How did we arrive at this proposal — and how do we track that value is delivered?
| Map | Question | Key Finding |
|---|---|---|
| Outcome Map | What does success look like? | 50%+ tasks via conversation. 0% today. Kill signal: <10% after 30 days. |
| Value Stream Map | Where does time die? | 4-module navigation per task. Copy-paste PDF to form. 1x1 modality out of 49 possible. |
| Dependency Map | What must happen first? | Agent Platform (identity + memory) and Identity & Access (auth) block everything. |
Templates: docs/pictures/patterns/
The Bridge
Pictures sit between sales and engineering. The prompt deck sells the vision in five cards. The spec builds the machine. These three maps prove the thinking is sound.
| Prompt Deck (sales) | Pictures (bridge) | Spec (engineering) |
|---|---|---|
| "Forms serve databases, not users" | Outcome: 50%+ conversational task rate, 3 jobs | T0: Text chat + session memory + feature flag |
| "50% tasks via conversation" | Value Stream: 4-module navigation, 1x1 modality | T1: Modality router + WorkChart adapter + normaliser |
| "WorkCharts built, wiring missing" | Dependency: Agent Platform + Identity block all work | T2: File upload + streaming progress + rich results |
| "Text first, voice second" | Outcome: text MVP proves value before adding voice | T3: CRM query adapter + conversation history |
| "Colleague, not chatbot" | Value Stream: broken promises = AI skepticism | T4: Voice input (STT) |
Context
- PRD Index — Multimodal Agent Interface
- Prompt Deck — 5-card pitch
- Spec — Engineering depth
- Plan — Implementation coordinates