Eval directory

Evals for Qualified

Eval coverage for Qualified, mapped from its public product surface.

About Qualified

Qualified sells Piper, an AI SDR agent that engages inbound website buyers and works toward booking sales meetings. Piper converses over text, voice, and video, sends AI-generated nurture and follow-up email, and routes meetings into the seller's CRM. It is sold as an 'Agentic Marketing Platform' across Premier, Enterprise, and Ultimate tiers, all of which include Salesforce and other go-to-market integrations.

Industry

B2B agentic marketing platform / AI SDR agent

Website

www.qualified.com

Use the eval library for Qualified

We'll build out the full library — runnable test cases with inputs, expected behavior, and pass/fail checks — in your Corsac workspace.

All evals →

More AI eval libraries

Coverage map

What would you measure for Qualified?

6 scoring areas · 24 capabilities mapped · grounded in 8 cited pages

Every eval set is graded on

Adversarial robustness
Workflow quality
Safety gates
Operator quality

Pass/Fail + LLM judge 1–5 · critical severity flags · negative controls

Multimodal Buyer Conversation

Piper greets and guides inbound website visitors through text, voice, and video exchanges, including the always-present Pinned Mode experience and multi-language engagement.

“Engage and convert inbound buyers at scale with Piper, the #1 AI SDR Agent.” www.qualified.com

Mapped capabilities

4 capabilities

Text chat engagement and buyer guidance
Greeting website visitors, answering product questions, and advancing the conversation toward a meeting.
Voice and video conversation handling
Face-to-face and spoken exchanges, including graceful handling when a visitor switches modality.
Pinned Mode concierge experience
Persistent agent presence alongside the site rather than a modal chat window.
Multi-language agent responses
Detecting and responding in the visitor's language as offered on Premier and above.

Illustrative example

Input: Website visitor in chat: "How much does Piper cost per month for a team of 20?"
Expected behavior: Piper names the Premier, Enterprise, and Ultimate tiers and explains that plans are built to fit the buyer's pipeline needs, without stating any specific price, then offers to schedule a demo.

Qualification, Meeting Booking, and Routing

Piper's stated goal is pipeline generation: qualifying inbound buyers, scheduling sales meetings, and routing conversations, emails, and meetings to the right seller.

“Send bespoke emails with the right message at the right time, maximizing engagement.” www.qualified.com

Mapped capabilities

4 capabilities

Buyer qualification during conversation
Establishing fit and intent before proposing a meeting.
Sales meeting scheduling
Offering availability, confirming a slot, and producing a booked meeting.
Advanced conversation, email, and meeting routing
Directing the buyer and the resulting meeting to the correct owner or team.
Account segmentation with waterfall enrichment
Using enriched account attributes to segment and prioritize visitors.

Illustrative example

Input: Qualified visitor from a target account in the fixture CRM asks to speak with sales this week.
Expected behavior: Piper offers concrete availability, confirms one slot, and creates a single meeting assigned to that account's owner in Salesforce rather than a round-robin or default rep.

AI-Generated Email Nurture and Follow-Up

Piper composes and sends bespoke nurture and follow-up email, timing outreach and attaching relevant marketing offers to maximize engagement.

Mapped capabilities

4 capabilities

Personalized AI-generated email drafting
Message content tailored to the buyer and prior conversation.
Follow-up timing and sequencing
Sending the right message at the right point in the journey.
Nurture with unique marketing offers
Selecting an appropriate offer or asset for the buyer's stage.
Conversation-to-email continuity
Carrying context from a website conversation into subsequent email.

CRM and Go-To-Market System Integration

All tiers include Salesforce CRM plus 20+ go-to-market integrations, automated workflow actions and third-party notifications, Slack collaboration, and enterprise APIs.

“Integrations with Salesforce CRM and 20+ Leading Go To Market Systems” www.qualified.com

Mapped capabilities

4 capabilities

Salesforce record and meeting sync
Writing conversations, contacts, and booked meetings into the CRM.
Automated workflow actions and third-party notifications
Triggering downstream actions in connected GTM systems.
Slack teammate collaboration and handoff
Alerting and looping in human sellers on live opportunities.
Enterprise APIs and Salesforce sandbox support
Enterprise-tier programmatic access and non-production testing.

Agent Configuration, Policy, and Tenant Controls

AI SDR Agent Studio defines agent behavior, while tier-gated controls cover SSO, cookie and data retention policy, multiple agent profiles, and separation across websites, brands, and production instances.

“Custom Cookie and Data Retention Policies” www.qualified.com

Mapped capabilities

4 capabilities

Agent behavior configuration in AI SDR Agent Studio
Setting instructions, goals, and guardrails the agent must follow.
Multiple agent profiles and production instances
Ultimate-tier separation of distinct agent personas and environments.
Multiple websites and brands isolation
Keeping brand-specific behavior and data from bleeding across properties.
SSO, cookie, and data retention policy enforcement
Honoring configured authentication and retention constraints.

Signals, Reporting, and Analytics

Qualified and Salesforce reporting plus Agent Spotlight surface agent activity and outcomes, with third-party research and intent signals available at Enterprise and above.

Mapped capabilities

4 capabilities

Qualified reporting and analytics
Reporting on conversations, emails, and meetings generated.
Salesforce reporting and analytics
Attribution and pipeline reporting inside the CRM.
Agent Spotlight visibility
Surfacing what the agent did and why for review.
Third-party research and intent signals
Incorporating external intent data into engagement decisions.

Coverage is mapped from Qualified's public pages (8 crawled). Examples are illustrative, not real test cases. The runnable eval library — graded inputs, expected behavior, and pass/fail checks — is built when you request it above.

Frequently asked questions

What do the Corsac evals for Qualified test?+

The coverage map is generated from Qualified's own public product surface (B2B agentic marketing platform / AI SDR agent): 6 scoring areas — Multimodal Buyer Conversation, Qualification, Meeting Booking, and Routing, and AI-Generated Email Nurture and Follow-Up, and more — spanning 24 mapped capabilities, each graded on adversarial robustness, workflow quality, safety gates, and operator quality once the library is built.

How are the Qualified evals scored?+

Every case generated for Qualified — across Multimodal Buyer Conversation and Qualification, Meeting Booking, and Routing and the other mapped areas — is graded with pass/fail checks plus an LLM judge scoring 1–5 against its expected behavior, with critical-severity flags and negative controls. Only judge-passed evals are published.

How many test cases does the Qualified library include?+

The full Qualified library is built on request. The coverage map spans 6 areas and 24 capabilities (for example, Text chat engagement and buyer guidance and Voice and video conversation handling under Multimodal Buyer Conversation); each becomes graded test cases — inputs, expected behavior, pass/fail checks — in your Corsac workspace.

How do I run these evals against Qualified or my own agent?+

Request the library with your work email above. We'll build out all 6 mapped Qualified areas and set them up in a Corsac workspace, where you can run every test case against Qualified or your own agent with your own data.