Source-linked memory
Durable records keep the source, time, state, and history needed to inspect why Actionairy remembers something.
AI memory you can inspect, control, export, and erase.
Every durable claim keeps its source. You can control whether external AI may process it, export your memory, and follow deletion through completion.
Per-record processing control
Mark memory Never send, Redacted only, or Allowed. Denied and restricted records are excluded before external AI processing.
Metadata-only vector index
Semantic search stores embeddings and policy metadata in the vector index, not the source text. Every hit is rechecked against the authoritative record.
Cascading deletion
Delete a source and its dependent memory is reconciled. Delete the account and cleanup retries across configured providers until it completes.
Privacy is part of product value.
Independent research shows that clear data practices influence both adoption and trust in AI products.
75%will not purchase from organizations they do not trust with their data.Cisco Consumer Privacy Survey46%name clear communication about data use as the most effective trust builder.Cisco 2026 Data and Privacy Benchmark60%say advances in AI make trust even more important.Salesforce AI customer research
Authorization is checked twice.
The vector index finds candidates. The source record decides what can actually be used.
Deletion receipt
A provider outage does not turn deletion into a dead end.
Account deletion is placed in a durable queue. If a configured provider is temporarily unavailable, Actionairy keeps the local identity long enough to retry safely, then removes it after provider and local cleanup completes. A capability-protected receipt reports progress without exposing account data.
- Provider cleanup fails closed
- Retries use a durable lease and backoff
- The completed receipt is content-minimized and expires
We do not make a blanket “more private than every AI lab” claim.
Privacy depends on the product, plan, settings, and data flow. Large AI providers already make meaningful enterprise privacy commitments. Our narrower advantage is concrete: Actionairy makes operating memory source-linked, per-record controllable, exportable, and deletable with a visible path.
Evidence, in the openThe intelligence.
The intelligence.
The evidence behind it.
Useful AI needs more than a convincing answer. We evaluate task relevance, engineering readiness, and code implementation separately—and publish the limits alongside the results.
Archived development results
Latest Nebius results and live workflow checks. The dated results below remain available for comparison.
01 / Relevance
Task relevance
Keep real tasks visible. Let evidence decide what belongs in the engineering queue.
14/14
investigated cases passing all checks
Synthetic development testgpt-5.4-2026-03-05
Small synthetic set, not measured real-world accuracy.
02 / Readiness
Engineering enrichment
Recognize when a request has enough context to become engineering work—and when it does not.
24/24
correct readiness decisions
Synthetic development testgpt-5.4-2026-03-05 · low reasoning
Readiness is not plan correctness. Independent plan-quality review is still pending.
03 / Implementation
Datacurve DeepSWE
Test code changes against a separate, externally defined coding benchmark.
56.6%
64/113 · full-cohort tasks passed
Separate Compress Cloud runArchived Compress Cloud coding run
A separate Compress Cloud run, not a meeting-to-code success rate.
Explore full results and methodologyBaselines, limitations, and what we still need to measure
Separate measurements of task relevance, plan preparation and coding. Development fixtures are not independently labeled real-world accuracy. These scores must not be combined into an end-to-end success rate.
Task relevance
- investigated cases passing all checks
- 14/14100.0%
- Real tasks retained
- 14/14100.0%
- Incorrect queue admissions
- 0/140.0%
- Source-only baseline passing all checks
- 8/1457.1%
- 14 agent-authored cases; live reviewer with frozen history, code and web retrieval. Planning is an invocation spy, not an executed plan.
- A real task may remain visible without belonging in our engineering queue. Human acceptance and execution approval remain separate.
Engineering enrichment
- correct readiness decisions
- 24/24100.0%
- Completed cases
- 24/24100.0%
- False-ready decisions
- 0/120.0%
- Automatic wording checks
- 23/2495.8%
- Plain-model readiness baseline
- 24/24100.0%
- Plain-model wording baseline
- 20/2483.3%
- Raw reviewer contrast checks
- 8/1080.0%
- 24 agent-authored ambiguous tasks (16 original + 8 transfer). Readiness is not plan correctness. The separate raw reviewer scored 8/10, incorrectly rejecting two valid briefs.
- Same source evidence and per-call output cap; unequal total budget: up to 4 Actionairy calls versus 2 baseline calls. No claim of competitor superiority.
- Independently reviewed usable-plan accuracy and human correction time are not yet measured.
- Failed calls remain in the full denominator. Automatic wording checks are lexical, not semantic grading. No independent human usable-plan score is available.
Datacurve DeepSWE
- full-cohort tasks passed
- 64/11356.6%
- 2 tasks remained ungradeable after bounded regrading. They receive no pass credit and stay in the full-cohort denominator.
- Sealed candidate patches and pinned verifier contexts. This is a separate coding evaluation, not an end-to-end Actionairy meeting-to-code test or a current-model leaderboard claim.
What these results do not measure
Meeting extraction: independently labeled capture precision and recall are not yet available. Transcript-upload acceptance is a user-journey check, not an accuracy estimate.
This archived report does not measure independently reviewed plan quality, human correction time, or a representative meeting-to-code success rate. Historical results do not establish current-model performance or competitor superiority.
The DeepSWE mark identifies Datacurve’s benchmark. Our result is a Light Reach evaluation, not a Datacurve endorsement or an official leaderboard entry.