---
name: lite-constraints
description: Generates synthesis-constraints.json for the Diffmode growth-tactics pipeline by reasoning in-context over the per-run growth-factors.json (LIGHT vector DB) + founder context — the clean-room, no-Python replacement for the proprietary Python constraints generator. Emits the white-space pairs, mandatory synergy/founder-leverage pools, prohibited (conventional-outcome) combinations, and category-diversity requirements that the synthesis chain reads. Use after growth-factors mining and before synthesis.
metadata:
  version: "1.0.0"
---

# Lite Constraints (synthesis constraints, no Python)

You produce `synthesis-constraints.json` — the file the synthesis chain reads to force
unconventional vector combinations and block conventional ones. In the paid pipeline this
is generated by the proprietary Python constraints generator reading the proprietary
intelligence layer (curated anchors + internal pair-scoring). Here you **reason in-context**
over the per-run `growth-factors.json` + founder constraints to emit the same JSON shape.
You drop the proprietary intelligence-layer scoring entirely — it was scaffolding for *how*
the script picked pairs, not a field the synthesis prompts consume.

## ⚠️ Clean-room rule

Build constraints **only** from this run's `growth-factors.json` + `founder-input.md`. Do
NOT read anything under `tactics_DB/`. **Every vector ID you reference MUST exist in this
run's `growth-factors.json`** — never invent IDs and never use IDs you remember from the
proprietary DB. Prohibited-combination rules are expressed at the **category / theme
level** plus generic conventional-outcome patterns (clean-room), not as proprietary
specific pairs.

## Inputs & Output

- **INPUT** (required): `WS/03-think-tanks/demand-generation/growth-factors.json` (the
  LIGHT DB — read its `vectors` and `metadata.category_counts`).
- **INPUT** (required): `WS/01-diagnostics/founder-input.md` (budget, team size, hours,
  unfair advantages, stage — to build the founder-leverage pool and bias selection).
- **OUTPUT**: write `WS/03-think-tanks/demand-generation/synthesis-constraints.json`.

## What the synthesis chain actually uses (build these fields)

1. **`diverse_white_space`** (explore + build read this) — 8-10 cross-category vector PAIRS that
   are genuinely unconventional and exclude over-represented "content flywheel"-type
   vectors. Each: `{ "vectors": [id_a, id_b], "reason": "<the emergent angle in plain
   English>", "source": "white_space" }`. Pick pairs whose mechanisms, when combined,
   would make a generic marketer say "that's unusual / risky" (not "obviously do that").

2. **`mandatory_combinations`** (explore + build read these pools) — a flat array; each
   item has a `pool`, `vectors`, `reason`, `priority`:
   - **Pool A — `A_white_space`** (5): the strongest 5 from `diverse_white_space`.
   - **Pool B — `B_synergy`** (5): high-synergy CROSS-CATEGORY pairs (e.g. Structural +
     Resource, Leverage + Positioning, Psychological + Leverage, Structural + Psychological,
     Resource + Positioning). `reason`: name the synergy type.
   - **Pool C — `C_founder_leverage`** (5): pairs that exploit what THIS founder HAS
     that's rare — their unfair advantages (technical skill, industry access, network,
     domain expertise, existing audience) — within their time and budget. Both vectors
     should be transferability "High"; at least one "Emerging". `reason`: name the asset
     it exploits.
   `priority`: `must_include` for A/B, `suggested` for C.

3. **`prohibited_combinations`** (Step 1's conventional-detection) — category/theme-level
   rules that always yield conventional outcomes, each `{ "pattern": "<theme A> + <theme
   B>", "vectors_if_present": [<any matching ids from this run, or []>], "reason": "<the
   conventional mechanism it produces>", "alternative": "<keep one vector, swap the other
   for an emerging/contrarian one>" }`. Always include these generic conventional patterns
   (map them onto whatever matching vectors exist this run):
   - "customer-research/personal-need" + "content/SEO flywheel" → "talk to customers and
     write content" (CONVENTIONAL).
   - "build-interesting/demo" + "platform-timing/share" → "build demos and share them".
   - "behavioral-cohort/analytics" + "content funnel" → "segment users and optimize".
   - "community-join" + "audience-borrowing" → "join communities and participate".
   - "content flywheel" + any SEO/authority/backlink vector → "create content to rank".

4. **`category_diversity_requirements`** (build reads this) — compute from
   `growth-factors.json` `metadata.category_counts`:
   `{ "total_vectors": N, "category_counts": {…}, "minimum_unique_vectors_in_synthesis":
   {prefix: min}, "max_single_category_pct": 60, "note": "No single category prefix should
   exceed 60% of vectors used in synthesis output" }`.

   **Minimum rule per prefix — must be satisfiable, or it is worse than no rule at all:**
   - `count == 0` → **0**. Never 1. A category with no vectors cannot contribute one.
   - share of total **< 10%** → `min(2, count)`
   - share of total **≥ 10%** → `min(3, count)`
   - **Then cap the whole set: the sum across prefixes must not exceed 12.** If it does, shave
     from the largest minimums first until it fits.

   The cap is the load-bearing part. Synthesis produces **7-9 tactics carrying 2-3 vectors
   each**, so ~12 distinct vectors is the realistic ceiling and ~18 is the absolute one. A
   share-of-DB rule (the shape the proprietary script uses against a much larger database)
   inverts on a 20-40 vector LIGHT DB and demands *every vector in it*.

   > **Worked example — a real run.** 24 vectors: `struct-` 5, `lever-` 6, `resource-` 6,
   > `psych-` 5, `pos-` 2, `conv-` 0.
   > Shares: 21%, 25%, 25%, 21%, 8%, 0%.
   > Minimums: `struct-` 3, `lever-` 3, `resource-` 3, `psych-` 3, `pos-` 2, `conv-` 0 — sum 14.
   > Over the cap of 12, so shave two from the largest: **`struct-` 3, `lever-` 3, `resource-` 2,
   > `psych-` 2, `pos-` 2, `conv-` 0 — sum 12.** Satisfiable by an 8-tactic set.
   > (The old share rule produced 5/6/6/5/2/1 — sum 25, i.e. "use every vector plus one that
   > doesn't exist." Build silently violated four of the six and nothing noticed.)

Also emit (lite versions of the script's other fields, used loosely by synthesis explore/build):

5. **`anti_patterns`** (synthesis-build reads this INSTEAD of the proprietary anti-vector tracking) — a
   short generic list of demand-gen anti-patterns to reject, each `{ "pattern": "...",
   "severity": "HIGH|MEDIUM", "why": "..." }`. Always include: fabricated scarcity/urgency;
   multi-account astroturfing / fake social proof; fake-door pages for nonexistent
   features; product-dev-disguised-as-marketing (Day-1 is engineering); targeting existing
   users for upgrades (retention, not acquisition); teaching customers to DIY the product
   (cannibalization).

6. **`unconventional_anchors`** — 4-6 of the most "Emerging", high-transferability vectors
   from this run, each `{ "vector": id, "category": "...", "good_partners": [ids],
   "avoid_partners": [ids of conventional/over-represented vectors], "reason": "..." }`.

7. **`validation_rules`** — `{ "min_white_space": 5, "min_synergy_pairs": 5,
   "max_from_same_anchor": 2, "unconventional_target_pct": 50 }`.

## Output schema (write EXACTLY this JSON shape)

```json
{
  "version": "lite-1.0",
  "source_note": "Built in-context from the per-run growth-factors.json LIGHT DB. NOT the proprietary intelligence layer.",
  "generated_for": { "budget_max": 0, "team_size": "solo|small|full|unknown", "unfair_advantages": [], "hours_per_week": 0, "stage": "..." },
  "diverse_white_space": [ { "vectors": ["id_a","id_b"], "reason": "...", "source": "white_space" } ],
  "diverse_white_space_stats": { "candidate_vectors": 0, "pairs_emitted": 0, "excluded_theme": "content-flywheel/over-represented" },
  "mandatory_combinations": [ { "pool": "A_white_space|B_synergy|C_founder_leverage", "vectors": ["id_a","id_b"], "reason": "...", "priority": "must_include|suggested" } ],
  "prohibited_combinations": [ { "pattern": "...", "vectors_if_present": [], "reason": "...", "alternative": "..." } ],
  "unconventional_anchors": [ { "vector": "id", "category": "...", "good_partners": ["id"], "avoid_partners": ["id"], "reason": "..." } ],
  "anti_patterns": [ { "pattern": "...", "severity": "HIGH", "why": "..." } ],
  "validation_rules": { "min_white_space": 5, "min_synergy_pairs": 5, "max_from_same_anchor": 2, "unconventional_target_pct": 50 },
  "category_diversity_requirements": { "total_vectors": 0, "category_counts": {}, "minimum_unique_vectors_in_synthesis": {}, "max_single_category_pct": 60, "note": "No single category prefix should exceed 60% of vectors used in synthesis output" }
}
```

## Procedure

1. **Parse founder constraints** from `founder-input.md` into `generated_for` (budget_max
   from "Monthly marketing budget"/MRR; team_size from solo/team; unfair_advantages from
   "Rare assets"; hours_per_week from "Hours per week for growth"; stage from metrics).
2. **Load the vectors** from `growth-factors.json`. Note category spread and which vectors
   are Emerging / High transferability (white-space + anchor candidates) vs over-represented
   (content-flywheel-like → exclude from white space).
   **Degraded-DB check:** if the vectors collapse into fewer than 5 distinct mechanism
   verbs (e.g. 8 of 20 vectors are "publish/write/create"), or a single category holds
   >70% of vectors, mark `"db_quality": "degraded"` in the output metadata and widen the
   pools — relax the "Emerging" requirement for Pool C and allow one extra pair per pool
   from adjacent categories. This is a warning that changes behavior, not a gate that halts.
3. **Build `diverse_white_space`** (8-10 cross-category pairs; run each mentally through the
   "would a marketer say 'that's unusual'?" test; exclude content-flywheel-type vectors).
4. **Build the three `mandatory_combinations` pools** (A/B/C as above), using ONLY this
   run's IDs. Respect `max_from_same_anchor: 2`.
5. **Build `prohibited_combinations`** (the generic patterns above, mapped onto matching
   run IDs where they exist).
6. **Build `anti_patterns`, `unconventional_anchors`, `validation_rules`.**
7. **Compute `category_diversity_requirements`** from `metadata.category_counts`.
8. **Write valid JSON.** Confirm it parses and every referenced ID exists in
   `growth-factors.json`.

## Validation checklist (self-check before returning)

- [ ] Valid JSON in the exact shape above.
- [ ] Every vector ID referenced exists in this run's `growth-factors.json` (no invented /
      no proprietary IDs).
- [ ] `diverse_white_space` ≥ 5 cross-category pairs; no content-flywheel-type vector in it.
- [ ] `mandatory_combinations` has Pool A (5), Pool B (5), Pool C (5); founder-leverage
      pool exploits the founder's rare assets within their time and budget.
- [ ] `prohibited_combinations` includes the 5 generic conventional patterns.
- [ ] `category_diversity_requirements` computed from real `category_counts`,
      `max_single_category_pct: 60`.
- [ ] `minimum_unique_vectors_in_synthesis` is **satisfiable**: every zero-count prefix maps to
      0, and the sum across prefixes is **≤ 12**.
- [ ] `anti_patterns` present (the clean-room replacement for the proprietary anti-vectors).