Skip to content
AutoResearch
StaleInconclusiveLow bandNews Digest

News Digest source-mix rebalance

Baseline
62%
Final
68%
Delta
+6 pts
Variants
4
Objective

What we set out to improve

Improve digest relevance without adding noisy duplicate sources to the configured source mix.

Inconclusive

Inconclusive. The best variant nudged relevance from 0.62 to 0.68, but the gain fell within the eval confidence band, so no change was promoted. Logged for a future re-run with more daily samples.

Iterations

Variants we tried

Each variant and its coarse objective metric. The kept variant is marked; bars are relative to the best run.

  • 1Baseline — current source weightsLow62%
  • 2Variant A — upweight primary sourcesLow66%
  • 3Variant B — add two adjacent sourcesLow64%
  • 4Variant C — dedupe near-duplicatesLow68%
Run

Stages

  1. baseline

    Succeeded · 2.1s

  2. variant run

    Succeeded · 6.4s

  3. eval

    Succeeded · 900ms

Output

Artifacts and what shipped

Redaction-safe artifact previews, diffs, metric tables, and prompt variants with sensitive text removed.

  • Metric table

    Relevance by variant (0.62 → 0.68, within noise)

  • Report

    Inconclusive: gain inside confidence band

What you can see, and what is hidden

Every projection on this page is redaction-safe by construction. Redaction level: Sample content, curated, public-safe excerpts only.

Shown

  • Identifiers & counts
  • Closed-enum statuses
  • Coarse quality / resource bands
  • Timestamps & freshness

Intentionally hidden

  • Raw prompts
  • Raw documents
  • raw tool log
  • Raw trace spans
  • Embedding vectors
  • Free-text feedback
  • Auth internals & secrets
  • Secrets

Related in the Lab

All experimentsThe full gallery, grouped by product area.Family Manager observatoryThe capture → approve → route loop.News DigestRanked items, source health, and feedback.Knowledge Base observatoryWhere promoted learnings are written.