100 lines
3.0 KiB
Markdown
100 lines
3.0 KiB
Markdown
# Tilbudgivern Mission
|
|
|
|
Last updated: 2026-03-29
|
|
|
|
## North Star
|
|
|
|
Tilbudgivern exists to make quote creation so fast and reliable that a carpenter can stand with the customer, measure the roof, note a few project facts, and leave with a strong quote draft the same day.
|
|
|
|
The product should work equally well on:
|
|
- mobile phone on site
|
|
- laptop in the van
|
|
- desktop in the office
|
|
|
|
## Core Mission
|
|
|
|
1. Minimize friction in the field.
|
|
The carpenter should only need a few inputs to get started:
|
|
- customer/address
|
|
- project type
|
|
- roof type/material
|
|
- length/width/pitch or rough area
|
|
- short customer note
|
|
|
|
2. Reuse as much real data as possible.
|
|
Tilbudsgiveren should prefer real historical evidence over empty forms:
|
|
- local Tilbudgivern project history
|
|
- synced Ordrestyring history
|
|
- previously used Smart Packages
|
|
- previously accepted/sent offers
|
|
|
|
3. Make Smart Packages the operational backbone.
|
|
Smart Packages should be:
|
|
- quick to choose
|
|
- easy to edit
|
|
- grounded in real carpenter work
|
|
- structured with materials, tasks, hours, and pricing
|
|
|
|
4. Let AI help with language, not fake facts.
|
|
AI should:
|
|
- fix spelling and messy notes
|
|
- structure rough carpenter input
|
|
- produce sharp, customer-friendly offer text
|
|
- explain the work clearly
|
|
|
|
AI must not:
|
|
- invent measurements
|
|
- invent prices
|
|
- silently change quantities, rates, or totals
|
|
- fabricate work not present in project/package data
|
|
|
|
5. Make the system improve through usage.
|
|
Every completed quote flow should create reusable learning signals:
|
|
- what package was suggested
|
|
- what package was chosen
|
|
- what materials/tasks were changed
|
|
- what text was accepted
|
|
- which historical cases were used
|
|
|
|
The system should get better over time as more quotes are created.
|
|
|
|
## Product Principles
|
|
|
|
- Field-first beats backoffice-first.
|
|
- Prefill beats blank state.
|
|
- Editable beats locked automation.
|
|
- Real history beats generic AI.
|
|
- Short path to first useful draft beats perfect initial completeness.
|
|
- Structured project data beats free-text prompts.
|
|
|
|
## What “Good” Looks Like
|
|
|
|
A carpenter can:
|
|
- create a project in under 2 minutes
|
|
- get a relevant Smart Package recommendation automatically
|
|
- receive suggested materials and hours from similar jobs
|
|
- generate a customer-ready quote draft from structured data
|
|
- correct mistakes quickly before sending
|
|
- leave the quote in a clear persisted status before sending to Ordrestyring
|
|
|
|
## Implementation Direction
|
|
|
|
When choosing features, architecture, or UX, prefer work that moves the product toward:
|
|
|
|
- quick quote flow
|
|
- strong historical matching
|
|
- local sync and reuse of Ordrestyring data
|
|
- structured quote generation
|
|
- mobile-friendly editing and confirmation
|
|
- persisted workflow states that match the real carpenter journey
|
|
- visible material pricelist freshness from synced supplier/import data
|
|
- measurable learning from accepted/edited quotes
|
|
|
|
## Non-Goals
|
|
|
|
Avoid optimizing primarily for:
|
|
- long admin workflows before first quote value
|
|
- AI-generated content without structured project grounding
|
|
- rigid package systems that are hard for carpenters to override
|
|
- flows that assume office-only usage
|