Skip to content
SQA Cockpit
← All runslive api
The contract
Metaintro Chat’s promise: tell us what you need — we return relevant, quality job results based on your ask, verified daily, no ghost jobs.
The claim SQA tests: The jobs returned by Metaintro Chat answer what the user asked for, judged by an LLM ensemble against the query and the user's profile. (claim C8).
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.
0 pass · 0 fail · 13 unknown
  • C0 MUST
    Headline promise
    could-not-evaluate — no relevancy score in this run
    UNKNOWN
  • 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
  • C6 MUST
    The chat returns job cards
    no 'wait-for-jobs' step in this run
    UNKNOWN
  • C7 MUST
    Job cards have required fields
    no 'card-shape' step in this run
    UNKNOWN
  • C8 MUST
    Returned jobs are relevant to the query · HEADLINE
    could-not-evaluate — no relevancy score in this run
    UNKNOWN
  • C9 SHOULD
    All aspects of the query are covered
    could-not-evaluate — no relevancy score in this run
    UNKNOWN
  • C10 SHOULD
    Score holds across reruns
    needs a sweep — a single run cannot witness this clause — needs a sweep
    UNKNOWN
  • C11 SHOULD
    Competitive vs LinkedIn / Indeed / Google
    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
  • ·Metaintro Chat (SUT) ran 1 run on behalf of 1 seeker (P1, Lena Park).
  • ·The chat returned 0 jobs. The judge scored them.
  • ·Result: Job-Seeker Index 0/100. Not relevant— see “Why this verdict” (each gap maps to a claim in the Contract).
  • ·Compared to 3 competitors (LinkedIn / Indeed / Google) further down.

1 ·THE VERDICT

the answer in one number
30-day JSI history
METAINTRO CHAT · JSI SWEEP · RUN #27

Not relevant.

Run #27 of metaintro-chat on profile P1 for the query "deploy verification". Job-Seeker Index 0/100.

2 ·WHY THIS VERDICT

ranked by severity
No gaps reported for this run.

3 ·THE STORY

what went in, what came out

Input

the same input was run against all 4 platforms
Query
Job-seeker profile
Skills
(no skill inferred)
ESCO
Industry
Computer Systems Design
NAICS 541512
Location
United States
ISO US
Education
Bachelor or equivalent
ISCED ISCED 6

Output · jobs returned

TitleCompanyLocationPostedLink
No jobs returned.

4 ·THE BENCHMARK

vs. LinkedIn, Indeed, Google

Benchmark · 4 platforms × 7 axes

RecognitionSpecificityReachabilityRecencyMatch qualityHostility filterSalary surface
  • Metaintro (us)
  • LinkedIn
  • Indeed
  • Google

Capability matrix · platforms × axes

PlatformRecognitionSpecificityReachabilityRecencyMatch qualityHostility filterSalary surfaceOverall
Metaintro ·us65
LinkedIn 63
Indeed 50
Google 56

5 ·SESSION RECORDING

watch the probe drive each platform

Session recording

watch what the probe actually saw

6 ·RUN MECHANICS

provenance & reproducibility
Duration
5.00s
Steps
Judges
Commit
Started
2026-05-29 03:00 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

This run carries no per-component probe data, so only system is shown. When a run exercises external components (Chat Engine, MongoDB, OpenRouter…), each appears here with its own health and the verdict driver is highlighted.

Press ⌘K to search