe draft (1 Apr 2026)
- Why volatile
- Reported as AI-assisted and not formally reviewed; may be revised or withdrawn
- Where used
- Risk profile crosswalk; agent types
- Re-check
- January 2027
- Item
- Anthropic's measure of 0.8 percent of tool calls appearing irreversible (18 Feb 2026)
- Why volatile
- Vendor telemetry on its own platform, not independently checked
- Where used
- Agent types, evidence
- Re-check
- When an independent measure appears
- Item
- Entra Agent ID sponsor rules (sponsor required at creation; passes to the leaver's manager), updated 3 Sep 2026
- Why volatile
- Vendor-documented product behaviour, subject to change
- Where used
- Agent lifecycle; identity chain
- Re-check
- January 2027
- Item
- Prompt-cache prices (about 0.1 times the base input price for cached reads; 1.25 to 2 times for cache writes), the Claude Code figures (about 7 times for agent teams, about USD 13 per developer per active day), and the absence of a native per-agent budget in model gateways
- Why volatile
- Change with model and gateway releases
- Where used
- /memory/token-efficiency
- Re-check
- January 2027
- Item
- Memory-service status (Microsoft Foundry memory in preview; no automatic expiry in AWS AgentCore memory)
- Why volatile
- Preview to GA and feature releases
- Where used
- /memory/six-architectures, /memory/permissions-and-lifecycle
- Re-check
- January 2027
- Item
- Memory benchmark figures: LongMemEval vendor scores, the Redis rerun of 21 Sep 2026, the LoCoMo answer-key audit (one unreviewed post)
- Why volatile
- Scores move monthly; the audit has not been reviewed
- Where used
- /memory/what-the-benchmarks-measure, /memory/what-we-have-measured
- Re-check
- April 2027
- Item
- Gartner's forecast that inference cost per agentic workflow rises more than fivefold through 2028 (17 Aug 2026)
- Why volatile
- Read only through search excerpts; the release returned 403
- Where used
- /memory/token-efficiency
- Re-check
- When the release is readable
- Item
- Utilities figures reported by vendors or consultancies: AGL 36 percent containment (IBM), PG&E 67 percent (PolyAI), Vector pole inspection times (Tapestry), Westnetz 90 percent and EWE 99.5 percent (consultancy citing PwC), Kraken's A$170 million at Origin against Origin's own A$100 to 150 million
- Why volatile
- Self-reported outcomes that the reporters may revise; the Origin deck was seen only in a search excerpt
- Where used
- Utilities, energy, billing exceptions, vegetation and water pages; utilities blueprint
- Re-check
- January 2027, against the utilities' own filings
- Item
- Packaged-application vendor counts and dates: SAP agent and skill counts (Q1 2026) and the Autonomous Suite (12 May 2026), Oracle's edition exclusions (Forrester, 8 May 2026), Salesforce Agentforce revenue (27 May 2026) and per-action pricing, Microsoft Dynamics 365 agent dates (April to September 2026)
- Why volatile
- Vendor marketing counts and roadmap dates move quarterly
- Where used
- Agents and packaged applications
- Re-check
- January 2027
Due Q4 2026
- Item
- OpenTelemetry GenAI semantic conventions
- What to check
- Whether the conventions have reached a stable release. Not stable as of mid-2026
- Where it is used
- R12 findings; the observability category profile. The single most important item on this list
- Item
- Dynatrace and Arize
- What to check
- Whether the transaction announced 13 August 2026 closed, and what happened to the open-source project
- Where it is used
- R12 vendors; evaluation and observability profile
- Item
- MCP registry and server trust
- What to check
- Registry status and whether signed and pinned server distribution has matured
- Where it is used
- R03 findings; gateways and identity profile
- Item
- EU AI Act enforcement
- What to check
- Article 50 enforcement in practice since 2 August 2026, and any movement on classification guidelines
- Where it is used
- R11 findings; sovereignty matrix; HR and public sector blueprints
- Item
- Kubernetes Agent Sandbox
- What to check
- Production readiness
- Where it is used
- R01 findings
- Item
- Generative and encoder price table in the economics experiment
- What to check
- Whether the per-token prices as of 2026-08-19 still hold; the cost ratio is recomputed from the editable price table in the benchmark artifact. The constant-factor claim, not the prices, is the position
- Where it is used
- Research pages: the cheap gate and the bill; the recommended approach
- Item
- Framework consolidation
- What to check
- Whether the agent framework field has consolidated further, and support states
- Where it is used
- R07 findings and vendors
Due H1 2027
- Item
- SOC behavioural baselining for agents
- What to check
- Whether any vendor has a credible answer. Unsolved as of August 2026; re-check after RSAC 2027
- Where it is used
- R10 findings; concerns matrix open gaps
- Item
- Provenance-carrying grounding as audit evidence
- What to check
- Whether Big Four methodologies or JTC 21 standards give it formal recognition
- Where it is used
- R11 findings; economics of the evidence floor
- Item
- Agent lifecycle patterns
- What to check
- Whether registry-governed lifecycle has moved from proof of concept to observed operation
- Where it is used
- R07 findings
- Item
- Memory-service benchmarks
- What to check
- Whether any independent benchmark exists. All current claims are vendor-authored and disputed between vendors
- Where it is used
- R14 vendors; memory-pipeline architecture
- Item
- Multi-agent incident reporting
- What to check
- Whether any regulator or standards body has published a frame. None exists as of August 2026
- Where it is used
- R11 findings; concerns matrix open gaps
Standing items, checked every quarter
- Item
- All vendor pricing and packaging
- Why
- Product facts in this market change quarterly. Outcome pricing, per-action metering and governance-plane pricing are all list prices as of mid-2026
- Item
- The vendor coverage matrix
- Why
- Consolidation is active in security, identity and observability. A coverage matrix is a dated artifact
- Item
skillsCLI discovery from a bare domain- Why
- Whether
npx skills add <domain>reaches/.well-known/agent-skills/index.json. At CLI 1.5.23 (August 2026) it downloads the domain directly and fails, while its own error message recommends that form. Re-check on a CLI release and restore the instruction when it works
- Item
- Product names on the one-page wall chart
- Why
- Names and availability move faster than capability. Re-verified every two months against primary sources; the per-layer vendor tables were archived on 2026-08-23 rather than maintained at that rate
- Item
- Vendor question-bank answers collected from suppliers
- Why
- An answer more than two quarters old is a hypothesis, not a fact
Items deliberately not on this list
Claims sourced to peer-reviewed research, standards texts, regulation, and primary human-factors literature. These age slowly and are cited with dates. The 1983 residual-work finding underpinning the founding metaphor has been stable for four decades and is not a re-verification candidate.
September 2026 industrial examples
Next review: December 2026, or before an adoption decision. The following are vendor descriptions, not independently verified outcome claims.
- NVIDIA video search and summarization: supported inputs, deployment requirements, and documented capability. Checked 2026-09-17.
- Roboflow Workflows: supported processing and integration features. Checked 2026-09-17.
- LandingAI document grounding: source-page grounding claims and product scope. Checked 2026-09-17.
- AiDASH vegetation management case: current case description. Checked 2026-09-17.
- AlphaEarth annual embeddings: availability, annual intervals, resolution, and comparability across releases. Checked 2026-09-17.
Cite this page
Written by Murali Sid, Founder and AI Systems Architect, last updated 15 October 2026. Licensed CC BY-SA 4.0, so quote it freely with attribution.
Murali Sid (2026). The Re-verification List. Agentic Architecture Skills. https://www.agenticarchitectureskills.com/library/re-verificationMachine-readable version of this page: /library/re-verification.md
How the guide is organised
Editorial choices for the September 2026 revision. These are the author's choices about the guide, not external evidence for a technical recommendation.
Guide updates
Reorganized memory around working context, thread state, and long-term episodes, facts, and procedures. Added a guided reading path, grouped navigation, optional embedding tours, and generated diagrams for the operati...