The builder turns what you know about a company into a structured model. You do not need every field — operators on the right light up as you add the facts that trigger them, and grey (dormant) ones tell you what to add next.
For most companies, an honest model is a multi-person, multi-day discovery program, not a form you finish in one sitting. The builder is designed for that: add facts → Analyze → close the top gaps → repeat. You get value on a partial model; dormant operators are a roadmap, not a failing grade.
Fast start
- Set Interview focus — pick a department pack (finance, ops, support,
…) and/or data maturity level so prompts and section hints match your starting point.
- Set Archetype and resource level — the builder reorders sections and
adapts gap questions to your company stage (startup vs enterprise, etc.).
- Load an example (Meridian Fab, Lumen Consulting, or Beacon Pay) and skim
how the sections connect — or use Auto-map website to draft from public pages + pasted notes, then refine.
- Click Analyze (no API key) to see ranked candidates, operator coverage,
and Improve the model gaps. Use Generate full plan when you want full use-case write-ups (after the highest-impact gaps are closed).
Multi-day discovery (what works today)
Use this loop across sessions and contributors:
| Step | What to do |
|---|---|
| Day 0 | Auto-map + archetype + one department pack → first draft. Run Analyze. |
| Each session | Pick one department focus. Work only the top 3 gaps in Improve the model. |
| Between sessions | Copy the YAML tab into a shared file (git, Drive, etc.). Reload it next time. |
| Before Generate | Close high-severity gaps: linked pains, accessible data on high-volume processes, project abstractions where they matter. |
Important: the model lives in the browser until you Save to server (Step 1 → Saved models) or copy the YAML tab into a shared file. A refresh without saving loses in-progress work. When signed in, saved models are private to your account.
For the full multi-person workflow strategy and product roadmap, see the project documentation when you have repo access.
Recommended fill order
Work top to bottom, but prioritize facts that unlock the most operators. With an archetype set, the builder may reorder sections (e.g. segments first for greenfield startups).
| Order | Section | Why |
|---|---|---|
| 1 | Company | Name + risk appetite set the ranking tilt. |
| 2 | Offerings | Most external plays start here. Add components (`manual`, `rule_based`, `judgment`) and link segments. |
| 3 | Segments | Connect offerings via serves — unlocks Segment Expansion and Customer Success. |
| 4 | Assets | Accessible data is the main grounding signal. Mark `accessible` only if you truly have it today. |
| 5 | Processes | High volume + repetitive → Automate; scarce bottleneck skill → Augment; no data yet → Instrument First. |
| 6 | Skills | Scarce skills power Augment, Training, and Knowledge Capture (with a talent constraint). |
| 7 | Projects | Write the abstraction (pattern stripped of industry words) to unlock Abstraction Transfer. |
| 8 | Pain & value interview → Pains | Attach pains to a process/offering — raises Impact so real problems rank above generic ideas. |
| 9 | Constraints | Not just penalties — they generate Compliance, Integration, Risk Guardrails, and Knowledge Capture plays. |
Relationships (edges)
Links between sections are as important as the nodes themselves:
- Offering → serves → Segment — who buys what.
- Offering / Process / Project → uses → Asset — what data or tech grounds the work.
- Offering → reuses → Project — proven capability you productize.
- Process → bottlenecked_by → Skill — where expert judgment gates throughput.
- Process → uses → Data asset — required for Automate/Augment feasibility.
Tick the checkboxes in each section; the builder writes the graph edges for you.
Section cheat sheet
- Offerings — products/services you sell; delivery `bespoke` + data unlocks Sales Intelligence.
- Segments — customer groups; pair with offerings and data for retention and forecasting.
- Projects — past delivered work; the abstraction field is the reusable pattern.
- Processes — internal workflows; volume + repetitiveness drive automation; data drives feasibility.
- Skills — people capabilities; `med`/`high` scarcity marks bottlenecks.
- Assets — data (records), tech (platforms), physical (equipment). Only tick accessible when usable now.
- Pains — where time/money leaks; always attach to a node when you can.
- Constraints — regulatory, budget, risk, talent, stack — each unlocks targeted operators.
Hover any ⓘ icon in the form for field-level help.
Improve the model (interview planner)
Every Analyze also returns an Improve the model panel: a ranked list of gaps with the exact questions to ask next. Treat it as your interview sprint backlog — assign questions to the people who own those facts.
High-severity gaps (no linked pain, a high-volume process with no accessible data, a project with no abstraction) hurt ranking the most — close those first, re-Analyze, and watch the candidates sharpen. It needs no API key.
Analyze vs Generate
| Action | API key | Output |
|---|---|---|
| Analyze | Not required | Instant prescores (Impact · Feasibility · Moat · Quality), operator coverage, the Improve the model panel, and a grouped candidate list. |
| Generate full plan | Required | Above plus LLM-written use cases, business artifacts (`why_this_company`, `first_experiment`, …), and a sequenced plan (quick wins + strategic bet). |
| Critique & rewrite | Required (with Generate) | Extra LLM pass that flags generic candidates before final ranking. |
| Opportunity dossiers | Required (with Generate) | Packages the selected quick wins + strategic bet into decision-ready one-pagers you can copy as Markdown. |
Use the feasibility / moat slider (or Risk appetite) to tilt toward quick wins vs defensible bets.
Tips for better output
- Be specific — "RFQ → quote turnaround" beats "operations."
- Ground with data — accessible datasets lift feasibility, moat, and quality.
- Record real pains — linked pains are the strongest impact signal.
- Watch operator coverage — aim for green operators that match the company's actual leverage, not every box ticked.
- YAML tab — save and reload the model between sessions; switching back from YAML does not re-parse unsaved edits.
- One department per session — use Interview focus so each contributor sees relevant prompts without drowning in the whole company.