FIKA Admin — Observability

—

Online evaluation

Every live answer is scored automatically after it is sent: four RAGAS metrics, answer time and cost. Scores range 0–1, colour-coded: ≥ 0.85 0.70–0.85 < 0.70. Hover any metric name for its definition.

Summary

Avg Faithfulness
—
no data yet
Answer relevance answer-level
—
no data yet
Avg cited precision
—
no data yet
Retrieval relevance chunk-level
—
no data yet
Total evaluated
—

Answer time

How long engineers waited for an answer, measured at the API (not the scoring time).

Median
—
90th percentile
—
95th percentile
—
Slowest
—

Cost per answer

From the usage ledger.

Per answer
—
Answers
—
Answering spend
—
Scoring and background
—

Daily average (last 30d)

Faithfulness Answer relevance Cited precision

Knowledge Gaps

Topics users asked about that FIKA could not answer confidently, clustered by phrase. Read-only — uploading documents that cover the top topics closes the gaps.

Topic Count Sample question Last seen
Loading…

Metric health — automatic diagnosis

checking…

Recent evaluations

When User Question Faithfulness Answer relevance Cited precision Retrieval relevance Answer time
Loading…

Offline evaluation

Each release is scored against a fixed golden dataset of questions with known answers, and compared with the previous release against quality gates.

No release scorecards recorded yet.