The Call Sheet

Authorized access only

15-minute first call

Discovery owns the first call. Demo expands on later calls. Objection handling is reactive — distributed across all beats, not a separate segment. Budget ~10–15% of responsive bandwidth without disrupting structure.

One rule above all: Discovery first. Don't pitch features until they've described their pain. Personalization = +40% demo conversion.

The 15-minute target is the structured backbone. Calendly books a 30-minute slot, so there's a full 15 minutes of headroom for prospect follow-up questions, deeper objections, or multi-thread setup. If the buyer is engaged and discovery surfaces real depth, let the call breathe — don't truncate to hit the clock. The goal is to land the math and the demo within 15 minutes so the remaining time is theirs.

Beat% of callMinutes
Open + rapport5%~1
Discovery + live ROI calculator (cost-of-inaction emerges during diagnosis)50%~7
Live product demo (Zendesk feed + synthetic tickets + console backup)30%~5
Outcomes + Close + Multi-thread15%~2
The discipline. The most common founder-led-sales failure is inverting this on the first call — jumping to demo at minute 5 because the founder is excited about the product. Resist. Discovery is what makes the demo land.

Verbatim — deliver in order, then move into §3

~45 seconds total. Senior buyers know who you are when they accept the meeting — don't over-credential. As soon as you get a one-sentence response from Beat 2, push to Beat 3.

1
Greeting + brief intro ~10 sec
"Hi [Name] — good to meet you. Ron Paraison. Thanks for making time."
Don't over-credential.
2
One pre-call hook ~15–30 sec · skippable
ONE specific touchpoint from pre-call research. Skip the beat entirely if you don't have a real hook — generic small talk does more damage than no small talk.
LinkedIn (most reliable):
"Saw on LinkedIn you've been at [Company] about [X] years — how's [the eCom side / your queue / the team] handling [recent context] this year?"
Company news:
"Saw the news about your [Q3 raise / product launch / new market] — congrats."
Skip generic filler: "how's your week?", weather/traffic/sports, long compliments.
3
Bridge to business ~5 sec
"Alright — should we jump in?"
4
Upfront contract / agenda ~30 sec
"Thanks for jumping on the call. I'd like to start by asking about your queue with a calculator open so we can quantify what your current state actually costs. Then I'll show you the Agent Control Plane working live on my own support desk — three real ticket scenarios, no slides. From there, if there's a fit, we figure out the next step together. Sound fair?"
Wait for verbal consent before sharing screen. Then open paraison.io/roi and pivot to §3.

Diagnostic, not sales weapon (~7 min)

Have paraison.io/roi open on your shared screen from the start. Type her numbers in real time as she answers. Cost-of-inaction emerges naturally as her current monthly spend appears on screen — you don't have to pitch it.

Framing line before you share screen: "I'm going to keep a calculator open while we talk so I can work through your numbers in real time." Get verbal consent before sharing.

SPIN questions, mapped to calculator fields

Eight questions in SPIN order, two per beat. Type her answers into the calculator as she gives them. By the end of discovery, she will have watched her current annual spend appear, and the savings/payback math will be visible — without you having to "reveal" anything.

Situation → type Monthly Tickets into calc
"What's your monthly ticket volume, and what's the trend over the last six months?"type volume immediately
"What does routing look like today — Zendesk groups + triggers, custom triage app, manual?"
Problem → type Manual Cost per Ticket into calc
"What's your loaded cost per ticket? If you don't know, we can use a conservative $22 default."type manual cost; current annual spend now visible
"What's your current deflection rate? Where are agents spending time they wish they weren't?"
Implication → set Tier 0 Deflection % to her current low rate (cost-of-inaction moment)
"If volume doubles in eighteen months, how does the team grow?"let the current annual spend number sit visible — this is the cost of doing nothing
"What does a Tier 1 ticket cost you when it should have been Tier 0?"
Need-payoff → set Tier 0 Deflection % to a conservative projection (30%); savings appear
"If you could deflect thirty percent of your tickets at sixty-five cents each, what would that mean for your budget?"slide deflection to 30%; net savings + payback now visible
"What would the right ACP outcome look like, from your perspective?"
Stress-test before leaving the calc: drag deflection down to 10%. "Even at ten percent — way below industry — you're still positive ROI inside the first month. The platform fee is flat, so the math survives stress."
Close discovery with: "Who else needs to be in this conversation before we move forward?" — locks in multi-threading.

Then pivot to demo: "Now let me show you how those deflections actually happen."

Zendesk + synthetic tickets + operator console (~5 min)

After discovery, show — don't tell. This is the segment most vendors can't deliver because their demo is a sandbox or a pre-recorded video. You'll fire actual tickets at the live tenant during the call and let her watch real classification, real routing, real timing end-to-end.

Setup before the call

  1. Three pre-loaded Zendesk API curl commands — one per bucket (Tier 0, Tier 1, VIP). Creates a real Zendesk ticket → fires the Zendesk webhook → ACP classifies → ACP writes back routing + reply. End-to-end pipeline visible in Zendesk in ~5–7 seconds. Payloads in §5.
  2. Fallback screenshots for each bucket — if Anthropic API is slow mid-demo, you don't watch dead air.
  3. Zendesk view bookmarked — sorted newest-first, refreshed in a tab.
  4. console.paraison.io — pre-logged-in to paraison_internal tenant.
  5. Tenant scan — eyeball the visible ticket history before sharing screen; nothing in the test data should expose anything that shouldn't be visible to a prospect.

The 90-second opener (talk track)

Verbatim
"The Agent Control Plane — ACP for short — looks at every ticket and sorts it into one of three buckets:

VIP tickets — high-value accounts tagged in your Zendesk. Bypass automation entirely; route directly to a senior agent. Deterministic, no model decides.
Tier 0 — inbound matches a KB article you already approved. ACP synthesizes a reply from your approved content; you set the confidence threshold per category. This is where the deflection economics come from.
Tier 1 — doesn't match a KB. ACP classifies into your existing Zendesk groups and routes — same workflow your team already runs, but with routing decisions logged and confidence scored.

Anything the classifier isn't confident about queues for human review. Let me show you live."

Live demo (~3.5 min)

1

Fire a Tier 0 test ticket

~1 min

"Let me show you Tier 0 end-to-end." Run the Zendesk API curl. Tab to Zendesk. Watch the sequence land in real time:

  • Ticket appears (within 1 sec)
  • Internal note appears with category + confidence + matched KB article (~2–4 sec)
  • Public reply appears (AI-generated from the approved KB content)
  • Status changes to Solved
"This is the ticket your team never had to touch — five seconds, end-to-end."
2

Fire a Tier 1 test ticket

~45 sec

"Now one that doesn't match KB." Run the curl. Watch:

  • Ticket appears
  • Internal note appears with category + confidence + routing rationale
  • Group assignment updates to the correct Zendesk team
  • Status stays open, assigned and waiting
"Routed in seconds; reasoning logged. Your agent picks up where ACP left off."
3

Fire a VIP test ticket

~45 sec

"Now a VIP-tagged ticket — different path entirely." Run the curl with a VIP requester. Watch:

  • Ticket appears with VIP tag visible
  • Internal note: "VIP override — bypassing classifier"
  • Assignment lands directly on a senior agent
"ACP didn't try to classify this. Your VIP tagging forced human review by design."
4

Console as the "why" backup

~1 min · when asked

Buyer will often ask "how do I see WHY ACP decided that?" Pivot to console.paraison.io, pull the acp_decisions row matching the most recent trace_id, walk the captured fields: category, confidence, predicted agent, action taken, timestamp.

"Every decision is replayable, exportable. Your governance team can audit on demand."
If something fails mid-demo: Don't watch dead air. Pull up the matching fallback screenshot, narrate as if it were live: "Here's what just happened on my end — let me show you the ticket that landed." Keep moving. The buyer remembers the narrative, not the latency.
Reset for close: "That's the system end-to-end. You saw the math during discovery, you saw the system just now. Let me lock in the next step." Pivot to outcomes + close.

The three pre-loaded commands

Export your Zendesk creds once per terminal session. Auth format is email/token:API_TOKEN — the literal string /token follows the email (Zendesk-specific Basic Auth).

Requester gotcha. Without an explicit requester block, Zendesk defaults the requester to the authenticated user — every ticket would show as from Ron Paraison, which a prospect will spot in two seconds. Each payload below sets a synthetic end-user on paraison-ai.io (plus-aliases route back to your inbox if anything auto-replies). "tags":["demo"] filters these out of real KPI rollups. Edit subject/body to match a real KB topic in paraison_internal before the call.
# Export once per terminal session
export ZD_SUBDOMAIN="paraisonai"        # your Zendesk subdomain
export ZD_EMAIL="ron@paraison.io"       # auth user
export ZD_API_TOKEN="..."               # Zendesk Admin → Apps & integrations → APIs

# Tier 0 — matches a KB article, ACP replies from approved content
curl -sS -u "$ZD_EMAIL/token:$ZD_API_TOKEN" \
  -H "Content-Type: application/json" \
  "https://$ZD_SUBDOMAIN.zendesk.com/api/v2/tickets.json" \
  -d '{"ticket":{"subject":"How do I reset my password?","comment":{"body":"I forgot my password and need to log back in. How do I reset it?"},"requester":{"name":"Avery Demo","email":"ron+avery.demo@paraison-ai.io"},"tags":["demo"]}}'

# Tier 1 — no KB match, ACP classifies + routes to the right Zendesk group
curl -sS -u "$ZD_EMAIL/token:$ZD_API_TOKEN" \
  -H "Content-Type: application/json" \
  "https://$ZD_SUBDOMAIN.zendesk.com/api/v2/tickets.json" \
  -d '{"ticket":{"subject":"Webhook payloads arriving out of order","comment":{"body":"Our processing pipeline expects sequential events but ~3% of webhooks arrive late and out of order over the past week. Can you confirm whether there is queue contention on your side?"},"requester":{"name":"Jordan Demo","email":"ron+jordan.demo@paraison-ai.io"},"tags":["demo"]}}'

# VIP — tagged ticket bypasses classifier, lands on a senior agent
curl -sS -u "$ZD_EMAIL/token:$ZD_API_TOKEN" \
  -H "Content-Type: application/json" \
  "https://$ZD_SUBDOMAIN.zendesk.com/api/v2/tickets.json" \
  -d '{"ticket":{"subject":"SSO down for our org","comment":{"body":"Our SSO integration is down. CISO is asking for an incident report."},"requester":{"name":"Casey Demo","email":"ron+casey.demo@paraison-ai.io"},"tags":["enterprise","demo"]}}'

VIP trigger tags (any one forces VIP path): vip · enterprise · priority_account · premium · key_account · gold · platinum

One-time hygiene step. First time you fire these curls, Zendesk creates three end-user records (Avery / Jordan / Casey Demo). Open Admin Center → People → End users, find each one, and disable any trigger that auto-emails the requester so the prospect doesn't see "[Zendesk] Your ticket was received" bouncing through your mailbox mid-demo.

Nine outcomes — five lead, two risk reducers, two reserves

Memorize the five "lead" outcomes — you'll use these on every Maya call. The other four are tiered for specific moments (risk hesitation, governance review, CFO depth on demand).

Lead outcomes — drill cold, use on every Maya call

01

Routing accuracy improvement

Tier 1→Tier 2 escalations drop because tickets land in the right team the first time. Misroutes from her existing triage logic get absorbed by the classifier; operator corrections are logged and ACP learns from them.

02

Agent time freed for resolution

Less triage drudgery, less context-switching. Agents spend their minutes on resolution, not routing — the front of the workflow compresses, average handle time comes down.

03

Deflection lift on the easy stuff

Net $21.35 saved per Tier 0 ticket the RAG path absorbs. Even at a conservative 10% deflection — well below her likely real number — the math is positive in month one.

04

OPEX, not headcount

Per-resolution lives in OPEX. Not a headcount story, not a layoff story. Cost-reduction without HR risk — passes budget committees even in a hiring freeze. Lead with this when Marcus joins.

05

Speed to value — live in three business days

From completed intake to operational tenant in three business days. Her team gets the routing accuracy + agent time + deflection lift within the same week, not the same quarter.

Risk reducers — volunteer only if she hesitates

06

No customer-facing outage if ACP goes down

Sits above Zendesk, not in front of it. If we go dark, her queue keeps moving in Zendesk exactly as it did before ACP.

07

Month-to-month, cancel anytime

Thirty days notice on either side. If we raise the rate, she walks free — no termination fees, no minimum commitment.

Hold in reserve — only if discovery surfaces the specific need

08

Per-category auto-thresholds

For the "I don't trust automation yet" concern — gradual trust-building.

09

Full audit trail in acp_decisions

For CIO/governance review — cluster with security brief, not a lead outcome.

Three-beat short answers

Three beats, not two: punchline (answers the literal question), frame (mechanism that makes the punchline true), bridge (ties back to an outcome she felt during discovery). The bridge keeps the rebuttal from being purely defensive — it forwards the deal.

#1Payback under six months
Punchline"Inside the first billing cycle."
FrameSixty-five cents per resolution vs. your twenty-two-dollar loaded handle cost nets you twenty-one dollars per Tier 0 deflection. Even at ten percent deflection — way below industry — you're positive ROI inside month one.
Bridge"And after payback, your agents get those minutes back every day, every ticket."
#2Implementation bandwidth
Punchline"Implementation isn't your team's job."
FrameIt's mine, and it's automated. Three business days from completed intake to live tenant. One-hour kickoff with one analyst is the only synchronous step.
Bridge"Once it's live, those same overloaded agents stop spending fifteen minutes per ticket on triage they hate doing."
#3Three AI vendors this month — why you?
Punchline"Don't take my word — watch it work, live, end-to-end."
FrameEvery other vendor shows you a curated demo on a sandbox environment they control. I'll fire actual tickets at the live tenant during this call — classification, routing, and timing in real time. If anything misroutes, you'll see that too.
Bridge"Most vendors won't let you watch the classifier in flight because their demo is staged. Mine isn't."
#4HITL rubber-stamp / liability
Punchline"ACP replies from your approved KB, or routes to your team."
FrameACP only auto-replies when the ticket matches a KB article you already approved. It can't say something your team didn't write. Anything the classifier isn't confident about queues for human review.
Bridge"No liability surprises, and your agents only see what the classifier was confident about — less low-confidence rework noise."
#5Contract floor on $0.65
Punchline"No contract floor, because no contract lock."
FrameMonth-to-month, thirty days notice either side. If we ever raise the rate, you walk free. No termination fees, no minimum commitment.
Bridge"Practically, once you're seeing deflection lift, the contract becomes academic — you stay because the OPEX delta is too big to leave."

Read once before the call

Don't pitch features. Pitch outcomes. Features only when they ask.
End every answer on motion. "Send me…", "Watch this…", "Let me share my screen…" Never trail off.
Multi-thread on the call. Ask who else needs to be in the next conversation before closing.
Book the next call before this one ends. Don't leave the buyer thinking about timing.
Discovery is what makes the demo land. If the buyer skips discovery and demands a demo, push back gently: "Can I ask three questions first so the demo is on your numbers, not mine?"