AI Assistant for Design Documentation

Overview

BetterMode offers a Design Service for enterprise clients such as HubSpot, Samsung, Bosch, and Webflow, providing fully customized community designs.
This process required extensive design documentation based on client branding, audience personas, and feature needs collected by the CX (Customer Experience) team.
Previously, this documentation was manually compiled, often incomplete, and caused communication friction between CX and Design.
To address this, I developed an AI-powered assistant that converts CX meeting transcripts into structured, complete, and ready-to-use design briefs, saving time, improving accuracy, and accelerating delivery.

The Problem

Manual and inconsistent documentation slowed collaboration between CX and Design teams.

The CX team spent significant time rewriting notes and transcripts from client meetings into design briefs. The process was error-prone, inconsistent, and often incomplete, requiring frequent clarifications between teams. This inefficiency delayed project timelines and added unnecessary cognitive load on both CX and Design sides.

Design Approach

Applied human-in-the-loop automation to streamline documentation without losing context or quality.

I approached this as a workflow optimization problem, not just an automation task.
The goal was to preserve the nuance of human conversation while ensuring structured, reliable data for design.
The assistant was designed around three principles:

1. Context Understanding: interpret transcripts semantically, not literally.

2. Structure & Clarity: output organized documentation by sections (Branding, CMSs, Spaces, Menus, Features).

3. Human Validation Loop: CX members review and approve outputs before sharing with the design team.

Research

I interviewed CX members and reviewed several real design documentation examples to identify bottlenecks and quality issues.
Key findings included:

• 40-50% of meeting time was spent gathering repetitive information.

• 25% of documents were missing key design details like branding or inspiration samples.

• The need for consistency was critical, each designer interpreted partial data differently.

These insights shaped the assistant’s structured output model and verification logic.

User Personas

• CX Specialist: Responsible for client communication and delivering requirement briefs. Needs efficiency and accuracy.

• Product Designer: Relies on complete and consistent data to begin design work. Needs clarity and structure.

• Design Lead / Project Manager: Oversees workflow speed and quality. Needs transparency and reliable data flow.

Design Goals

1. Reduce manual documentation time for CX team by at least 40%.

2. Ensure consistency and completeness in design requirement documents.

3. Minimize back-and-forth communication between CX and Design.

4. Create an adaptable system that can improve over time with usage data.

Working Towards a Solution

Built an AI-assisted workflow that transforms transcripts into structured, validated design briefs.

I mapped the end-to-end workflow, from client meeting to design handoff, to identify automation points.
The AI assistant receives transcript text as input, extracts relevant design data, categorizes it under predefined sections, and outputs a complete, editable draft.
This draft is then reviewed by CX before final submission, ensuring human oversight and accuracy.

Ideation

Explored multiple ways the assistant could process input data, from keyword-based extraction to semantic intent mapping using LLMs.
Settled on a hybrid approach: rule-based extraction for structured data (e.g., color codes, logos) and AI-powered contextual inference for qualitative input (e.g., audience goals, tone, or brand personality).

User Flow

1. CX uploads or pastes the client meeting transcript.

2. The assistant analyzes and segments key information by topic.

3. Extracted content is previewed in an editable structured format in a dashboard.

4. CX reviews, corrects, or adds missing details.

5. Final approved document is exported as a ready-to-use design brief for the design team.

Designing Process

I designed and developed the assistant interface and workflow using Cursor AI and Vercel.
Iterations focused on clarity of output, readability, and reducing manual review steps.
I created a clear, hierarchical format with sections like:

• Brand Identity

• CMSs

• Spaces

• Navigation

• Profile Fields

• Additional Info & Feature Requirements

• Export

The tool was tested using actual client transcripts to ensure language flexibility and domain adaptability.

User Testing Process

The assistant was tested internally with CX team members using anonymized real transcripts.
Testing focused on:

• Accuracy of extracted data

• Time saved in document preparation

• Clarity and usefulness of the output structure

Feedback led to refinement in terminology interpretation, automatic section labeling, and smarter handling of missing data.

Success Metrics

• 50% reduction in average CX documentation time.

• 87% completion rate of design requirement documents (no missing sections).

• 30% faster design team onboarding per project due to clearer briefs.

• Significant reduction in CX-Design back-and-forth communication loops, confirmed via project tracking logs.

Key Insights

• Semantic AI understanding is far more effective than keyword extraction for human conversation data.

• Structured templates + AI create the best balance between automation and control.

• Human-in-the-loop validation ensures quality without compromising efficiency.

• The clarity of documentation directly impacts overall design velocity.

Iteration and Improvement

Iteratively refined the assistant based on CX feedback and real transcript data.

Early versions struggled with ambiguous language or overlapping topics.
Through iterative refinement, I improved prompt structures, added fallback logic for uncertain responses, and introduced validation prompts to flag missing details automatically.
This continuous iteration made the tool more accurate and user-trusted over time.

Outcome and Future Enhancements

A reliable, scalable AI workflow now saving hours weekly and improving inter-team collaboration.

The assistant is now integrated into the CX team’s workflow, generating consistent, complete design briefs in minutes instead of hours.
It has become a trusted internal tool, bridging the gap between client insights and design execution.
Planned enhancements include integrating it with the internal CMS for automatic client profile updates and exploring voice-to-text processing for direct real-time meeting integration.

Below are screenshots of the AI assistant in action: