How do agents orchestrate — and what instruments verify the work?
AGENT & INSTRUMENT DIAGRAM: SALES DEV AGENT
════════════════════════════════════════════════════════════
AGENTS (Yang — who applies force)
─────────────────────────────────────────────────────────
Sales Dev Agent ··· Prospect research, scoring, drafting, sequencing
Founder (Human) ··· Review, personalize, send, discover, close
RFP Agent ········· Proposal generation (A2A handoff at Proposal stage)
INSTRUMENTS (Yin — what verifies and rewards)
─────────────────────────────────────────────────────────
SPCL Gate ········· Outreach quality score (>3.5 to pass)
Lead Scorer ······· ICP fit ranking (Hot/Warm/Cold routing)
Explore-Exploit ··· Channel + message optimisation (doubles down on what converts)
CRM Pipeline ······ Deal progression tracking (stage transitions)
Kill Date Counter · Time pressure instrument (28 days → decision forced)
PROTOCOLS (data + value + decision flows)
─────────────────────────────────────────────────────────
┌──────────────────────────────────────────────┐
│ OUTREACH WORKCHART │
│ │
│ RESEARCH ──→ SCORE ──→ COMPOSE ──→ │
│ │ │ │ │
│ │ Lead SPCL │
│ │ Scorer Gate │
│ │ │ │ │
│ ──→ SEQUENCE ──→ MEASURE ──→ │
│ │ │ │
│ Explore- Compound │
│ Exploit Rate │
│ │ │ │
│ └── FEEDBACK ┘ │
│ │ │
│ Improves next cycle │
└──────────────────────────────────────────────┘
FEEDBACK LOOPS
─────────────────────────────────────────────────────────
Loop 1: QUALITY (per message)
┌─ Compose → SPCL Gate → Score < 3.5? → Rewrite → Compose ─┐
└────────────────────────────────────────────────────────────┘
Loop 2: ROUTING (per prospect batch)
┌─ Score → Route → Send → Measure → Explore-Exploit → Score ┐
└────────────────────────────────────────────────────────────┘
Loop 3: LEARNING (weekly)
┌─ Dashboard → What converted? → Update ICP model → Research ┐
└─────────────────────────────────────────────────────────────┘
Loop 4: KILL DATE (monthly)
┌─ 50 messages, 0 replies? → Diagnose → Pivot ICP or message ┐
│ Past kill date? → Decision: extend with evidence or stop │
└─────────────────────────────────────────────────────────────┘
A2A HANDOFF
─────────────────────────────────────────────────────────
Sales Dev Agent RFP Agent
────────────── ─────────
Research → Score → → Proposal gen
Compose → Sequence → [A2A at → AI auto-fill
Discovery call → Proposal → Answer gen
Deal created stage] → Deck composition
HORIZON FLOW
─────────────────────────────────────────────────────────
H1: Sales Dev Agent (this PRD)
│ outreach data, reply patterns, qualification outcomes
▼
H2: Sales Process Optimisation
│ 4-layer ICP scores, workflow dispatch, routing rules
▼
H3: Trust Commerce
warm referral leads pre-qualified by trust graph
════════════════════════════════════════════════════════════
Agent Roster
| Agent | Type | Force Applied | Verification |
|---|---|---|---|
| Sales Dev Agent | AI | Research, score, draft, sequence, log, optimize | SPCL gate, lead scorer, explore-exploit |
| Founder | Human | Review, personalize, send, discover, negotiate, close | Go/No-Go on every message, deal judgment |
| RFP Agent | AI | Proposal gen, auto-fill, answer generation | A2A handoff protocol, RFP quality score |
Instrument Registry
| Instrument | Measures | Threshold | Action on Fail | Outcome Map Link |
|---|---|---|---|---|
| SPCL Gate | Message quality | Score > 3.5 | Rewrite before human review | Enables O2 (reply rate) |
| Lead Scorer | ICP fit | Hot > 80%, Warm 50-80%, Cold < 50% | Route to appropriate channel treatment | Enables O1 (10+ prospects/week) |
| Explore-Exploit | Channel + message effectiveness | Conversion improvement per cycle | Shift budget to what converts | Enables O2 (reply rate) |
| CRM Pipeline | Deal progression | Stage transitions with evidence | Escalate stale deals | Measures O3 (20 scored contacts) |
| Kill Date Counter | Time to deadline | 28 days remaining | Force decision: extend or stop | Guards all outcomes |
| Outcome Dashboard | All 4 success measures | O1 ≥10/wk, O2 ≥15%, O3 ≥20, O4 ≥90% | Weekly review: diagnose which loop is broken | Measures O1-O4 directly |
Feedback Loop Quality
| Loop | Frequency | Sensor | Actuator | Latency |
|---|---|---|---|---|
| Quality | Per message | SPCL score | Rewrite trigger | Minutes |
| Routing | Per batch (weekly) | Reply/open rates | Explore-exploit channel shift | Days |
| Learning | Weekly | Dashboard aggregates | ICP model update | 1 week |
| Kill Date | Monthly | Cumulative results | Pivot or stop decision | 30 days |
Activation Sequence
From the Dependency Map — when does each agent come online?
| Phase | What Resolves | Agent State | Human Covers |
|---|---|---|---|
| Now (Track 3) | Nothing needed | Agent: offline | Human does all research, scoring, drafting, sending manually |
| Sprint -1 (3d) | Resend env vars, LinkedIn OAuth | Agent: email + LinkedIn channels live | Human still researches and drafts, but channels are wired |
| S1-S2 (5d) | Prospect Research, Lead Scoring | Agent: can research and score | Human reviews scores, still drafts messages |
| S3-S4 (6d) | Outreach Composer, Follow-up Sequencer | Agent: full outreach pipeline | Human reviews and approves, agent handles the rest |
| S5-S6 (3d) | WorkChart, Dashboard | Agent: orchestrated + measured | Human focuses on discovery calls and closing |
The agent doesn't replace the human in one step. Each sprint transfers one bottleneck from human to agent. The Capability Map P1 gaps (Prospect Research, Outreach Composer) are the first two transfers.
Gate
Before executing:
- Every agent named — YES (3 agents: Sales Dev, Founder, RFP)
- Every instrument named — YES (6 instruments with thresholds and outcome map links)
- Feedback loops explicit — YES (4 loops at different frequencies)
- Agent-to-agent handoffs documented — YES (A2A at Proposal stage)
- Horizon data flows declared — YES (H1 → H2 → H3)
- Activation sequence links dependency resolution to agent capability — YES (5 phases)
Context
- Capability Map — Previous: what can we do
- A&ID Template — The empty pattern
- Spec: Protocols — WorkChart detail, routing logic, build sequence