Cross-Tool Flow

From User Interviews to Prioritized Backlog

A complete, battle-tested workflow for product teams: conduct 10 generative interviews, synthesize insights, create a PRD, break it into tasks, and load a prioritized backlog into your project management tool.

See this flow as an interactive diagram

Visualize the entire workflow as a Value Stream Map. Identify bottlenecks, handoffs, and optimization opportunities.

Open in Value Stream Mapper

Workflow Overview

1
Conduct Interviews
2
Synthesize Research
3
Create PRD
4
Break into Tasks
5
Prioritize
6
Load Backlog
2-3 weeks
Total workflow duration
5-6 tools
Tools used across workflow
AI-assisted
With prompt templates
1

Conduct 10 Generative Interviews

Recruit participants, run discovery interviews, and capture rich qualitative data

🛠️ Tools for This Phase

Step-by-Step Process

  1. 1
    Define research objectives

    What do you want to learn? What decisions will this research inform?

  2. 2
    Create discussion guide

    5-7 open-ended questions focused on understanding problems, workflows, and pain points

  3. 3
    Recruit 10-12 participants

    Plan for 10 completed interviews (some may cancel). Use User Interviews or Respondent for recruitment.

  4. 4
    Conduct and record interviews

    45-60 min sessions. Record with Dovetail, Great Question, or Lookback. Take notes during the session.

  5. 5
    Auto-transcribe all sessions

    Most tools auto-transcribe. Review transcripts for accuracy.

💡 Pro Tip

Don't wait until all interviews are done to start analysis. Review transcripts and tag insights after every 2-3 interviews to identify emerging themes early.

📤 Output from This Phase

  • 10 recorded interview sessions with transcripts
  • Tagged highlights and quotes in your research tool
  • Raw notes from each session
2

Synthesize Research with AI

Extract themes, pain points, opportunities, and user quotes using AI-assisted analysis

🛠️ Tools for This Phase

Analysis Platform
Dovetail, Great Question
AI Assistant
Claude, ChatGPT, or tool's built-in AI

Step-by-Step Process

  1. 1
    Export transcripts and highlights

    From Dovetail or Great Question, export all transcripts and tagged highlights as text or CSV

  2. 2
    Use AI to identify themes

    Feed transcripts to an LLM with a synthesis prompt (see below)

  3. 3
    Review and refine insights

    Validate AI-generated themes against original data. Add context and nuance.

  4. 4
    Extract actionable opportunities

    Identify 3-5 key opportunity areas based on pain points and user needs

🤖 AI Prompt Template: Research Synthesis

I conducted 10 user interviews to understand [RESEARCH OBJECTIVE].
Below are the transcripts from all sessions.

Please analyze these interviews and provide:

1. **Key Themes** (5-7 major themes that emerged)
   - For each theme: description, frequency across interviews,
     supporting quotes

2. **Pain Points** (Top 5 pain points mentioned)
   - For each: severity, frequency, user quotes

3. **Opportunities** (3-5 actionable opportunity areas)
   - Based on unmet needs, workarounds, and expressed desires

4. **User Segments** (If applicable)
   - Different user types or personas that emerged

5. **Workflow Patterns**
   - How users currently accomplish [TASK/GOAL]
   - Tools they use and handoffs between tools

Format the output in markdown with clear sections and
include specific quotes to support each finding.

[PASTE TRANSCRIPTS HERE]

How to use: Replace [RESEARCH OBJECTIVE] and [TASK/GOAL] with your specifics. Paste all transcripts. Review AI output and validate against source data.

📤 Output from This Phase

  • Research synthesis document with themes, pain points, and opportunities
  • Key user quotes organized by theme
  • 3-5 validated opportunity areas for product development
3

Create Product Requirements Document

Transform insights into a structured PRD with clear requirements and success criteria

🛠️ Tools for This Phase

Document Creation
Notion, Google Docs, Confluence
AI Drafting
Claude, ChatGPT
Collaboration
Figma (for mockups)

PRD Structure

1. Problem Statement

What problem are we solving? For whom? Why now?

2. User Insights

Key findings from research (pull from synthesis doc)

3. Goals & Success Metrics

What defines success? How will we measure it?

4. Solution Overview

High-level approach to solving the problem

5. Functional Requirements

Detailed features and capabilities (must-have vs nice-to-have)

6. User Stories

As a [user], I want [capability] so that [benefit]

7. Technical Considerations

Dependencies, constraints, integration points

8. Out of Scope

What we're explicitly NOT doing (prevents scope creep)

🤖 AI Prompt Template: PRD Creation

Based on the research synthesis below, help me draft a Product
Requirements Document (PRD) for [FEATURE/PRODUCT NAME].

Research Synthesis:
[PASTE YOUR SYNTHESIS FROM PHASE 2]

Please create a PRD with the following sections:

1. Problem Statement (2-3 paragraphs)
2. User Insights (key findings from research)
3. Goals & Success Metrics (3-5 measurable goals)
4. Solution Overview (high-level approach)
5. Functional Requirements (organized as Must-Have, Should-Have,
   Nice-to-Have)
6. User Stories (8-12 stories in "As a...I want...so that" format)
7. Technical Considerations
8. Out of Scope (what we're NOT doing)

For functional requirements, be specific and actionable.
For user stories, reference actual pain points from the research.
Include relevant user quotes where appropriate.

How to use: Paste your research synthesis. Review AI draft and refine with team input. Validate requirements against research findings.

📤 Output from This Phase

  • Complete PRD document with all 8 sections
  • Prioritized functional requirements (Must/Should/Nice-to-Have)
  • 8-12 user stories ready to be broken into tasks
4

Break PRD into Actionable Tasks

Decompose user stories and requirements into granular, estimatable tasks

🛠️ Tools for This Phase

Task Breakdown
Spreadsheet, AI assistant, or whiteboard
Engineering Input
Collaborative session with engineering team

Step-by-Step Process

  1. 1
    Take each user story from PRD

    Start with must-have requirements first

  2. 2
    Use AI to generate initial task list

    Break each story into engineering tasks (see prompt below)

  3. 3
    Review with engineering team

    Refine tasks, identify dependencies, add missing tasks

  4. 4
    Add acceptance criteria to each task

    What does "done" look like for this task?

  5. 5
    Estimate effort for each task

    Use story points, t-shirt sizes, or hours based on your team's practice

🤖 AI Prompt Template: Task Breakdown

Break down this user story into granular engineering tasks:

User Story:
[PASTE USER STORY]

Context:
- Tech stack: [YOUR TECH STACK]
- Architecture: [BRIEF ARCHITECTURE DESCRIPTION]

Please provide:
1. Frontend tasks (if applicable)
2. Backend tasks (if applicable)
3. Database/infrastructure tasks
4. Testing tasks
5. Documentation tasks

For each task:
- Make it specific and actionable
- Identify dependencies on other tasks
- Suggest acceptance criteria
- Flag any technical unknowns or risks

Format as a numbered list with dependencies clearly marked.

How to use: Run this prompt for each user story. Review with engineers to validate and refine. This gives you a comprehensive task list.

📋 Task Format Template

Task Title: [Action verb] + [specific work]
Example: "Build API endpoint for user profile updates"

Description: [1-2 sentences explaining what and why]

Acceptance Criteria:
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3

Dependencies: [Task IDs this depends on]

Estimate: [Points/Hours/Size]

Labels: [frontend, backend, testing, etc.]

📤 Output from This Phase

  • 50-100+ granular tasks (depending on PRD scope)
  • Each task has acceptance criteria and dependencies
  • Effort estimates for planning purposes
5

Prioritize Your Backlog

Use frameworks to determine what to build first based on value, effort, and dependencies

🛠️ Prioritization Frameworks

RICE Framework

Score each feature: (Reach × Impact × Confidence) / Effort

Reach
How many users?
Impact
How much benefit?
Confidence
How sure are we?
Effort
How much work?

Value vs Effort Matrix

Plot tasks on 2×2 grid: High Value/Low Effort = do first

Quick Wins
High value, low effort
Big Bets
High value, high effort
Fill-ins
Low value, low effort
Time Sinks
Low value, high effort

MoSCoW Method

Categorize every task into one of four buckets:

Must Have:Critical for launch, non-negotiable
Should Have:Important but not critical
Could Have:Nice to have if time permits
Won't Have:Out of scope for this release

Prioritization Process

  1. 1
    Choose your framework

    RICE for data-driven teams, Value/Effort for speed, MoSCoW for clear scoping

  2. 2
    Score or categorize all tasks

    Involve PM, engineering, and design in the exercise

  3. 3
    Check dependencies

    Some low-priority tasks must be done first (e.g., infrastructure)

  4. 4
    Create final rank order

    Number tasks 1, 2, 3... in priority order

🤖 AI Prompt Template: RICE Scoring

Help me prioritize these tasks using the RICE framework.

Context:
- Total addressable users: [NUMBER]
- Our key success metric: [METRIC]
- Sprint capacity: [POINTS/HOURS]

Tasks to prioritize:
[PASTE YOUR TASK LIST]

For each task, provide RICE scores:
- Reach: How many users impacted (0-10)
- Impact: How much it moves the metric (0.25/0.5/1/2/3)
- Confidence: How certain we are (50%/80%/100%)
- Effort: Story points or hours

Calculate RICE score: (R × I × C) / E
Output as a table sorted by RICE score descending.

📤 Output from This Phase

  • Prioritized backlog with tasks ranked 1, 2, 3...
  • Clear rationale for prioritization decisions
  • Dependencies mapped and addressed
6

Load Backlog into Task Management Tool

Import prioritized tasks into Linear, Jira, or your PM tool of choice

🛠️ Tools for This Phase

Project Management
Linear, Jira, Asana, Shortcut
Import Method
CSV upload, API, or manual entry

Loading Process by Tool

Linear
  1. Prepare CSV with columns: Title, Description, Priority, Estimate, Labels
  2. Go to Project Settings → Import → CSV Import
  3. Map CSV columns to Linear fields
  4. Import creates issues in bulk
  5. Manually add dependencies and parent/child relationships
Jira
  1. Format tasks as CSV: Summary, Description, Issue Type, Priority, Story Points
  2. Settings → System → Import & Export → CSV
  3. Map fields during import wizard
  4. Review and confirm import
  5. Use Jira Automation to set dependencies based on labels
Asana/Monday/ClickUp
  1. Export tasks to CSV format
  2. Use built-in CSV import feature
  3. Map columns to fields
  4. Import and review
API-Based Import (Advanced)
  1. Use Linear API, Jira API, or Asana API
  2. Write script to POST tasks with all metadata
  3. Programmatically create dependencies
  4. Best for large imports (>100 tasks)

📊 CSV Format Template

Use this format for bulk import into most PM tools:

Title,Description,Priority,Estimate,Labels,Parent,Dependencies
"Build user profile API endpoint","Create REST API endpoint for updating user profile data. Should accept JSON payload with user fields.",High,5,"backend,api",,
"Design profile edit UI","Create Figma designs for profile editing screen with form validation",High,3,"design,frontend",,
"Implement profile edit form","Build React form component based on designs",Medium,5,"frontend","Design profile edit UI","Build user profile API endpoint"
"Write API integration tests","Unit and integration tests for profile API",Medium,3,"testing,backend","Build user profile API endpoint",
"Update user documentation","Add profile editing to user guide",Low,2,"docs","Implement profile edit form",

✅ Post-Import Checklist

📤 Output from This Phase

  • Fully loaded backlog in your PM tool
  • Team can start sprint planning immediately
  • Clear roadmap from research to implementation

Ready to map your own workflow?

Use our Value Stream Mapper to visualize this entire flow. See the handoffs, identify bottlenecks, and track cycle times for continuous improvement.

Open in Value Stream Mapper

Workflow Complete! 🎉

You've gone from raw user insights to a prioritized, ready-to-build backlog.

🎯

Research-Driven

Every task traces back to user insights and validated pain points

🤖

AI-Accelerated

Used AI to synthesize research, draft PRD, and break down tasks

📊

Data-Informed

Prioritized using frameworks, not opinions or HiPPO

What You've Built

📄 Artifacts Created:
  • • Research synthesis document
  • • Complete PRD with requirements
  • • Task breakdown with estimates
  • • Prioritized backlog
🔗 Tools Mastered:
  • • User research platforms
  • • AI for synthesis & planning
  • • Prioritization frameworks
  • • Project management tools

Next Steps

1. Share PRD and backlog with your team

2. Schedule sprint planning to pull in first tasks

3. Start building! 🚀

Share Your Workflow Variations