Abundant data, scarce insights?—Orchestrait

Empowering employees to query enterprise data in natural language & get quick, actionable insights.

Veloceo

Veloceo

2 months+

2 months+

Enterprise AI

Enterprise AI

Lead Product Designer

  • User research

  • MVP definition

  • UI Design

  • User testing

  • QA

Lead Product Designer

  • User research

  • MVP definition

  • UX/UI Design

  • User research

  • MVP definition

  • UX/UI Design

Product Owner

AI Architect

Offshore dev team

CTO

CEO

Problem

Problem

In today’s fast-paced enterprise environment, employees struggle with accessing & analysing vast amounts of data quickly & efficiently. This leads to delays in decision-making & reduces productivity.

In today’s fast-paced enterprise environment, employees struggle with accessing & analysing vast amounts of data quickly & efficiently. This leads to delays in decision-making & reduces productivity.

Goal

Goal

To enhance operational efficiency, reduce costs, & empower executives with actionable insights that align with their strategic objectives.

To enhance operational efficiency, reduce costs, & empower executives with actionable insights that align with their strategic objectives.

Solution

Solution

An AI-powered platform designed to simplify complex data. It consolidates information from various sources, analyses it, & presents tailored insights to each user. For employees, this means quicker, more accurate decision-making. For IT teams, Orchestrait offers a secure & manageable backend, & for executives, it provides the high-level insights needed to guide strategic decisions effectively.

An AI-powered platform designed to simplify complex data. It consolidates information from various sources, analyses it, & presents tailored insights to each user. For employees, this means quicker, more accurate decision-making. For IT teams, Orchestrait offers a secure & manageable backend, & for executives, it provides the high-level insights needed to guide strategic decisions effectively.

Discovery

2

Internal workshops

Internal
workshops

12

Interviews

3

Ethnographic
walk-throughs

What we found…

We began with an in-depth exploration of the challenges faced by our target clients—large enterprises in sectors like mining & resources, financial services & public services.

01

02

03

04

Abundance of data—but scarce insights.

01

Data security & compliance cannot be compromised.

Data security & compliance cannot be compromised.

Data security & compliance cannot be compromised.

02

The tool must be easy to use & integrate seamlessly into existing workflows.

The tool must be easy to use & integrate seamlessly into existing workflows.

The tool must be easy to use & integrate seamlessly into existing workflows.

03

Executives need actionable insights to make informed strategic decisions.

Executives need actionable insights to make informed strategic decisions.

Executives need actionable insights to make informed strategic decisions.

03

User personas

User / stakeholder personas

Design

A reflection on genAI UX

Before diving into designing this product, I wanted to do extensive research on existing genAI products.

It’s clear that UX design often gets sidelined in AI development, with companies racing to deploy features rather than ensuring a seamless user experience. This rush leads to products that fall short of user expectations, resulting in clunky, confusing interfaces.

Most of the issues are failure to meet fundamental UX principles—like Jakob's 10 usability heuristics.

This deep dive helped me identify common pitfalls to avoid and find design inspiration for a better generative AI user experience.

People are bad at prompt writing.

Unclear feedback loops.

Disjointed workflows.

Inconsistent UI patterns

Some key design choices we wanted to hit…

Allow the user to direct the AI on where to focus

Don't rely on natural language interactions.

Personalisation & contextual workflows

Facilitation of team collaboration

Wolfram Alpha's topic selection

Perplexity's focus selection

Grammarly's plug-in & Canva's magic write

Apple's Siri suggestions

Figma's tone adjuster

Slack's project summaries

Although, this might seem like an extra click, we found this is what yields the best results, alleviating some of that user frustration from bad outputs.

Natural language is powerful, but it shouldn’t be the only way users can interact with AI. Alternative input methods can go a long way to prevent prompt writing meltdowns.

Contextual AI can anticipate user needs based on their current or previous actions, offering suggestions or completing tasks with minimal disruption to the workflow.

A lot of existing AI tools are siloed, but I want Orchestrait to enhance collaboration by making it easier for team members to share insights & collectively train their AI models.

Perplexity's focus selection

Wolfram Alpha's topic selection

Figma's tone adjuster

Apple's Siri suggestions

Grammarly's plug-in & Canva's magic write

Slack's project summaries

Future State User Journey

Some high level flows were created to align the team's design process.

Broad end user flow

Broad IT user flow

UI design

Low-fi sketches

High Fidelity

High-fidelity UI design is currently in progress.

We’re building an MVP version of Orchestrait within our existing product, Relait, to test its capabilities and gather preliminary user feedback.

In parallel, we are continuing to design the standalone product. Our current focus is on the configuration interface, ensuring IT professionals can seamlessly set up connections & manage Orchestraitors (AI-powered co-pilots).

This approach will allow us to incorporate feedback of the UI from Figma prototypes, as well as feedback of the AI experience from the Relait MVP.

Learnings

Balancing Sales Priorities with User-Centric Design

Balancing Sales Priorities with User-Centric Design

A key challenge in this project was finding the right balance between the CEO’s sales-driven focus and my commitment to user-centric design. While the CEO prioritised marketability, I emphasised the importance of understanding the problem and user needs to ensure we weren’t creating something no one wants. I believe a human-centred approach guides us toward marketability.

To align our efforts, I guided the team through the persona exercise to ensure we were broadly aligned and understood who we were designing for. It was helpful that our personas roughly embodied DVF—desirability (end users); viability (customers); and feasibility (implementation partners and IT departments). I then directed the team to focus on what the product delivers to the end user and how they might like to experience it.

During this exercise, I introduced a method of documenting our assumptions, with the agreement to validate them later rather than getting bogged down in minor details early on. This method kept us focused and helped prevent us from spreading ourselves too thin.

We were then able to break off to validate our assumptions individually—me on design, our CTO and AI architect on feasibility, and our CEO and product manager on viability, collaborating along the way. Ultimately, it enabled us to overcome the initial hurdle of spinning our wheels while trying to solve everything all at once.