/synthesis-explore

name: synthesis-explore
description: Synthesis EXPLORE stage for the Diffmode growth-tactics pipeline (fuses the blind-combination draw + emergent-mechanism derivation — formerly two separate synthesis steps — into ONE structural-check-only stage). Reads the per-run growth-factors.json (LIGHT vector DB) + synthesis-constraints.json + founder-input + audience-jtbd + the 3 think-tank reports; draws vector combinations BLIND (IDs only, before any analysis), runs the Stripped Core Action Test + prohibited-combination + must_include checks, then derives the NOVEL MECHANISM that EMERGES from each (Reframing Test, structural-advantage classification, 3-step prototype, verb-group dedup). Outputs synthesis-explore.md — 15-20 blind combinations + 12-18 validated mechanisms, NO tactic names. Feeds synthesis-build.
metadata:
  version: "1.0.0"

Synthesis — Explore (Phase 1 Blind Combinations → Phase 2 Emergent Mechanisms)

This is the FIRST synthesis stage. It fuses two jobs that MUST stay ordered: **Phase 1** draws vector combinations BLIND (vector-first, before any tactic exists), and **Phase 2** derives the NOVEL MECHANISM that emerges from each combination. Vector-first thinking is the novelty engine: you commit to combinations BEFORE knowing what tactic they might produce, which is how you escape conventional playbooks. **Output: 15-20 raw vector combinations + 12-18 validated mechanisms. NO TACTIC NAMES. NO EXECUTION STEPS.** (Tactic design is synthesis-build's job.)

Vectors and their definitions come from the per-run `growth-factors.json` (the LIGHT DB). Do NOT read `tactics_DB/` (clean-room — moat-critical). The category structure and `{prefix}-NNN-slug` ID format are shared conventions; the specific IDs are whatever this run mined.

The two phases are WALLED — do them strictly in order

**You MUST complete Phase 1 (blind draw + combinations) in FULL before starting Phase 2 (mechanisms).** The output must physically PROVE this ordering: the section `## Blind Draw (IDs only)` must precede `## Vector Combinations`, which must precede `## Validated Mechanisms`. If you catch yourself deriving a mechanism (Phase 2) before the blind draw and combinations (Phase 1) are written, STOP — you have broken the wall; go back.

Inputs & Output

The invoker provides (do not hardcode absolute paths):

• `WS/01-diagnostics/founder-input.md`
• `WS/03-think-tanks/demand-generation/growth-factors.json` (LIGHT vector DB — vector IDs,

categories, mechanisms, transferability, saturation_risk)

• `WS/03-think-tanks/demand-generation/synthesis-constraints.json` (mandatory pools, white

space, prohibited combinations, category diversity)

• `WS/02-enrichment/audience-jtbd.md` (trigger events + emotions)
• Think-tank context (use if present): `WS/03-think-tanks/demand-generation/cross-industry.md`

(transferable mechanisms worth combining), `competitor-gaps.md` (open channels/segments), `platform-arbitrage.md` (emerging-platform timing windows)

• **OUTPUT**: `WS/03-think-tanks/demand-generation/synthesis-explore.md`

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

PHASE 1 — BLIND VECTOR COMBINATIONS (no tactics, no execution)

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

Force exploration of vector combinations WITHOUT thinking about tactics yet. **Output of this phase: 15-20 raw vector combinations with synergy rationale. NO TACTIC NAMES. NO EXECUTION STEPS.**

Critical Rules

**YOU MUST NOT:** name tactics · describe execution · pick channels · think "what marketing to do" · generate combinations that produce CONVENTIONAL outcomes.

**YOU MUST ONLY:** explore vector synergies · explain WHY vectors combine · identify white space · document founder leverage · **REJECT combinations that produce conventional marketing.**

If you find yourself writing a tactic name or execution step, STOP and delete it.

Conventional Outcome Detection (BLOCKING)

Some combinations ALWAYS produce conventional outcomes regardless of framing. REJECT them before they reach Phase 2.

**The Mechanism Preview Test** — before accepting a combination, ask: > "If I combine these vectors, what mechanism results, in plain English?" > If it sounds like standard marketing advice, REJECT.

**Apply `synthesis-constraints.json` → `prohibited_combinations`.** Those are theme-level rules (e.g. customer-research + content-flywheel = "talk to customers, write content"; build-demo + share = "build demos and share them"; community-join + audience-borrowing = "join communities and participate"; content-flywheel + any SEO vector = "write content to rank"; behavioral-cohort + content-funnel = "segment and optimize"). Any pair whose mined vectors match a prohibited theme is REJECTED.

**What makes a combination UNCONVENTIONAL** — its mechanism (1) a marketer would advise AGAINST ("that's risky/unusual"), (2) competitors structurally CAN'T copy (not just won't), (3) exploits a timing window (first-mover in an emerging space), or (4) requires a specific founder constraint (solo founder can do what enterprise can't).

**The Replacement Rule** — don't skip a conventional pair, REPLACE it: keep ONE vector, swap the other for a partner (ideally an `unconventional_anchor` from the constraints file) that produces an unconventional mechanism; re-run the Mechanism Preview Test.

Blind Vector Selection (BEFORE ANY ANALYSIS)

Complete this BEFORE reading enrichment deeply or thinking about tactics — commit to combinations blind. Draw from the three mandatory pools in `synthesis-constraints.json`, listing ONLY vector IDs (no descriptions/previews yet), into the output's `## Blind Draw (IDs only)` section:

• **Pool A — White Space (5):** from `diverse_white_space` / `mandatory_combinations`

pool `A_white_space`.

• **Pool B — Cross-Category Synergy (5):** from `mandatory_combinations` pool `B_synergy`

(one per high-synergy category pair).

• **Pool C — Founder Leverage (5):** from pool