Skip to content

Latest commit

 

History

History
60 lines (45 loc) · 1.92 KB

File metadata and controls

60 lines (45 loc) · 1.92 KB

Evaluation

Evaluate source-grounded agents on the quality of their evidence and the usefulness of their recommendations.

Core Questions

  1. Did the agent find fresh, relevant sources?
  2. Did extraction return enough useful content?
  3. Are claims supported by source evidence?
  4. Are recommendations specific and actionable?
  5. Did the workflow stay within cost and latency budgets?
  6. Can a user inspect where the answer came from?

Suggested Scorecard

Dimension What To Check
Freshness Sources reflect the requested time window
Relevance Results match the approved context
Coverage Prospect, industry, and competitor lanes are represented
Grounding Every important claim maps to a source
Specificity Recommendations name concrete actions
Source diversity The brief does not depend on one domain
Cost Run stays within search, extraction, and token budgets
Latency User sees progress and receives output fast enough
Robustness Partial failures do not break the whole run

Regression Set

Keep a small fixture set for repeatable tests:

  • a known company profile
  • expected competitors
  • representative search results
  • extracted page samples
  • one high-quality target brief
  • examples of weak or irrelevant sources

Use the fixture set to test prompt changes, schema edits, and UI changes without spending provider credits.

Citation Validation

For every generated brief, validate:

  • cited URLs appear in the evidence packet
  • source titles are preserved
  • no final section cites an invented source
  • unsupported claims are either removed or marked uncertain

Human Review

For strategy-style outputs, a human reviewer should ask:

  • Would I act on this today?
  • Is the recommendation grounded in current evidence?
  • Is the source credible enough for the action?
  • Did the agent miss an obvious source category?
  • Is the brief concise enough for the target workflow?