Available for select roles Based in Bangalore, India
All work

Backlog AI

AI-powered backlog creation and refinement experience.

Role
Lead Product Designer
Project Type
AI Product / Enterprise UX
Platform
Enterprise SaaS — Built on Amazon Bedrock & SageMaker
Year
Ongoing
Responsibilities
Product Design UX Strategy AI Experience Design Interaction Design Prototyping Design Systems
AI Product Design Enterprise UX UX Strategy
Backlog AI — conversational backlog creation workspace
01 / Situation

Understanding the Context

What was happening, who it affected, and why the project mattered.

Project Context

Backlog AI is part of a broader enterprise SDLC platform, built to help Product Managers turn plain-language product intent into structured, prioritized backlogs. As AI generation was layered onto an already dense workflow, the product needed to stay understandable and trustworthy even as it became more automated.

Existing Experience

Creating a backlog meant moving through several disconnected steps — uploading requirement documents, waiting for generation, then reviewing output across separate panels with little indication of what the AI had changed or why. Each step reset context, so users had to reconstruct their intent as they moved forward.

The Challenge

Multiple disconnected steps made it difficult for users to understand what the AI was generating, changing, or recommending.

User Problems

01

Users lacked visibility into AI-generated changes.

02

Complex backlog workflows required too many disconnected actions.

03

Users needed more control before applying AI recommendations.

04

Important issues were difficult to prioritize.

Supporting Visuals

Old vs. new home screen comparison

Old vs. new home screen

02 / Task

Defining What Needed to Change

What I was responsible for solving, and what success needed to look like.

Design Challenge

How might we create an AI-assisted backlog workflow that remains understandable, controllable and efficient for complex enterprise use cases?

My Role

I led the end-to-end experience design for the redesign — from early workflow mapping through to final interaction patterns and design-system components. I worked closely with product management to define scope, with engineering to validate what was technically feasible for AI-generated content, and with research to test directions with real Product Owners.

Goals

01

Simplify backlog creation and refinement.

02

Make AI activity more transparent.

03

Give users control over AI-generated changes.

Constraints & Success Criteria

  • Work within the existing product architecture and platform-wide design system
  • Support enterprise-scale workflows, real delivery timelines, and inherent AI uncertainty
  • Deliver a clearer, lower-effort workflow with better visibility into AI recommendations
  • Make review and approval easier, with consistent behavior across every AI-assisted step
03 / Action

Designing the Experience

What I actually did — from mapping the existing workflow to shipping the final experience.

3.1

Understanding the Workflow

Before proposing anything new, I mapped the existing information architecture end to end — where users entered the flow, where they lost context, and where AI activity was invisible. Reworking that structure, not just the visual layer, turned out to be the core of the fix.

Information architecture — before / after
Home Select project Upload requirements Multi-panel review Push to Jira (buried)
Open workspace Describe intent Backlog renders inline Refine in place Dedicated review & handoff step

The Shipped Flow, Step by Step

01

Land in chat — Intent-first landing.

02

Describe the feature — Natural language, attach context.

03

AI confirms scope — Summarizes before generating.

04

Backlog generates inline — Epics, stories, criteria, priorities.

05

Refine in thread — Split-panel epic/story detail.

06

Selective push to Jira — Choose epics and stories to publish.

07

Confirmation — Published with Jira IDs.

3.2

Exploring the Experience

I explored several interaction models before settling on a direction — from a lighter-weight version of the existing wizard, to a fully conversational surface, to a hybrid that kept structured views but removed the step-by-step gating. Prototypes helped compare how each held up under real, messy inputs.

3.3

Key Design Decisions

From Workflow to Conversation

Problem
Traditional multi-step interactions made the AI workflow feel fragmented.
Decision
Move toward a conversational interaction model.
Why
Users could progressively refine their backlog while maintaining context.
Design
The conversational backlog-creation surface

Surfacing AI Reasoning Inline

Problem
Recommendations appeared without explanation, which made them easy to distrust.
Decision
Show a short rationale alongside every AI-generated suggestion.
Why
Users act faster on recommendations they understand, and are more willing to correct ones they don't.
Design
AI clarifying questions, old vs. new

Review Before Apply

Problem
AI changes were applied directly, leaving no room to catch mistakes before they landed in Jira.
Decision
Introduce an explicit review step between generation and apply.
Why
Keeps the user as the final decision-maker, especially for anything downstream teams will act on.
Design
Split-screen review before applying AI changes

Showing What AI Is Doing

Problem
A generic spinner gave no sense of what the AI was actually working on.
Decision
Replace the spinner with narrated status — what the AI is checking, generating, or waiting on.
Why
Users trust a system more when they can see it thinking, not just waiting.
Design
Narrated loading states showing what the AI is doing
3.4

User Research Findings

“I clicked the Backlog AI CTA and thought it was stuck — nothing happened after I clicked.” — Product Owner, usability session

No loading state existed between the click and the result. We added visible system feedback at every step, so the system is never silently working.

“I'm not sure what the AI is doing — if I knew, I'd trust the tool more.” — Product Owner, usability session

Trust was breaking down because the AI's reasoning was invisible. We surfaced its intermediate steps directly in the conversation instead of treating generation as a black box.

3.5

Benchmarking: Old vs. Re-skin vs. New

Old

Traditional form-based tool — project gate, manual field entry, no AI framing.

Re-skin

Visually modernized but functionally identical — still required project selection before intent, still separated “Create” and “Edit” as distinct paths.

New (conversational-first)

Intent-first landing, progressive context collection, AI reasoning surfaced inline, single workspace for chat, backlog, and refinement.

The re-skin comparison was a useful checkpoint — it proved that visual polish alone doesn't fix navigation or cognitive load; the underlying interaction model had to change.

3.6

The Final Experience

The shipped experience across the core stages of the workflow — from first describing intent through to a finished backlog.

Create Backlog

Users describe what they're building in plain language; the AI asks clarifying questions before generating a first pass.

Creating a backlog through the conversational surface

Refine Backlog

Refinement happens in place — no separate edit mode, no re-uploading documents to adjust scope.

Refining a generated backlog with visible history

AI Recommendations

Recommendations surface inline with a rationale, priority signal, and a clear accept/adjust/dismiss action.

AI-generated backlog recommendations, default view

Review & Apply

A dedicated review step summarizes everything the AI is proposing before anything is written back to the backlog.

Split-screen review before applying AI changes
3.7

Working Within the Design System

Backlog AI shares a single design system with the rest of the platform. Most of the work meant extending existing components with AI-specific states rather than inventing a parallel visual language — new patterns were added only where none of the existing components could honestly represent what the AI was doing.

Epic detail view built from shared design-system components
3.8

Bringing In Outside Context

Beyond file uploads, the AI can connect to live data sources — Jira, Confluence, Google Workspace — so it grounds its questions and generated backlog in what already exists, not just what's typed into the chat.

Connecting live data sources — Jira, Confluence, Google Workspace
04 / Result

What Changed

What shipped, and what it changed for the people using it.

Outcome

The redesigned experience established a clearer, more transparent workflow for creating and refining backlogs with AI while maintaining user control.

Impact

Improved Clarity

The workflow reads as one continuous thread instead of a series of disconnected steps, so intent isn't lost between screens.

Reduced Complexity

Fewer required actions to go from a plain-language description to a reviewable backlog.

AI Transparency

Every AI action now carries a visible rationale, so recommendations are easier to trust or correct.

Workflow Consistency

The same review-before-apply pattern now holds across every AI-assisted step in the product.

Metrics

0Faster backlog creation (days → 10–15 min)
0Backlogs generated
0User satisfaction

Before / After

The workflow shift, summarized the same way the rest of the product experienced it.

Before / after
Multi-step wizard Opaque AI generation Manual cross-checking
Conversational workspace Transparent AI reasoning Guided review & apply

What I Learned

01

Designing for AI means making uncertainty visible rather than smoothing it over — the moments I was tempted to hide were usually the ones users needed to see most.

02

Complex enterprise workflows respond well to progressive disclosure. Removing steps mattered less than removing the need to hold everything in your head at once.

03

AI should assist decision-making without removing user control — the best moments in this project were the ones where the system slowed down to ask, not just act.

Situation
An AI backlog tool that generated results without explaining them, inside a fragmented, multi-step workflow.
Task
Design an AI-assisted backlog workflow that stays understandable, controllable, and efficient.
Action
Rebuilt the workflow around a conversational surface with visible AI reasoning and an explicit review step.
Result
A clearer, more transparent backlog experience that keeps users in control of what AI applies.
Feedback
“Backlog AI gave me back my evenings. I'm no longer staying late just to write Jira stories — I'm using that time to talk to customers and think about the product.” — Product Manager, internal user on Backlog AI