The Challenge
The initial brief came from the product team: “Enable users to ask questions about their workspace in plain language.” That was it! no specific success metrics, or guiding principles beyond “be helpful.”
Designing an AI-Assisted interface
Plane is a modern project management tool built to help teams plan and execute work effectively. As teams grew, one major gap became clear: users, especially admins and project owners, didn't have an easy way to understand what was happening across their workspace at a glance.
TIMELINE
Jul - Aug 2025
TEAM
Sibira Gopal Shivangi Jain 1 PM and 3 Developers
MY ROLE
I conducted user research, developed end-to-end solution & prototype, and participated in QA testing up until the go-live date.
About Plane
Plane is a project management tool scaling for startups to enterprise level. It's a B2B SaaS product, directly competes with tools like Jira (Atlassian), Linear, Monday etc. It aims to simplify managing and assigning workflows internally in an org and also maintaining visibility with clients.
Compiling customer problems
I reviewed support tickets and feature requests, talked to a few active users, and spent time in our own Plane workspace watching how the team used grouping day-to-day. Major requests people kept getting into:
Analytics isn't much helpful, the graphs are fine, but we need something quick to discuss over.
Organizing and handling multiple teams and projects is a task, and my work has low visibility.
Pages is a nice feature, but I rely heavily on external AI tools to write PRDs, without that it's a waste.
Multiple managers work on same board and create repetitive tasks, at times assigned to different ICs.
Is the product reliable? I don't want my team to invest their efforts in the tool than the work itself.
Existing tools already have the AI support that helps me summarize and analyze projects better.
Defining goals
Key design questions I defined early on:
- What tasks do users really want to accomplish via AI?
- When does typing become easier than just filtering?
- How can responses reduce cognitive load instead of adding noise?
Instead of a generic chatbot, we redefined Plane AI as an assistant; a tool that helps users answer questions, analyze progress, and surface insights without deep dives into UI filters.
Understanding user personas
Manager / Scrum masters
- - Primary concern is workflow — making sure work moves smoothly.
- - Constantly scanning for bottlenecks and dependency on them.
- - Their biggest frustration is when the board doesn't reflect reality.
→ issues get stale, statuses aren't updated, and they waste time asking "is this actually in progress?" in Slack. - - The tool gives them control, but doesn't give them clarity.
PMs or team leads
- - Who's working on what? Is anyone overloaded? Who has capacity?
- - Answerable to stakeholders: "When will this feature ship? Who's working on the integration?"
- - Biggest pain point is visibility gaps. Someone might have 15 issues assigned, but 10 of them are blocked or low-priority.
- - Tool shows assignments, but not actual capacity or progress.
Individual contributors
- - What do I need to focus on right now?
- - They group by priority or filter to show only their assigned issues, sorted by due date.
- - Their view is personal and immediate — they're not looking at the whole project, just their slice of it.
- - With a new task added, their mental prioritization is scrambled. They want the tool to help them stay focused.
- - Stuck on KT or dependencies to get done with their tasks.
Insight - 1
Users weren't just asking for more grouping options instead they were struggling with context switching and information overload.
Insight - 2
The tool was flexible, but it forced them to constantly reconfigure their view to get the information they needed. These questions helped pivot the brief from “add chat” to “augment insight discovery and reduce friction.”
These insights moved the focus from:
FEATURE → WORKFLOW
OUTPUT → DECISION-MAKING
NOVELTY → RELIABILITY
Competitive research
Major products in the market were for coders, designers, generalists etc. But project management tool having AI as chat, canvas and agent was still evolving.
Solutions
Phase 1 — Simple Query Interface
We initially built a basic chat overlay where users could type questions and see responses. Early prototypes focused on handling simple queries like “show recent bugs” or “what tasks are overdue.”
It easily solved users queries related to any particular project or gave a wholistic view quickly.
They could choose an existing task, document, or project to get the analysis and progress.
Users expected actions after answers, not just text responses.
Phase 2 — Contextual Interaction
Next iteration integrated context awareness:
- The AI recognised the active workspace or project.
- Results referenced issues with links back into the UI.
- Users could attach screenshots or docs for richer queries.
For richer experience, the chat became an assistant to help quickly perform actions like write a doc, create a task etc.
Even here, we slipped into overly textual responses that didn't help users take action, a common early-version trap.
Phase 3 — Task-Oriented Queries
We emphasized task outcomes in the conversational UI, e.g., “show me all high-priority issues blocking this cycle” turned into a structured list with links back into the workspace. At this stage, user feedback highlighted another tension: clarity vs. verbosity. We iterated on response design patterns; concise bullets with optional expanded explanations.
Concept 1: Alerts user for potential duplicate tasks, reduced 38% of repetitive tasks.
This was a small experiment to understand user behavior and the need for AI agents in a project management tool and it proved to be a success.
Concept 2: Aimed for structural and cleaner UI, to incorporate complex actions.
The canvas feature was introduced to create Plane entities directly from chat, with better editing capabilities.
Additional UX delights
Decision 1-Ambiguous Queries
Free-form natural language is inherently ambiguous. “Show overdue tasks” could mean different things depending on filters, projects, or views.
SOLUTION:
We designed disambiguation prompts and offered filter suggestions to refine queries. If the AI wasn't confident, it asked clarifying questions before answering.
Decision 2- Balancing Accuracy and UX
There was a high chance of responses feeling helpful but being technically imprecise.
SOLUTION:
We invested in previewing reasoning behind results, surfacing the logic, so users could understand why a certain set of tasks matched their query. This transparency built trust and helped users refine their questions.
Decision 3- Designing for Read-Only at Launch
Originally, the read-only design (no automatic write capabilities) limited the assistant's usefulness.
SOLUTION:
We focused instead on insight amplification. By steering users toward more actionable queries and linking results back to the core Plane UI, users still felt productive without the AI performing automated actions (which came later in the roadmap).
Outcomes
Plane AI launched as a conversational assistant capable of:
🔍 Reading the page, the project, and the cycle you're in. It sees what's at risk, what's blocked, and what needs attention. No setup prompt or context dump required.
✅ Linking responses back into the workspace to reduce clicks and duplicates were caught before creation of new task.
⚒️ Summarize, rewrite, expand, or translate any block. Right inside the editor.
📈 Helping users uncover insights without complex filters or manual queries.
Though quantitative metrics are internal, qualitatively users reported less frustration with navigating complex workspaces and a noticeable reduction in time spent on analysis tasks. More importantly, the design set expectations for future iterations, including action execution and iterative refinement of conversational flows.
Intrigued?
Let's connect to discuss more about the AI agents, workflows and what the final designs looked like.
