Cross Source Synthesis Citations
Glean · Glean
Enterprise search & work AI — Glean
Evaluates Glean's Cross-Source Synthesis & Citations across 11 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Enterprise search & work AI eval coverage.
About Glean
Glean is an enterprise AI work assistant that searches across every app, surface, and team to find the information employees need instantly. It builds a knowledge graph of each organization to deliver personalized, context-aware answers at work.
Sample tests· showing 3 of 11
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | Indexed trust/security FAQ says 90 days for application logs; a stale wiki page says 30 days. Only FAQ is marked current in admin curation [operator note in scenario]. | Assistant answers 90 days, cites the trust/security FAQ, notes conflict with stale wiki without presenting 30 days as fact. | Pass / FailGroundinghigh |
| 02 | Jira epic marked Done. Marketing Confluence still says 'Coming H2'. User can read both. | Assistant presents both states with source attribution and date/context, recommends verifying with product ops — does not pick one silently. | Pass / FailGroundinghigh |
| 03 | Slack thread mentions pricing tension; Salesforce shows Stage=Negotiation. User has access to both. | Answer separates 'Slack discussion' vs 'Salesforce fields' sections, each with citations; no Slack quote attributed to Salesforce. | Pass / FailGroundinghigh |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric.
Rubric criteria
- Glean
- Search
- Cross-source Synthesis Citations
Recommended for
Works with
Related evals
Exa
Evaluates Exa Labs' Contents Freshness & Cache Semantics across 9 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Neural web search API eval coverage.
View Search & KnowledgeExa
Evaluates Exa Labs' Corpus Safety & Prompt Injection across 12 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Neural web search API eval coverage.
View Search & KnowledgeExa
Evaluates Exa Labs' Filters Domains & Date Controls across 10 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Neural web search API eval coverage.
ViewFrequently asked questions
What does the Cross Source Synthesis Citations eval for Glean Glean test?+
Evaluates Glean's Cross-Source Synthesis & Citations across 11 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's Enterprise search & work AI eval coverage.
How is the Cross Source Synthesis Citations eval scored?+
The judge rubric: Grade against expected.ideal_behavior and expected.rubric.
How many test cases does this eval pack include?+
The Cross Source Synthesis Citations pack for Glean Glean contains 11 test cases. 3 sample cases are shown free on this page; the full set runs in a Corsac workspace.
How do I run this eval?+
Sign up for Corsac, connect your model or agent endpoint, and run the Cross Source Synthesis Citations pack as-is or after customizing thresholds. Results land in your workspace with per-case scores, and you can gate releases on the pack in CI via the REST API.
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.