---
source: discover synthesis (DISC-04)
date: {today's date YYYY-MM-DD}
---

# Discovery Brief - {Client / Product}

The synthesis step fills each slot below from the discovery conversation. Every
slot is a blank placeholder or a guidance note; fill it from local room data
only. Per Canon Part 9, every guess lands flagged as an assumption, never as a
confirmed fact.

## Brand soul

- Essence (one line):
- The big why:
- Core values (3 to 5):
- Archetype (primary + secondary):
- Voice (3 do's):
- Never says / never does:

## Product essence

- What it is (one sentence):
- The one core job:
- Business case (who pays, why they keep paying):
- Hard constraints (budget, timeline, stack, legal, brand rules):
- "Done well" metric:

## Personas and JTBD

For each persona, build one card:

- Name + context (situation, pressure, constraint at the moment of need):
- Job statement ("When I ___, I want to ___, so I can ___"):
- Functional / Emotional / Social job:
- Fires (current alternative + the last straw that makes them switch):
- Trigger (the event that sends them looking):

## Positioning

- The whitespace / sea of sameness to break:
- The one sentence only we can say:

## Habit loop

Design the returning loop, not the pages. The four Hooked stages are inlined
here so the brief is self-contained (no dependency on a separate hooked-model
skill):

- Trigger (external + internal): the external prompt the user arrives from
  (search, referral, email, ad), and the internal emotion or itch the product
  attaches to so they return on their own (boredom, anxiety, FOMO, pride,
  curiosity).
- Action (simplest valuable behavior; B=MAP notes): the single simplest
  behavior that delivers value. Check Fogg B=MAP - enough Motivation, low
  enough Ability (effort), a clear present Prompt. Reduce effort before adding
  motivation.
- Variable reward (tribe / hunt / self + how varied): which reward type, and
  how it is varied so it is not identical every time. Tribe (validation,
  belonging, recognition), Hunt (a feed, a search, a deal, a result), Self
  (mastery, completion, progress, control).
- Investment (what loads the next trigger): what the user puts in that makes
  the next visit better for them and loads the next trigger - data, content,
  reputation, followers, configuration, skill. Investment is the difference
  between a visit and a relationship.
- Ethics (Facilitator check): does this loop improve the user's life AND would
  the maker use it themselves? Build for the Facilitator quadrant, not the
  Dealer.

## Plain-language message

This section is the load-bearing handoff from discovery to any website or deck
build. Fill it before any visual work begins.

- One-liner (explain it to a smart twelve-year-old): one plain sentence, no
  jargon, that a smart twelve-year-old would understand.
- Value-prop ladder: the message laddered from the single core benefit up
  through the supporting reasons-to-believe (benefit -> how -> proof).

Note: the deck is produced on request only, via mos-deck-engine. The command
dispatches mos-deck-engine through the resolver door; this template does not
build the deck and does not name a slide format.

## Design implications

- Structure / IA:
- Tone + visual direction:
- THE single most important user action:

## Open questions and assumptions

Flag every guess. Per Canon Part 5 and Part 9, every guess is recorded as an
assumption with `review_status: proposed` and is never allowed to harden into a
confirmed fact without a human decision at the Decision Gate.

- (assumption, review_status: proposed):