← Sales Development Agent · Prompt Deck · Pictures

How do we think slowly so the agent gets smarter and the outreach gets cleaner each cycle?

Intent Contract​

Agent autonomy boundary. Not parsed by engineering — governance instrument for humans and agents.

Build Contract​

The deliverable. Engineering builds from this. Commissioning reads this. Every row has an acceptance test.

Job: Research and Score Prospects​

Job: Compose Personalized Outreach​

Job: Deliver Through Channels​

Job: Learn What Converts​

Job: Agent Identity and Orchestration​

Principles​

What truths constrain how this agent operates?

The Job​

Hidden objection: "AI outreach feels spammy." Agent composes — human reviews every message before send. Research is automated, relationships are not.

Why Now​

The product is ready. The demand generation isn't. Nine algorithms, four adapters, a CRM, an RFP tool — all built, none generating demand. The outreach IS the commissioning test.

The convergence: Eddy Whatt at Sneakers Media identified the same pattern from the buy side. Every lead gen provider delivers volume, not quality.

OLD: Advertiser -> Agency -> Lead Gen Provider -> Database -> Leads (unqualified)
NEW: Advertiser -> Agent -> Pre-Qualified Leads (with conversation context)

The NZ angle: Small market (5M) makes lead gen quality critical. Relationship-based culture means bad leads damage agency reputation.

Design Constraints​

Performance​

How do we know it's working?

Priority Score​

PRIORITY = Pain x Demand x Edge x Trend x Conversion

Quality Targets​

Functional:

Outcome (Kill: 2026-03-24):

Failure Budget​

Kill signal: 50 messages, 0 replies, 30 days — ICP or message is wrong. Diagnose with explore-exploit data before iterating.

Business Dev​

Platform​

What do we control directly?

Current State​

This agent is one instrument in the SPO orchestra.

Build Ratio​

~80% composition (Email, LinkedIn, CRM, Forecasting, Document Intelligence), ~20% new code (WorkChart orchestration, prospect research pipeline, channel dashboard).

Protocols​

How does the system coordinate?

Agent/Human Split​

AGENT (AI-Led + AI-Only)              HUMAN (Human-Led + Human-Only)
----------------------------          ----------------------------
Prospect research                     Discovery calls
Lead scoring + ranking                Relationship building
Outreach drafting                     Message review + send
Follow-up sequencing                  Deal negotiation
Activity logging                      Go/No-Go decisions
Channel optimization                  Trust building

WorkChart​

RESEARCH -> SCORE -> COMPOSE -> SEQUENCE -> MEASURE
    ^                                        |
    +---- Feedback improves next cycle ------+

Build Order​

Commissioning​

Horizon Model​

HORIZON 1: PROVE (now -> 90 days)          <- THIS PRD
  Sales Dev Agent — one instrument
        | feeds
        v
HORIZON 2: ORCHESTRATE (90d -> 6 months)
  Sales Process Optimisation — the orchestra
        | generates data for
        v
HORIZON 3: PROTOCOL (6m -> 18 months)
  Trust Commerce — the protocol

Risks​

Agent-Facing Spec​

Commands:

pnpm nx serve stackmates        # Dev server
pnpm nx test stackmates          # Unit tests
pnpm nx e2e stackmates-e2e       # E2E tests

Boundaries: Always: research, scoring, draft composition. Ask first: new channel integration, ICP changes. Never: send without human review, delete CRM data.

Players​

Who creates harmony?

Demand-Side Jobs​

Job 1: Find Prospects Worth Talking To​

Situation: Pipeline empty, 3 hours to find 5 prospects, then equal time on high-fit and low-fit.

Features that serve this job: #1, #2

Job 2: Say Something Worth Reading​

Situation: Blank compose window, writing same ineffective message.

Features that serve this job: #3, #4

Job 3: Follow Up Without Forgetting​

Situation: Meant to follow up Wednesday, it's Friday, window closing.

Features that serve this job: #5, #6, #7, #8

Job 4: Learn What Converts​

Situation: Month of outreach, no idea what worked.

Features that serve this job: #9, #10, #11

Job 5: Pre-Qualify for Media Clients​

Situation: Every lead gen campaign: volume not quality. Client sales team complains. Agency absorbs blame.

Features that serve this job: #1, #2, #3, #5

ICP: NZ Media Agency​

Archetype. Sneakers Media exemplifies the segment.

Psycho-logic:

The real problem: Not "higher quality leads" — leads their client's sales team doesn't complain about. The complaint loop costs more than the CPL.

Revenue model: Pilot CPL ($20-100/lead) -> Platform competing with lead gen providers -> Partnership (media + creative + AI/data).

Two Deployment Contexts​

Same WorkChart, different jobs. One instrument, multiple ventures. BOaaS proven.

Role Definitions​

Relationship to Other PRDs​

Context​

• PRD Index — Sales Development Agent
• Prompt Deck — 5-card pitch
• Pictures — Pre-flight maps