Plaky
Through this project we are transforming a static project management tool "Plaky" into an intelligent agentic system to eliminate manual data entry by the means of Generative & Agentic AI.
Role
Interaction Designer
Industry
AI Integration & Project Management Tools
Timeline
1 Month
2026
Team
AI used
Every experience speaks for itself
Source
This dataset reviews a Plaky's user feedback and simple analysis. It groups issues into categories to show common problems, especially to identify specific areas for improvement, while also including some positive feedback.
Gen AI Problem Statement
The Goal
Automatically generate meaningful task updates so users don’t need to manually write progress descriptions.
The Idea
AI drafts status updates and summaries based on chats and user input.
How
The system analyzes team conversations and uploaded files to draft contextual status updates and activity summaries for each item.
So we ideated...
Human-only brainstorming was conducted to explore possibilities, define flows, and map features including formats, error states, details, restrictions, and requirements. (Human-In-The-Loop)
Information Architecture
What if… Generative AI worked like a Proactive Project Coordinator?
A new AI-powered chatroom transforms everyday conversations into structured, actionable work.
AI Suggests. User Confirms.
A "suggestion card" appears in the chat, allowing the user to review, edit, or confirm the task details before they hit the board.
Confirmed & Synced
Upon confirmation, a visual task card is shared in the chat, and the item is automatically added to the corresponding project board.
The Problem
When one task slips, the project manager must manually move every dependent task, check calendars, and "guess" the new timeline. This creates a Management Tax, where more time is spent fixing the board than doing the work.
The Consequence
Because manual updating is tedious, boards are often left out-of-date, leading to missed deadlines and team confusion.
What if … An Auto-Rescheduler could reorganize timelines when delays happen?
The Auto-Rescheduler monitors user activity on board and system. When a delay occurs, it analyses dependencies and generates rescheduling options for the user to choose from.
Delay & Dependency Detection
The system analyses board data including deadlines, task status, dependencies, calendars, and workspace context to predict potential delays. A subtle nudge highlights these risks directly on the board.
AI Rescheduling Options
The system generates three rescheduling options earliest, balanced, and latest based on timeline constraints and dependencies. All options respect the project’s final deadline, while the user retains full control to select or dismiss them.
Together, Generative and Agentic AI transform the system from a passive tool into an active, intelligent workspace.
