Merilin Ekzarkova

Work

Built a live dashboard tracker for client trials, kept up to date by an AI agent

Head of Product and Design · a health app · 2026 · client:

Sketch of a trial tracker: a score out of 100, a bar for each day, a weekly report and four data sources 72 score out of 100 active members, day by day Weekly report Approve Sign-upsApp useSurveysChat
Sketch with made-up numbers, not the real screen.

Problem

Trial data lived in four separate systems and was consolidated retrospectively. brought together once the trial had ended.no daily view

A participant who disengaged stopped using the app in week one showed up in the numbers only after the trial closed.

Solution

A daily consolidated view of engagement and retention, maintained by an AI agent following a documented procedure. The page computes a composite trial score and drafts a weekly report, gated by human approval. and a person says yes before it goes anywhere.about ten minutes a day

It came with a written guide, so a colleague could run it.

What it showed in the first weekit showed everything

Retention, engagement, and what each participant was doing hour by hour, all anonymised.

  1. Non-returning participants.
  2. Cross-system differences in counting. Places where two tools counted people and activity differently.
  3. A logged failure event with no user impact. An error nobody actually saw.

Previously, all three would have surfaced post-trial, at the end, or not at all.

The rules I built in

← All work