Brief Builder: From Blank Page to Growth Engine.

CQuel Brief Builder interface - Optimize view with improvement recommendations and performance metrics
CQuel Brief Builder interface - Optimize view with improvement recommendations and performance metrics

My role

Product design, research, prototyping, testing

Team

PM, 2 Engineers

Timeline

4 months (May - Aug 2025)

4 months
(May - Aug 2025)

The goal was to unlock the funnel. Customers couldn't start tendering because brief creation was too complex.

I joined when Brief Builder was a concept: help customers create briefs themselves. Through research and testing, I discovered they didn't want independence - they wanted guided collaboration. This insight transformed Brief Builder from a self-service tool into a hybrid system that accelerates CQuel's service delivery while giving customers confidence to proceed.

100+

briefs generated in 5 months

30%

faster time-to-tender

75%

supplier-rated brief quality

My contribution:

  • Designed the end-to-end experience from upload to publish

  • Engineered the scoring & validation logic that algorithmically guides users to a "ready-to-publish" state.

  • Led high-stakes validation with difficult-to-access senior stakeholders (Asset Managers & Engineers).

  • Built production-grade prototypes in Cursor that enabled Sales to demo and validate the product before engineering started

01

The Problem

CQuel connects real estate with sustainable solutions through bidding, but customers couldn't get started – brief creation was their biggest barrier. Without templates or guidance, potential projects never reached suppliers.

  • Information Chaos
    Data scattered across files. No idea what suppliers actually need.

  • Role Confusion
    Who provides technical specs? Who handles strategy?

  • Status Uncertainty
    Is this brief good enough to publish?

  • Manual Coordination
    Endless emails chasing missing information.

02

The Research

Overall scope:

Worked with senior B2B stakeholders - asset managers, sustainability consultants, engineers. These users are busy, hard to access, and skeptical of new tools. Recruited through cold outreach, existing client relationships, and sales introductions.

6

in-depth interviews

50+

existing

briefs

8

workflows shadowed

Key insight from research:

Managers needed structure, not blank pages. But more importantly - they wanted to delegate and get expert help, not do everything themselves. The most-used features became "Delegate to team member" and "Request help from CQuel."

03

The Solution

What is Brief Builder?

An AI tool that helps customers create quality briefs without needing to know what to include. It guides them from scattered information to a confident "ready to publish" decision.

How it works

Customers upload whatever they have - PDFs, photos, notes. AI generates a structured brief with all required sections filled in. Then they review, optimise, and either publish or request help.

Design principles I established:

  • Direction over data
    Show what to do next, not just what's missing.

  • Whose court clarity
    Always visible who acts next and what they need to do.

  • Proactive status
    the system tells them when the brief is ready.

CQuel Brief Builder interface - Optimize view with improvement recommendations and performance metrics
CQuel Brief Builder interface - Optimize view with improvement recommendations and performance metrics
CQuel Brief Builder interface - Optimize view with improvement recommendations and performance metrics
Brief Performance panel showing three quality indicators: Pricing accuracy rated Excellent, Time in Tender rated Standard, and Clarity level rated Adequate, with comparison metrics and optimization tips
Brief Performance panel showing three quality indicators: Pricing accuracy rated Excellent, Time in Tender rated Standard, and Clarity level rated Adequate, with comparison metrics and optimization tips
Brief Performance panel showing three quality indicators: Pricing accuracy rated Excellent, Time in Tender rated Standard, and Clarity level rated Adequate, with comparison metrics and optimization tips

How do you tell a non-expert their brief is "good enough"?

What I designed:

Outcome-focused ratings that answer the real question: "Can I proceed?"

  • Good / Excellent / Adequate - Clear status without judgment

  • "Ready to Proceed" signal - Binary confidence to publish

  • Grouped recommendations by priority - Accurate pricing, Fastest start, Best bids

The specific scoring criteria came from team expertise and supplier feedback analysis. The conceptual framework - making it about decisions, not scores - was my contribution.

The B2B gamification insight:

In B2B, gamification isn't about points and badges. It's about reducing decision anxiety. The Brief Performance panel works because it turns uncertainty ("Is this good enough?") into confidence ("You're ready to proceed").

Role Confusion → Four Clear Ways to Fill Gaps

For each missing piece, choose how to complete it:

  • upload a document,

  • write it manually,

  • delegate to a team member,

  • or request help from CQuel.

No more guessing who should provide what.

Structural assessment recommendation card with Save up to €10k tag, showing four action options: Add details, Upload, Delegate to team member, or Get assistance
Structural assessment recommendation card with Save up to €10k tag, showing four action options: Add details, Upload, Delegate to team member, or Get assistance
Structural assessment recommendation card with Save up to €10k tag, showing four action options: Add details, Upload, Delegate to team member, or Get assistance
Solar PV Project brief showing project details including 101.7 kWp installation size, 90,809 kWh energy demand, and 494.3 m² roof area for a residential property in Germany
Solar PV Project brief showing project details including 101.7 kWp installation size, 90,809 kWh energy demand, and 494.3 m² roof area for a residential property in Germany
Solar PV Project brief showing project details including 101.7 kWp installation size, 90,809 kWh energy demand, and 494.3 m² roof area for a residential property in Germany

Information Chaos → Structured Brief

Upload whatever you have - PDFs, photos, notes, scattered documents. AI analyses the content and generates an organised brief with all required sections filled in.

Manual Coordination → Educational Guidance

Built-in explanations show why each piece matters:

"Without structural docs, contractors add 15% safety margin" or "Visual confirmation reduces electrical estimates by 10%."

Customers learn tender dynamics while building their brief.

Optimize tab showing three priority filters - Accurate pricing, Fastest start, Best bids - with prioritized recommendations and cost savings for each action
Optimize tab showing three priority filters - Accurate pricing, Fastest start, Best bids - with prioritized recommendations and cost savings for each action
Optimize tab showing three priority filters - Accurate pricing, Fastest start, Best bids - with prioritized recommendations and cost savings for each action

04

Testing

What we did:

Built a fully functional prototype using Cursor - not just clickable screens, but working like a real product. This enabled:

  • 10 live testing sessions with asset managers, consultants, and engineers.

  • CEO used it for sales demos while we were still designing.

  • Real feedback on real workflows, not hypothetical scenarios.

What changed and why:

Percentages → Simple Ratings

Users didn't want scores - they wanted to know "is this good enough?"

Before and after: percentage-based quality scores replaced by outcome-focused Brief Performance with Excellent, Standard, and Adequate ratings and clear explanations
Before and after: percentage-based quality scores replaced by outcome-focused Brief Performance with Excellent, Standard, and Adequate ratings and clear explanations
Before and after: percentage-based quality scores replaced by outcome-focused Brief Performance with Excellent, Standard, and Adequate ratings and clear explanations
Before and after: percentage-based quality scores replaced by outcome-focused Brief Performance with Excellent, Standard, and Adequate ratings and clear explanations
Before and after: percentage-based quality scores replaced by outcome-focused Brief Performance with Excellent, Standard, and Adequate ratings and clear explanations
Before and after: percentage-based quality scores replaced by outcome-focused Brief Performance with Excellent, Standard, and Adequate ratings and clear explanations

Our Jargon → Their Words

Terms like "best bids" confused people. Switched to plain language customers actually use.

Terminology changes: Brief quality to Clarity level, Costing Precision to Pricing accuracy, Accurate to Good, Could be reduced to Adequate
Terminology changes: Brief quality to Clarity level, Costing Precision to Pricing accuracy, Accurate to Good, Could be reduced to Adequate
Terminology changes: Brief quality to Clarity level, Costing Precision to Pricing accuracy, Accurate to Good, Could be reduced to Adequate

Everything in One View → Separate Tabs

Editing and reviewing at the same time caused confusion. Split into Review and Optimise.

Before and after: combined editing and assessment view split into separate Review and Optimize tabs with clear improvement recommendations
Before and after: combined editing and assessment view split into separate Review and Optimize tabs with clear improvement recommendations
Before and after: combined editing and assessment view split into separate Review and Optimize tabs with clear improvement recommendations
Before and after: combined editing and assessment view split into separate Review and Optimize tabs with clear improvement recommendations
Before and after: combined editing and assessment view split into separate Review and Optimize tabs with clear improvement recommendations
Before and after: combined editing and assessment view split into separate Review and Optimize tabs with clear improvement recommendations

Text Editing → Recommendation Actions

Users wanted to trust the AI baseline, not constantly question it. Removed inline editing in favour of structured actions.

Before and after comparison: inline text editing with incomplete information warning replaced by structured recommendation card with clear action options and cost savings highlighted
Before and after comparison: inline text editing with incomplete information warning replaced by structured recommendation card with clear action options and cost savings highlighted
Before and after comparison: inline text editing with incomplete information warning replaced by structured recommendation card with clear action options and cost savings highlighted
Before and after comparison: inline text editing with incomplete information warning replaced by structured recommendation card with clear action options and cost savings highlighted
Before and after comparison: inline text editing with incomplete information warning replaced by structured recommendation card with clear action options and cost savings highlighted
Before and after comparison: inline text editing with incomplete information warning replaced by structured recommendation card with clear action options and cost savings highlighted

05

Impact

For CQuel's business model:

  • Validated Brief Builder as growth funnel entry point

  • Discovered hybrid service model outperforms pure self-service

  • Created foundation for Deal Closing Management product

06

Key Learnings

  • Functional prototypes enable sales
    Cursor prototype became a sales tool before dev shipped.

  • Design for teams, not individuals
    B2B workflows need delegation built in.

  • Senior users need faster decisions, not more data
    The scoring system works because it reduces anxiety, not because it's comprehensive.

  • Self-service isn't always the goal
    Sometimes the best UX is making human help easier to access.