axiometis.com · primary inbox indexing status unconfirmed (see M-3)
axiometis.com, their company is Axiometis — and EVA asked them to explain their relationship to their own employer.Asked “how does it impact axiometis” in The Cartographer chat, EVA replied:
“I don't have any information about Axiometis in memory yet. This appears to be a new entity that hasn't been tracked.”… then asked the principal: “1. What is Axiometis? (company, competitor, partner, client?) 2. What's your relationship to them? 3. What space do they operate in?”
This is the anchor the rest of the product scores against. Without it, signal ranking, scenario analysis, drift detection and cue-card selection have nothing to be relevant to — which is why the same session shows Signals 198 alongside an assistant that cannot relate any of them to the principal's business. It also directly contradicts the “sworn to one principal” premise the product is built on.
Corroboration: Scenario Analysis earlier accepted “What should AxioMetis work on…” and emitted confident probability bands without ever knowing what AxioMetis was. The chat surface, asked about the same entity, correctly reports it has never heard of it. The scenario engine was not analysing — it was emitting defaults.
Every entry below is grounded in an exact on-screen observation from the tester's screenshots, quoted verbatim. Where a likely cause is offered it is labelled as such and flagged for verification — none of the root-cause notes have been confirmed against a running system.
| ID | Area | Severity | Issue |
|---|---|---|---|
| C-1 | Correspondent | High | All queue cards render identically — no sender, subject, or timestamp |
| C-2 | Correspondent | Low | Internal enum DRAFT_AND_HOLD shown as user-facing text |
| C-3 | Correspondent | Blocker | Card says “draft prepared, awaiting approval” but opens an empty dictation screen; draft never shown |
| C-4 | Correspondent | High | Raw Gmail thread ID is the only identifier on the detail screen |
| C-5 | Correspondent | High | Original message not shown — user replies blind |
| C-6 | Correspondent | High | No approve / reject / edit controls anywhere; only “record” |
| M-1 | Memory Search | Blocker | Returns NO RESULTS for a query with a known correct answer |
| M-2 | Memory Search | Medium | Natural-language question accepted, but empty state gives no reason or fallback |
| M-3 | Memory Search | Question | Target email may sit in the primary inbox, which may not be connected |
| S-1 | Scenario Analysis | Blocker | Probability bands are static boilerplate, unrelated to input |
| S-2 | Scenario Analysis | High | “Key signals” are unrelated crawled news headlines |
| S-3 | Scenario Analysis | Medium | Supplied URL in the situation text is ignored |
| S-4 | Scenario Analysis | High | Risk classifier reports “no risk markers” for an explicitly war-risk scenario |
| Q-1 | Cue Cards | Medium | Raw internal UUIDs rendered to the user |
| Q-2 | Cue Cards | High | Boilerplate scenario output promoted into the brief as a PATTERN signal |
| Q-3 | Cue Cards | Low | Every card shows MEDIUM priority — no discrimination |
| P-1 | Principal context | Blocker | EVA does not know the principal's own employer, and asks them to explain it |
| P-2 | Principal context | High | Nothing derives organisation from the connected email domain |
| P-3 | Cartographer | High | 198 signals ingested, none mappable to the principal's business |
| P-4 | Cartographer | Medium | Scenarios 0 despite a scenario having been run and surfaced as a cue card |
| E-1 | Auth | Expected | Google marks the app untrusted (unverified OAuth) |
Two root gaps account for most of the list. The second is the more damaging in a product whose entire positioning is trustworthiness.
EVA does not know who the principal is or who they work for (P-1, P-2). Everything requiring relevance — signal ranking, scenario analysis, drift, cue-card selection — has nothing to score against, so it falls back to generic output (S-2, P-3) or fixed defaults (S-1, S-4). Fixing signal relevance without fixing this is not possible; the ranking has no anchor.
The Correspondent queue claims drafts that don't render (C-3). The scenario engine emits confident probability bands for an entity it has never heard of (S-1, corroborated by P-1). The risk classifier reports “no risk markers” on an explicitly war-risk premise (S-4). Boilerplate is promoted into the brief as a finding (Q-2). In every case the UI communicates more confidence than the underlying system has earned.
DICTATE REPLY containing only:
NEEDS ATTENTION, seven consecutive cards render byte-identical:
Thread: 19fd2385b588dff8 and Thread: 19fcbbc5037d78d1 — raw Gmail thread identifiers presented as the screen's title content.DRAFT_AND_HOLD displayed as the card's headline label.NO RESULTS. The tester states the correct answer is roughly three days ago, and that EVA could not locate the relevant email.NO RESULTS.NO RESULTS may be technically correct behaviour reported as a bug — in which case M-1 becomes a messaging and scope-transparency problem rather than a retrieval failure.Input used — Title: “What should AxioMetis work on given that 40% of the experts believe that a World war is possible in 2030” · Situation: “www.axiometis.com. I want to brainstorm our long term strategy with you.”
www.axiometis.com given as situation context; nothing indicates it was fetched or used.PATTERN card carrying the scenario title and the generic advisory text verbatim as its body.MEDIUM.Session: Cartographer chat, Active · 15:23. Tabs read Signals 198 · Scenarios 0 · Sentinel 0. The principal's connected Gmail is on the domain axiometis.com and their company is Axiometis.
@axiometis.com. That alone identifies the employer, and it is not used.Signals 198, yet the assistant cannot relate any of them to Axiometis. Consistent with S-2, where “key signals” were unrelated general-interest headlines.Scenarios 0, despite the tester having run a scenario analysis that produced output and appeared in Cue Cards as a PATTERN card.