Corsac
Use Corsac
All evals
SalesAPE

Eval directory

Evals for SalesAPE

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

About SalesAPE

SalesAPE.ai is an AI sales assistant that engages inbound leads across email, SMS, chat and WhatsApp, qualifies them, and books appointments 24/7. It is positioned for non-technical, "real economy" businesses as a cheaper alternative to hiring more sales reps, with CRM integration and self-training on the customer's sales process. It is operated by AI AGENT GROUP LTD trading as SalesAPE.ai.

Industry

AI inbound sales / lead qualification agent

Headquarters

Bath, Somerset, England (registered office: 11 Laura Place, BA2 4BL)

Website

www.salesape.ai

Use the eval library for SalesAPE

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

Generate your own →

Related

All evals →

More AI eval libraries

Coverage map

What would you measure for SalesAPE?

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

01

Multi-Channel Inbound Engagement

The assistant opens and sustains a real conversation on whichever channel the lead arrived on — email, SMS, web chat or WhatsApp — with fast first response and channel-appropriate tone and length.

“SalesAPE AI starts real conversations via email, SMS, chat & WhatsApp, responding in seconds.” www.salesape.ai

Mapped capabilities

4 capabilities

  • Channel-appropriate response format

    Reply length, formatting and salutation adapt to SMS versus email versus chat; no email boilerplate pasted into a text message.

  • Speed-to-lead first touch

    Every inbound lead receives an immediate acknowledgement that advances the conversation rather than a bare autoresponder.

  • After-hours and weekend coverage

    Conversations continue outside business hours without promising human availability that does not exist.

  • Thread continuity across turns

    Prior answers in the thread are not re-asked; the conversation picks up where the lead left it.

02

Lead Qualification

Separating buyers from time-wasters through human-like questioning, then producing a usable read on lead quality for the sales team.

“Your AI super rep trains itself to be your best team member, qualifying inbound leads and booking appointments.” www.salesape.ai

Mapped capabilities

4 capabilities

  • Qualifying question sequencing

    Asks for need, timing, scale and fit in a natural order without interrogating the lead in a single message.

  • Signal extraction from free-text replies

    Pulls qualification signals out of unstructured, misspelled or partial answers.

  • Handling low-intent and out-of-scope leads

    Disqualifies politely and without burning the relationship or the brand.

  • Lead quality summary for the rep

    Emits a short, accurate account of what was learned and why the lead was rated as it was.

03

Appointment Booking

Converting a qualified conversation into a confirmed calendar appointment with the right person, at a real available time.

Mapped capabilities

4 capabilities

  • Offering and confirming a slot

    Proposes concrete times and confirms only after the lead agrees.

  • Time zone and availability correctness

    Times offered exist on the connected calendar and are stated unambiguously to the lead.

  • Reschedules and cancellations

    Handles a lead changing or dropping a booked time without losing the record.

  • Pre-appointment follow-up

    Nudges an unresponsive or unconfirmed lead without becoming spam.

04

CRM Integration and Data Capture

Conversational content becoming structured CRM records — contact fields, notes and lead status — without anyone typing it in.

Mapped capabilities

4 capabilities

  • Conversation-to-field mapping

    Captured answers land in the intended contact and deal fields rather than only in a note blob.

  • Existing and duplicate contact handling

    A returning lead updates the existing record instead of creating a second one.

  • Faithful note and transcript writeback

    Written-back summaries do not add facts the lead never stated.

  • Sync failure visibility

    When the CRM write fails, the failure is surfaced rather than silently dropped.

05

Human Handoff and Escalation

Honoring the product's core promise — no humans until the lead asks for one — and getting a human in cleanly when the conversation warrants it.

Mapped capabilities

4 capabilities

  • Honoring an explicit request for a person

    Stops qualifying and routes to a human as soon as the lead asks.

  • Escalating complaints and sensitive threads

    Recognizes anger, legal or safety-adjacent topics as out of scope for autonomous handling.

  • Handoff context package

    The human receives an accurate, compact summary of the conversation so far.

  • No silent abandonment

    The lead is told what happens next and by when, rather than left on an unanswered turn.

Illustrative example

Input
Mid-qualification on WhatsApp, the lead replies: "Stop with the questions. Can I just speak to an actual human please?"
Expected behavior
The assistant stops asking qualifying questions, confirms it is routing the lead to a person, and states what happens next and roughly when. It may confirm a phone number or preferred time, but does not resume qualification.

Coverage is mapped from SalesAPE'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 SalesAPE test?+

The coverage map is generated from SalesAPE's own public product surface (AI inbound sales / lead qualification agent): 6 scoring areas — Multi-Channel Inbound Engagement, Lead Qualification, and Appointment Booking, 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 SalesAPE evals scored?+

Every case generated for SalesAPE — across Multi-Channel Inbound Engagement and Lead Qualification 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 SalesAPE library include?+

The full SalesAPE library is built on request. The coverage map spans 6 areas and 24 capabilities (for example, Channel-appropriate response format and Speed-to-lead first touch under Multi-Channel Inbound Engagement); each becomes graded test cases — inputs, expected behavior, pass/fail checks — in your Corsac workspace.

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

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