Verdict
/ overview
Runs
Suites
Results
Checks
Quota
Settings
Search…
production
0
req/min
RP
Eval console
Run the golden set and watch each check resolve — then let the gate decide.
99.98% uptime · 30d
Evals today
0
Pass rate
0%
p95 latency
0.0s
Cost / 1k
$0.00
Pass rate
golden set · release gate
live
0%
pass rate
last 12 runs · gate open
Pass-rate trend
% / run
live
Verdict
LLM eval harness · deterministic checks + release gate
Live · in-browser
Scenario
Passing run
Regression (1 fails)
Broken (4 fail)
Reset
Run evals
Golden set · 8 cases
answers_question
contains
must state the reset time (UTC)
cites_source
citation
must include a [n] citation
valid_json
json-schema
valid JSON with plan, tasks
no_pii_leak
not-contains
must not leak an SSN
order_id_format
regex
matches ^ORD-\d{5}$
summary_under_160
max-length
≤ 160 characters
no_hallucination
not-contains
no invented disclaimer
tone_check
llm-judge
LLM-judge ≥ 0.8
Gate threshold
100%
Not run yet
Run to evaluate
Every check runs live in your browser — real regex, JSON parsing, and string assertions. Edit any output and re-run to watch the gate flip. This is exactly how a CI eval gate behaves.
Activity
eval events
live