Synthesis Build

Synthesis — Build (Phase 1 White Space → Phase 2 Founder Fit → Phase 3 Merge) — FINAL stage

This is the last stage of the free pipeline. It fuses three jobs that MUST stay ordered:

1. Phase 1 — IDEATE (white space): write 4-5 genuinely unconventional white-space tactics in full, IGNORING founder constraints (exploration mode).
2. Phase 2 — ADAPT & GENERATE (founder fit): review the Phase-1 tactics and adapt for founder constraints preserving the unconventional core, then generate 4-5 more from the synergy + founder-fit pools.
3. Phase 3 — MERGE: merge into a final synthesis of 7-9 total tactics (target 50%+ unconventional).

It produces a portfolio of novel demand-gen tactic IDEAS and stops. (Prioritization, implementation guides, and the proprietary 576-vector DB are the paid product — do not attempt them here.)

Vector definitions come from growth-factors.json; pools/anti-patterns from synthesis-constraints.json; the validated emergent mechanisms come from synthesis-explore.md. Do NOT read tactics_DB/ (clean-room — no proprietary anti-vectors DB; use the lite anti_patterns field instead).

The three phases are WALLED — do them strictly in order

You MUST write the Phase-1 white-space tactics in FULL before you adapt anything in Phase 2. You have NOT earned the right to reject a tactic for impracticality during Phase 1 — that is Phase 2's job. The output PROVES the ordering held: the ## Pass 1 Disposition table (Phase 2) can only dispose tactics that Phase 1 already wrote in full. If you catch yourself filtering a Phase-1 tactic for "the founder can't do this," STOP — that belongs in Phase 2.

Inputs & Output

• WS/03-think-tanks/demand-generation/synthesis-explore.md (PRIMARY — the validated emergent mechanisms + blind combinations; Phase 1 ideates from these + diverse_white_space)
• WS/03-think-tanks/demand-generation/synthesis-constraints.json (diverse_white_space; pools B_synergy + C_founder_leverage; anti_patterns; category_diversity_requirements)
• WS/03-think-tanks/demand-generation/growth-factors.json (vector definitions)
• WS/01-diagnostics/founder-input.md (Phase 1 READS but does NOT filter by constraints; Phase 2 applies them; goal + deadline)
• WS/02-enrichment/audience-jtbd.md, WS/02-enrichment/competitors-analysis.md
• Think-tank context: competitor-gaps.md, platform-arbitrage.md (channel selection, structural advantage), cross-industry.md (transferable mechanisms / adaptation angles for the new Phase-2 synergy + founder-fit tactics)
• ${CLAUDE_PLUGIN_ROOT}/reference/Marketing-Channel-Menu-2026.md (bundled channel menu)
• OUTPUT: WS/03-think-tanks/demand-generation/synthesis.md

═══════════════════════════════════════════════════════════════════════════

PHASE 1 — IDEATE (white space; IGNORE founder constraints)

═══════════════════════════════════════════════════════════════════════════

Generate 4-5 tactics exclusively from diverse white-space combinations — vector pairs that are novel for this run and exclude over-represented "content-flywheel"-type vectors. This phase prioritizes unconventional exploration over practicality and IGNORES founder constraints (Phase 2 applies them).

Philosophy: Exploration Mode

Mindset: "What interesting mechanisms emerge from these never-combined vectors?" / "What would a founder do with unlimited resources?" — NOT "can this founder do this?" The goal is to discover unconventional approaches Phase 2 can refine or preserve. Write all 4-5 tactics in FULL here, before any adaptation.

Scope Enforcement — DEMAND GENERATION ONLY

Before generating ANY tactic: "Does this bring NEW PEOPLE to the site who've never heard of the product?" YES = include; NO = delete (CRO territory).

Engineering-as-marketing: allowed but scoped. Building things to ATTRACT new users is valid demand gen, but the tactic's PRIMARY purpose must be acquisition, not product improvement. Test: if you removed the distribution/acquisition channel, would the remaining work be on the product roadmap anyway? If YES → not demand gen.

Process (Phase 1)

1. Load diverse white space from synthesis-constraints.json (diverse_white_space). These are pre-filtered to exclude content-flywheel-type vectors and limit repetition (max 2 per anchor). Display the loaded pairs in a table. Category awareness: aim for ≥2 different category prefixes across your 4-5 tactics (soft target here; Phase 2 applies the per-prefix minimums from category_diversity_requirements, which are built to be satisfiable within 7-9 tactics of 2-3 vectors — if a minimum is still unreachable, say so explicitly in the disposition rather than silently missing it).
2. For each combination, derive the emergent mechanism (reuse/extend the matching synthesis-explore.md mechanism where one exists): "What UNUSUAL capability emerges?" It must differ from what either vector produces alone and feel uncomfortable/counterintuitive. Do NOT consider whether the founder can execute it.
3. Design a complete tactic from each mechanism. Name it per the naming rule in ${CLAUDE_PLUGIN_ROOT}/reference/writing-style.md: plain words that tell a smart friend what you'd actually do — what you do + the twist — with the unconventional mechanism visible in the name (not generic marketing, and not an invented codename either). No practicality filtering — include tactics even if they need skills/budget the founder lacks or feel risky.

Kill List (still applies in exploration mode)

Skip combinations whose core action is: start a newsletter · write SEO content · build community (join Discord/Slack) · demo the product · interview customers · improve the core product · re-engage churned users · upgrade existing customers · improve onboarding · build a tool/dashboard/calculator (engineering, distribution as afterthought) · create a feature and announce it · develop an integration. If the white-space pair only produces a kill-list action, it didn't yield anything novel — skip it.

Self-Audit (per Phase-1 tactic)

1. Remove all vector references — does the tactic still sound unusual? NO → vectors are labels on a conventional action (regenerate from a different pair).
2. Day-1 action on the Kill List? YES → kill & regenerate.
3. Marketer Test — would a B2B marketer recommend this unprompted? YES → too conventional, reconsider.
4. Cannibalization Test — does it teach customers to DIY what the product does? YES → reframe (emphasize the PAIN of manual methods, don't teach the method).

Phase-1 gate: 4-5 white-space tactics, each from a diverse_white_space pair (IDs exist in growth-factors.json), each passing all 4 self-audit tests, 100% unconventional target, demand-gen only. Carry a one-line Practicality Assessment per tactic (Difficulty / Resource intensity / Risk / Phase-2 action: Preserve / Adapt / Consider dropping) so Phase 2 can act.

═══════════════════════════════════════════════════════════════════════════

PHASE 2 — ADAPT & GENERATE (founder leverage; ≥60% of Phase 1 PRESERVED)

═══════════════════════════════════════════════════════════════════════════

Philosophy: Preserve the Unconventional Core (CRITICAL)

The #1 goal of Phase 2 is to PRESERVE Phase-1's unconventional mechanisms. What makes a tactic unconventional: the positioning (contrarian / anti-establishment), the structural advantage (competitor lockout, platform arbitrage), and the uncomfortable edge that makes traditional marketers hesitate.

When adapting for constraints: DO reduce budget/time, simplify execution, scale down scope — while keeping the uncomfortable positioning, the structural advantage, and the contrarian angle. DON'T soften the move itself to make it "safer," replace a structural advantage with an execution advantage, sand down the edge that creates the lockout, or drop a tactic because the founder hasn't done it before — unfamiliarity is not a constraint. The unconventional POSITIONING must survive adaptation — and per the naming rule (Output language below), it survives in PLAIN WORDS: the uncomfortable move stays visible in the name; the edge lives in the mechanism, never in invented vocabulary.

• BAD: "Call Out Enterprise Tools by Name in Your Docs" → "Technical Citation Authority" ❌ (the confrontation vanished → lost the lockout)
• BAD: "Anti-Enterprise Citation Rebellion" ❌ (edge hidden behind a codename — a smart friend can't tell what you'd do)
• GOOD: "Call Out Enterprise Tools by Name in Your Docs (Lean Version)" ✅ (the uncomfortable move is right in the name; only budget/time reduced)

Aim for ≥60% Phase-1 preservation with unconventional edges intact.

Phase 2a: Review Phase-1 Tactics (PRESERVE / ADAPT / DROP)

A skill the founder would need to LEARN is NOT a reason to drop. State the learning cost honestly (time to competence, quality of first attempts) and keep the tactic. Founders will learn any channel that brings customers — unfamiliarity is not a constraint.

Timeline gate: if a structural-advantage timeline (6-24 mo) exceeds the founder's deadline by >3x AND the founder has a ≤90-day deadline → ADAPT so the tactic produces observable acquisition signal (traffic/signups/trials) within the deadline, even while the moat builds over time. If it fundamentally can't signal within 3x the deadline → DROP.

Adaptation rules: budget too high → reduce scope, not approach; skill missing → state the learning cost honestly (time to competence, quality of first attempts) and KEEP the tactic — a founder will learn any channel that brings customers; time-intensive → phase it; positioning feels risky → KEEP IT (the risk IS the advantage).

DROP threshold: at most 2 Phase-1 tactics dropped (preserve ≥60%).

Channel-justification rule. For each tactic, the Primary Channel choice must be justified against the mechanism — explain WHY this channel amplifies THIS mechanism (not just "the founder can do content"). If the mechanism would work equally on any channel, the channel choice is arbitrary — pick the one with the lowest competitive adoption from the matrix. The channel shapes the execution steps; it is a design input, not a label.