Auxot
Tutorials Docs Pricing Login

Stress-test your pitch with simulated buyer personas

Stand up a **pitch-rehearsal agent** — rotate skeptical CFO, security lead, and end-user voices against **your** demo narrative — surface objections and trap questions **before** real prospects invent them — grounded in ideal-customer-profile context ([Add your first context file](/tutorials/add-your-first-context-file)) — debrief stays human.

Plus: three Admin-Agent passes — mint three personas from your directory bullets alone, script an **adversarial round** with scoring rubric, and harvest **talk-track patches** for [Prep for your next sales call](/tutorials/prep-for-your-next-sales-call) briefs.

Audience Everyone · Admins · Executives
Time ~12 min
Prerequisites Positioning lives somewhere durable ([Add your first context file](/tutorials/add-your-first-context-file) — ideal customer profile, pricing stance, and competitive claims you defend). Agent comfort ([Create an agent from scratch](/tutorials/create-an-agent-from-scratch), [Give your agent its job description](/tutorials/give-your-agent-its-job-description)). Helpful: factual call prep ([Prep for your next sales call](/tutorials/prep-for-your-next-sales-call)), inbound motion ([Triage and follow up on inbound leads](/tutorials/triage-and-follow-up-on-inbound-leads)).
You'll end up with One **Pitch Rehearsal** agent — persona cards + rules of engagement — plus a completed **three-round rehearsal** transcript you tagged **FIX / WATCH / DROP** for your real pitch.

When a tutorial shows italic text in quotation marks, it usually mirrors a label or helper string inside Auxot. Product copy changes between releases — if something reads differently in your workspace, trust what you see on screen.

Callouts with a Worth knowing gold accent are meant as must-read context before you move on. Blockquotes that open with Tip are lighter, optional depth.

Why this matters

Call prep tells you who is in the room (Prep for your next sales call). It does not always rehearse how they fight back: budget freezes, security questionnaires mid-cycle, and “we tried AI and turned it off.”

A pitch-rehearsal agent runs deliberate role-play inside Chat: the agent adopts named personas, presses weaknesses in your story, and stops when you say stop. It is training (not prophecy); models exaggerate; you decide what deserves a script change versus noise.

Teams skip this because role-play feels awkward solo. An agent removes the scheduling tax: you still speak your pitch aloud or paste bullets; the personas answer as they might.

Nobody loses a deal on rehearsal alone — you run reps, you tighten claims (Ship clear customer communications helps keep voice disciplined).

Quick start

  1. Freeze facts — attach pricing bands, supported deployments, and honest limits: the pitch-rehearsal agent reads only context files (Add your first context file); forbid inventing SKU math.
  2. Mint Pitch Rehearsal — Admin Agent instructions:
    • Personas: CFO, Security, and Skeptical IC, rotate per round on demand.
    • Behavior: interrupt, ask for proof, and cite competitor shorthand; no personal insults; stay professional.
    • Output each round: Objections raised, Severity low/med/high, and Suggested counter-move; label counters draft: human verifies.
  3. Paste pitch skeleton — opener + three pillars + pricing framing: keep under ~200 words first pass.
  4. Run three rounds — tag personas explicitly: ROUND 1: CFO etc.; capture transcript.
  5. Debrief — sort objections into Fix messaging, Add FAQ context, and Engineering truth ticket; update Call Prep notes (Prep for your next sales call) same day.

Done? Pitch Rehearsal in picker; one rehearsal logged; at least one messaging patch merged.

The agent can do that?

1. Persona minting

Chat → Admin Agent:

Ideal-customer-profile bullets pasted: […]. Create three buyer personas — name, title, top fear, and success metric — markdown — tie fears to our product claims without inventing features.

Why it’s non-obvious: Generic hard customer lacks teeth; persona specificity surfaces real tensions after you paste the profile.

2. Adversarial rubric

We're scoring rehearsal harshness — propose 0-3 rubric dimensions — e.g. evidence demand, budget pressure, and security cynicism — table — include when to stop escalating same persona.

Why it’s non-obvious: Without scoring, reps confuse mean-spirited lines with useful prep; rubric calibrates difficulty you choose.

3. Talk-track patch list

Paste Pitch Rehearsal transcript excerpt — extract max five **talk-track edits** — each one bullet **Old phrase → New phrase — why** — no entire slide rewrite.

Why it’s non-obvious: Transcripts overwhelm; compression step yields actionable edits after you paste chaos.

Go deeper

Competitive ethics

Train personas on public positioning only: no fabricated competitor defects; cite sources in context files.

Inbound tie-in

Hot leads surface objections early (Triage and follow up on inbound leads): fold repeated objections into rehearsal personas quarterly.

Executive variants

Leadership-facing narratives differ (Brief leadership on your agent program): spawn separate short rehearsal for board-story stress.

Safety

If personas turn abusive, tighten instructions; parity with adversarial discipline (Red-team your agents against prompt injection) mindset without security jargon.

Walkthrough

Step 1: Context audit

Remove stale pricing: the rehearsal amplifies lies fastest.

Step 2: Voice check

Read opener aloud: paste transcript snippet optional; rhythm beats perfect prose.

Step 3: CFO round first

Money objections hardest: tackle fresh attention.

Step 4: Security round

Map worries to Answer vendor security questionnaires from your own evidence questionnaire themes when enterprise matters: still rehearsal only.

Step 5: Archive

Save transcript under sales wiki: date; link related CRM-mapping agent updates (Turn account research into CRM field updates) when objections revealed deal risks.

What’s next

Reference

Browse all tutorials