EmbryoNet AI Technologies
I helped turn a validated AI and microscopy technology into a laboratory-facing software product: from product vision and UX architecture to prototypes, delivery, and client-specific workflows.
Actual screens can be blurred or reconstructed due to confidentiality.
Context
I had been close to the project for years, helping with smaller visual and presentation tasks. In 2024, I joined as a core product contributor, when the research, publications, AI models, and computer vision foundation were already strong.
What was missing was the product layer: no laboratory-facing software, no interface for interacting with the microscope, no website, and no coherent product narrative for demos, conferences, and potential clients.
Users & workflow
The users were scientists in small and mid-sized laboratories, plus research teams inside a large pharmaceutical client. Their main task was to test new drugs and compare which experimental conditions looked most promising.
Before entering the software, they prepared samples, chose experiment conditions, placed samples into plates, and defined observation parameters. The interface had to reflect this physical laboratory process instead of forcing it into generic dashboard logic.
Product scope
Onboarding, project creation, sample setup, experiment conditions, microscope configuration, admin and settings.
Dashboard, image/video analysis, time-series viewer, model segmentation, deviation detection, and comparison views.
Reports, statuses, alerts, error states, client-specific workflows, and preparation of results for downstream use.
Actual product screen, blurred or cropped.
Sanitized reconstruction showing the logic without exposing sensitive details.
Key decisions
Scientists needed to trust AI-assisted analysis in a serious research workflow. I structured the AI experience around visible analytical steps: time sequence, segmentation, detected deviations, comparison, and report preparation.
Before the experiment, users needed control and validation. After the experiment, they needed comparison and interpretation. I separated the product into setup and analysis workspaces.
In a hardware-connected workflow, users need to know what is configured, what was sent to the microscope, what is running, what failed, and what is ready for analysis.
I designed a core workflow flexible enough to adapt selected processes for specific clients without rebuilding the product from scratch each time.
Leadership & delivery
I led a small product team of four people: myself as CPO / Product Design Lead, plus three developers across frontend and backend. My role was to translate scientific and client needs into product decisions, prototypes, development tasks, and iterative software releases.
Deep immersion at the start, then focused calls whenever a feature needed scientific clarification.
About one week observing the current process, one week designing, then roughly two iterations before development.
Prototypes as shared specifications, Trello tasks, daily calls, and AI-assisted tools for faster exploration and tests.
Results
The project moved from a scientifically validated technology toward a working software product that could be demonstrated, tested, customized, and used with real partners and clients.
The broader EmbryoNet technology is positioned around 91% AI accuracy, 10x faster analysis, automated microscopy, real-time and batch processing, and time-series phenotyping.
The design outcome was confidence: users could follow the process, understand system states, and rely on the interface while moving from manual laboratory work to automated AI-assisted workflows.
Reflection
Product design here was translation: from science to software, from laboratory practice to interface logic, from AI capability to a workflow people can trust.
The most meaningful part was contributing to a tool that can help researchers study complex biological processes faster and with more confidence.