I lead the design of AiDA (Ansarada’s AI agent) as a Senior Product Designer.
I launched AiDA with our team in October 2025, evolving her from being a simple pre-prompt based chatbot to now, an increasingly nuanced AI assistant who provides rich insights to customers inside the Ansarada platform.
AiDA is now being used in 25% of all live subscriptions in Ansarada, up 2x from launch.
How can we leverage AI to help customers reduce or eliminate administrative work in a high-stakes M&A or Procurement deal?
Human error is extremely costly in M&A. How can we leverage AI to reduce this possibility and risk?
My design process
Establish a shared problem
Our team and I only had a tight runway of 6 weeks to design and launch AiDA, however we didn't have a clear understanding of what LLM's could do back in October 2025 or what our MVP was going to be.
To address this gap, I researched and catalogued all of the different response types best-in-class LLM’s could generate, mapping those outputs to data sources we could connect in Ansarada.
I translated my observations into a capability map, plotting how user prompts in AiDA would translate into outputs. I leveraged this artefact to guide our team and helped establish must-haves and nice-to-haves for AiDA's launch and roadmap.
Designing in parallel with Engineering
With the scope and AiDA's capabilities defined, the next challenge was iterating designs quickly to enable Engineers to start technical estimations and development.
I led daily design reviews with engineering, product and senior leadership to gain clarity and alignment.
Together, we stress-tested interactions, validated the feasibility of designs and locked down the scope our deliverable as a collective.
By running together with Engineer and senior stakeholders and establishing clear deliverable, it created space for myself and our Product Manager to tackle onboarding and activation.
Driving quality of response
To ensure we launched on time, our team compromised on AiDA’s initial capabilities. AiDA could only provide answers based on a set of pre-written and controlled prompts at launch.
However, AiDA needed to become a dynamic and intelligent assistant grounded with context and not just be a basic chatbot.
To move towards this direction, I extended and embedded myself in quality assurance rituals, testing AiDA and refining her underlying system prompt. This gave me the opportunity to influence and challenge stakeholders on what quality meant and the vision.
To created further momentum, I created a coverage checklist of the key reports and databases, identifying a set of must-have and nice-to-haves reports and databases to unlock. This artefact has been essential to how we systematically improve AiDA and how we inform GTM on releases.
Outcome
Most recently, I owned and launched AiDA on a platform level. This is a significant and strategic evolution, as it's the first step to prompt first deal making, enabling Ansarada customers the ability to source answers from any data room from one place.
