Skip to content
SQA Cockpit
← All runslive api
The contract
kai’s promise: store what matters and recall it on demand — surface the right memory for the ask, ranked, with no relevant memory missed.
The claim SQA tests: The jobs the metaintro-chat search engine returned, in the chat thread, are relevant to what the user asked for. (claim C0).
This run tested the system against its contract, clause by clause. A single run can only witness some clauses; the rest stay UNKNOWN — never a faked pass.
1 pass · 0 fail · 7 unknown
  • C0 MUST
    Headline promise
    relevancy score = 75/100 (pass-band ≥ 60)
    PASS
  • C1 MUST
    User can sign in
    no 'login' step in this run
    UNKNOWN
  • C2 MUST
    User can open a new thread
    no 'open-thread' step in this run
    UNKNOWN
  • C3 SHOULD
    Onboarding gate completes
    no 'onboarding' step in this run
    UNKNOWN
  • C4 SHOULD
    Filters from onboarding don't bias the query
    no 'clear-filters' step in this run
    UNKNOWN
  • C5 MUST
    User-typed query is what the engine sees
    no 'submit-query' step in this run
    UNKNOWN
  • C10 SHOULD
    Score holds across reruns
    needs a sweep — a single run cannot witness this clause — needs a sweep
    UNKNOWN
  • C12 MAY
    Run completes within budget
    needs a sweep — a single run cannot witness this clause — needs a sweep
    UNKNOWN
TL;DR · 30-second primer
  • ·KAI (SUT) ran 1 run on profile longmem-phase-a.
  • ·Result: Memory Recall Index 75/100. Strong recall— see “Why this verdict” (each gap maps to a claim in the Contract).

1 ·THE VERDICT

the answer in one number
30-day MRI history
KAI · MEMORY RECALL · RUN #26

Strong recall.

Run #26 of kai on profile longmem-phase-a for the query "MRI sweep — memory-recall (real, recall@5)". Memory Recall Index 75/100.

Verdict PASS: every step completed cleanly; nothing pulled the verdict down.

AI synthesis · openai/gpt-4o-mini

The system successfully completed its task, achieving a pass with a JSI score of 75 out of 100 in the memory-recall scenario. The outcome was driven by a strong performance in the memory-recall step, where it correctly recalled 3 out of 4 items. However, there was a failure in the snappy deployment step due to a lack of matching memory in the top-k results.

2 ·WHY THIS VERDICT

ranked by severity
No gaps reported for this run.

3 ·THE STORY

what went in, what came out

Input

what the probe sent in
Query
Skills
(no skill inferred)
ESCO —
Industry
Computer Systems Design
NAICS 541512
Location
United States
ISO US
Education
Bachelor or equivalent
ISCED ISCED 6

5 ·SESSION RECORDING

watch what the probe saw

Session recording

watch what the probe actually saw
No recording available for Metaintro.

6 ·RUN MECHANICS

provenance & reproducibility
Duration
4.00s
Steps
5
Judges
—
Commit
kai-recall
Started
2026-05-28 20:24 UTC
Trace

Evidence by step

every artifact, link, excerpt, row, metric & recording — grouped by the step that produced it

No evidence recorded for this run.

Evidence integrity

each artifact is SHA-256 hashed at capture — proof it is unmodified

No integrity manifest recorded for this run.

7 ·SYSTEM ANATOMY

which component drove the verdict

Every component held — no failure attributed.

Press ⌘K to search