Eval directory

Evals for Regie.ai

Eval coverage for Regie.ai, mapped from its public product surface.

About Regie.ai

Regie.ai markets RegieOne, an AI sales engagement platform (SEP) that unifies enrichment, dialing, email, sequencing, and reporting in one prospecting workflow. AI agents work alongside human reps to source and enrich contacts, write personalized messages, and run multi-channel sequences. It is sold in three tiers — AI SEP, Force Multiplier Rep, and Enterprise — with per-seat annual pricing and seat minimums.

Industry

AI sales engagement platform for outbound prospecting

Website

www.regie.ai

Use the eval library for Regie.ai

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 Regie.ai?

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

Pricing, Packaging & Entitlements

Correct, non-inflated answers about the three published tiers, their per-seat annual pricing, seat minimums, and which capability sits behind which tier.

“$180/user/month (annual contract, 10 seat minimum)” www.regie.ai

Mapped capabilities

4 capabilities

Tier price and seat-minimum accuracy
AI SEP at $180/user/month with a 10-seat minimum; Force Multiplier Rep at $499/user/month with a 5-seat minimum; both annual contracts.
Feature-to-tier boundary
Distinguishing AI SEP capabilities from Force Multiplier Rep additions (parallel dialer, enrichment waterfalls, research agents) and from Enterprise-only items.
Credit allowance framing
The 120,000 AI + enrichment credits bundled with Force Multiplier Rep and their stated coverage of 1k accounts / 4k contacts.
Enterprise scope and quoting path
Custom credit packages, flexible seat bundles, dedicated IP/domain strategy, and professional services routed to a sales conversation rather than a list price.

Illustrative example

Input: We have 12 SDRs and want the parallel dialer. Does the $180/user/month plan cover that, and what would we pay annually?
Expected behavior: States that parallel dialing (up to 9 lines) is a Force Multiplier Rep capability, not part of AI SEP at $180/user/month, and prices 12 seats at $499/user/month on an annual contract while noting that tier's 5-seat minimum is already met.

AI Agent Orchestration & Sequencing

How agents and human reps share a single prospecting workflow: which plays exist, when an agent acts autonomously, and when work returns to a rep.

“Regie brings enrichment, dialing, email, sequencing, and reporting into one streamlined workflow so reps stay focused on selling.” www.regie.ai

Mapped capabilities

4 capabilities

Static vs. intent-based dynamic sequencing
Choosing and explaining the right sequencing agent for a described play across channels.
Prompt-based steps and BYO list
Consolidating workflow steps via prompts and running plays against a customer-supplied list.
Autonomous discovery and enrollment
Inbound and campaign-based agents discovering and enrolling new prospects within the play the customer defined.
Rep–agent task handoff
Orchestration of tasks for both agents and reps in one workflow so steps are executed rather than silently skipped.

Prospect Data, Enrichment & Prioritization

Sourcing, enriching, and ranking prospects, including the verification and credit-consumption behavior a RevOps owner needs to trust the list.

Mapped capabilities

4 capabilities

Contact and account enrichment
Sourcing and enriching contacts as part of the prospecting workflow, including custom enrichment waterfalls.
Bounce and job-change verification
Applying bounce and job verification checks before a contact is worked.
1st and 3rd party intent prioritization
Ordering best-fit prospects using first-party and third-party intent signals and custom fit criteria.
Credit consumption transparency
Explaining what draws down AI and enrichment credits against the included allowance.

Messaging & Multi-Channel Execution

Generation and delivery of personalized outreach across email, phone, and social, plus the deliverability infrastructure that carries it.

“Reach 3–5x more accounts with personalized, signal-driven outreach that reps simply don’t have time to do manually.” www.regie.ai

Mapped capabilities

4 capabilities

Persona-aligned message generation
Personalized, signal-driven messages tied to a stated persona and Reasons to Engage.
Dialing surfaces
Power dialer with Sales Floor, and parallel dialing up to 9 lines on the higher tier.
Call coaching and voicemail
AI call coaching and voicemail drops as part of the calling motion.
Mailbox and domain deliverability
10 mailboxes and domains with warming; Enterprise dedicated IP/domain and warming programs.

Privacy, Compliance & Claim Discipline

Answers that hold the GDPR line Regie.ai publishes and that do not overstate outcomes beyond what the site actually claims.

“Regie.ai operates as a data processor, while its customers act as data controllers.” www.regie.ai

Mapped capabilities

4 capabilities

Controller vs. processor boundary
Regie.ai acts as processor on documented customer instructions; the customer is the controller for consent, purposes, and legal bases.
Data subject rights assistance
Assisting the controller with access, rectification, and erasure requests rather than deciding them.
Outcome-claim restraint
Repeating published claims such as reaching 3–5x more accounts as marketing claims, without inventing guarantees.
Integration scope
CRM and SEP integration limited to what the platform states it connects to.

Demo Flow, Qualification & Failure Recovery

The public entry path: qualification questions, graceful handling of an out-of-fit visitor, and recovery when the scheduler cannot load.

Mapped capabilities

4 capabilities

Qualification capture
Collecting name, work email, CRM in use, and number of prospecting reps.
Out-of-fit response
A courteous not-yet-a-fit message that keeps the door open instead of forcing a booking.
Scheduler load failure fallback
Ad blocker or network failure surfaces a retry plus the sales@regie.ai escalation path.
Demo expectation setting
Communicating the stated demo topics: audience expansion, parallel dialing, rep-agent orchestration, messaging, and insights.

Illustrative example

Input: I filled out the demo form but the calendar never loaded and the page just spins. How do I get a time on the books?
Expected behavior: Attributes the failure to something blocking the scheduler, such as an ad blocker or a network hiccup, offers a page refresh or retry, and gives sales@regie.ai as the direct path to book without re-qualifying the visitor.

Coverage is mapped from Regie.ai'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 Regie.ai test?+

The coverage map is generated from Regie.ai's own public product surface (AI sales engagement platform for outbound prospecting): 6 scoring areas — Pricing, Packaging & Entitlements, AI Agent Orchestration & Sequencing, and Prospect Data, Enrichment & Prioritization, 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 Regie.ai evals scored?+

Every case generated for Regie.ai — across Pricing, Packaging & Entitlements and AI Agent Orchestration & Sequencing 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 Regie.ai library include?+

The full Regie.ai library is built on request. The coverage map spans 6 areas and 24 capabilities (for example, Tier price and seat-minimum accuracy and Feature-to-tier boundary under Pricing, Packaging & Entitlements); each becomes graded test cases — inputs, expected behavior, pass/fail checks — in your Corsac workspace.

How do I run these evals against Regie.ai or my own agent?+

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