Akooda
AI-powered platform that helps organizations unlock company-wide insights.
company
Akooda
role
Product Designer
Timeline
12 Weeks
COllaborators
Product Manager, Developers
About Akooda
Akooda is an AI-powered ops intelligence platform that connects organizational data, conversations, and workflows through APIs, helping teams understand what’s happening across their organization in real time and share insights effortlessly.
The project & the impact
At Akooda, we set out to reduce the time teams spent chasing context. I designed AI-driven features that surfaced answers in place - summarizing conversations, showing key interactions, and embedding insights where work happens. We cut down search time by 75%, helping users stay focused, move faster, and make smarter decisions.
Project Goal
Develop an AI-powered personalized summary tool that analyzes interactions, incorporates sentiment, and delivers trustworthy, contextually relevant answers derived from the source of truth in seconds.
Meet The Interactions Drawer
The Interactions Drawer is accessible throughout every page in the platform and is collapsible to allow reviewing the interactions within the each page's context.
What users wish they could do
As a small startup, we have the advantage of engaging with our clients on a bi-weekly basis. During these meetings, we asked clients to share their experiences using Akooda and suggest areas for improvement. What users wished they could do:
01 Comprehensive Overview
Bird-eye view of a project, topic, or account they are involved in.
02 Personalized Analysis
Highlights the status of various topics and provides updates on upcoming or ongoing action items.
03 Key Insights
Get the next steps and important insights based on specific interactions.
04 Ask Anything (Future Effort)
Ask open-ended questions in search bar.
In the first phase, we chose to focus on options 1, 2, 3 as a baseline, aiming to deliver the best user experience in a short timeframe.
Key Feature Guidelines
Stick to familiar AI patterns
Seamlessly integrated and easily discoverable
Answers - sentiments, credibility, context
Feedback loop - to improve our engine
Generate answer within 5 seconds
Feature Location - Component & Placement Exploration
Based on feature guideline and user flow, I explored the best practices for the feature's location and interaction type such as button, toggle or tabs.
Hi-Fi Mock-Ups
To verify the wireframes, I quickly created a few Hi-Fi mock-ups to test ease of use, clarity, visibility and the space the answer and data takes altogether.
Toggle your way to AI summary
The decision to use a toggle instead of the alternatives was based on its space efficiency, intuitiveness, and ease of allowing users to switch between two states.
Summary Refinements
Exploring the display of sources, engaged people, topics and organizations, and feedback loop.
Final Result Delivery
After 12 weeks of development, we launched Akooda AI as a BETA. Once validated, it was rolled out to all users, improving general search time by 75%. Following its success, we introduced it in every organization profile page and as a Slack bot, marking the second and third phases of the feature.
What We Solved
01 Cut down general search time by 75% by minimizing interactions mining.
02 Keep interactions in context, no extra clicks or external app detours.
03 Minimize cognitive load and visual noise by surfacing only relevant interaction details next to the summary.
Second Phase Delivery: Organization Profile Page
After defining the interaction table, we easily moved to the next stage of the AI feature: adding a summary to the organization page. This summary provides an overview of the profile, based solely on the latest 3 interactions related to the organization.
Third Phase: Integrating Summary feature to Akooda Slack Bot
When last two phases completed, we integrated the feature into our Akooda Slack bot, allowing users to stay within their work environment and quickly get the gist they were looking for.
Key Learnings & Future Efforts
After the successful launch, we gathered qualitative feedback through bi-weekly meetings with champion clients and quantitative insights from user sessions. Here’s what we learned:
01 Bullet Points
Users wish to be able to scan the text quickly and get to insights fast.
02 Open-Ended Questions
Users were still interested in asking open ended questions to get to the answers faster.
03 Add Hyperlinks
To get a better context, users asked to include hyperlinks to relevant sources within the textual answer.
04 Share Answers
User wish to share their answers with their colleagues in different apps such as Slack, email, etc.
The team is constantly gathering feedback and improving the AI features in the platform to give users the best and seamless experience as possible.
At-a-glance to the next AI feature designed for Akooda
Delivering insights and data directly in context through a Chrome extension. By integrating with users’ existing workspace, we simplify their workflow and remove the need to switch platforms.
