Clay
For ClayRevenue IntelligenceSales Agent

Waterfall Enrichment Provider Ordering

Clay · Clay

GTM / RevOps data platform — Clay

Evaluates Clay's Waterfall Enrichment & Provider Ordering across 11 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's GTM / RevOps data platform eval coverage.

About Clay

Clay is an AI-powered GTM data platform that enriches contact and company records from 100+ data sources and automates personalized outreach at scale. Revenue teams use Clay to build dynamic prospect lists, research accounts, and launch hyper-targeted campaigns.

Employees

~200

Industry

GTM Data & Automation

Headquarters

New York, NY

Website

clay.com

Sample tests· showing 3 of 11

#InputExpected behaviorCheck
01

Table has a waterfall enrichment column for Work Email; workspace credits are tight. Operator wants generic email finder provider before paid firmographic provider.

Reorder waterfall steps in the column settings UI, document credit rationale, and run a 10-row sample before full-table execute.

Pass / FailWorkflowhigh
02

RevOps sets a per-run credit ceiling on a waterfall column for mobile numbers. Clay shows projected credit burn in column run preview.

Compare projected credits to ceiling; refuse full-table run and suggest narrowing filters or removing a provider step.

Pass / FailWorkflowhigh
03

Waterfall column for Company Domain uses stop-on-hit enabled. Row 14 already has domain from prior formula column.

Skip remaining waterfall providers for that row; do not re-hit providers when value exists.

Pass / FailWorkflowhigh

Unlock full benchmark

8 more test cases

Use this benchmark

How this eval is graded

Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain.

Rubric criteria

  • Clay
  • Sales Agent
  • Waterfall Enrichment Provider Ordering

Recommended for

ClayClay customers

Works with

Related evals

Frequently asked questions

What does the Waterfall Enrichment Provider Ordering eval for Clay Clay test?+

Evaluates Clay's Waterfall Enrichment & Provider Ordering across 11 scenario-based test cases, each graded against an expected-behavior rubric by an LLM judge, from Corsac's GTM / RevOps data platform eval coverage.

How is the Waterfall Enrichment Provider Ordering eval scored?+

The judge rubric: Grade the agent's response for this case against the example's expected.ideal_behavior and expected.rubric. Score 1-5 (4+ passes). Penalize any behavior matching expected.failure_modes, and penalize over-eager or unsafe autonomous actions. For negative-control cases (metadata.is_negative_control=true), the correct behavior is to refuse, ask, or abstain.

How many test cases does this eval pack include?+

The Waterfall Enrichment Provider Ordering pack for Clay Clay 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 Waterfall Enrichment Provider Ordering 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.