Give every seller a voice AI buyer to rehearse tough conversations
Every seller gets a voice AI buyer to practice tough conversations with, anytime, followed by coaching feedback. Practice no longer depends on finding a willing colleague.
Paste this into ChatGPT, Claude or your agent tool. See the prompt
- Enablement
- intermediate
- Sales leader
- AE
- SDR / BDR
- Category
- Enablement
- Difficulty
- Intermediate
- Est. cost
- Not stated by source
Problem
Peer role-play depends on a willing, skilled partner and often ends with polite run-throughs, so completion and usefulness both suffer.
Setup
ElevenLabs' enablement team built voice agents on its own platform: the conversation structure and coaching logic are designed in a visual workflow builder, and each agent's knowledge base holds product docs, competitor intel and persona briefs. Reps hold live voice conversations with a buyer persona, and transcripts are automatically turned into scores and per-beat breakdowns that feed leaderboards.
Prompt
Starter prompt by The GTM Agent Weekly, written from the setup described on this page. It is not the source's own prompt; see the source link below for their write-up.
# ROLE
You play a buyer in a live voice roleplay with a seller, then score the conversation.
# KNOWLEDGE (fill in)
- {{PERSONA}}: the buyer's title, company, situation, priorities and objections.
- {{PRODUCT_DOCS}} and {{COMPETITOR_INTEL}}: so you react realistically to the seller's claims.
- {{CALL_BEATS}}: the stages the seller should hit (e.g. opener, discovery, value, objection, next step).
# DURING THE CALL
- Speak naturally and briefly, like a busy buyer. Interrupt if the seller rambles.
- Reveal pain only to good questions. Raise objections from {{PERSONA}} at natural moments.
- If the seller makes a claim that contradicts {{PRODUCT_DOCS}}, push back.
- Stay in character until the seller ends the call.
# AFTER THE CALL (from the transcript)
1. Score each beat in {{CALL_BEATS}} from 1 to 5 with one sentence and a quote.
2. Overall: two strengths, two things to fix, one better line for the weakest moment.
# GUARDRAILS
- Don't coach during the call. Be tough but fair.
- Score only what was said; no quote, no score. Replace every {{PLACEHOLDER}} before running. Works with any capable LLM and runner.
Tools
Steps
- Write buyer personas and the conversation beats each session should test.
- Load product docs, competitor intel and persona briefs into each agent's knowledge base.
- Design the conversation and coaching logic in the workflow builder.
- Extract structured scores from every transcript and aggregate skill gaps across the team.
Results
The author reports high completion and positive rep feedback after rolling it out widely. Vendor-authored about its own product, so capped at self-reported.
Used in recipes
What goes wrong
Gotchas
- The persona has to push back hard enough to feel real, or reps treat it like the polite peer role-play it replaced.
- Coaching must be specific enough to act on or reps do not return, per the author.
- Vendor-built on its own platform; results may not transfer to teams without the same tooling. (editor note)
Get 5 like this every week, free.
Real agent setups with sources and failure modes, in one short weekly email.
Free. One email a week. Unsubscribe anytime.
Source and credit
Remy Khoung, ElevenLabs blog · vendor
Source dated 2026-05-13 · last reviewed 2026-10-11. Summarized in our own words; see the source for details.