Programmatic Advertising Platform

AdTech · Programmatic Advertising Platform · 2019–2026

Role

Lead Product Designer

Span

2019–2026

Surface

DSP recommendation UI

Planning

2 wks → 3 hrs

Status

Shipped · under NDA

Reconstruction — anonymized, rebuilt from memory for illustration · client under NDA

High confidence Medium Low

Recommendation · Campaign 7 ACT

Shift evening budget toward Channel B — stronger projected reach this week.

model confidence 92 · the verb is the interface, not the number

Why this call

30-day channel performance

Audience overlap with target segment

Inventory price trend

Override this call

Overridden — logged · feeds next week's model

Interactive · data shown is illustrative, not client data

The scoreboard said the algorithm beat the traders. The traders read the scoreboard and played their hunches anyway. That's not a modeling failure — it's a missing interface. Client is under NDA — decisions and outcomes on a call.

The engine outperformed the buyers, and visibly so. Adoption sat near zero anyway.

The engine handed down verdicts without arguments. A bare number asks for faith. Traders deal in collateral, not faith, so they ignored it.

So I built three things. A confidence score that resolved to one of three verbs — act, review, or ignore — and never reached the screen as a naked 87%. A reasoning panel that named the exact signals behind each call. And an override that logged the correction and fed it into next week's model. The override was the hinge. The first time a buyer watched their own pushback sharpen the following week's calls, the relationship flipped from fighting the model to coaching it.

Campaign planning dropped from about two weeks to three hours. The model never changed. The humans finally bet on it.

Want to know more about this work?

Hiring? In an interview I'll walk you through the decisions, the artifacts I can't host publicly, and the numbers — under mutual NDA.

Send me the role

Arpit consistently demonstrated exceptional speed, creativity, and attention to detail… What stood out most was his ability to present multiple design options along with clear pros and cons, which made it much easier for different stakeholders to make informed decisions and align quickly. I highly recommend Arpit and would be delighted to work with him again.

Design Patterns Used in This Case

This project is where the Act / Review / Ignore rule was forged — and it directly informed three core patterns now used across multiple AI products:

• The Act / Review / Ignore Rule: every confidence score bound to one action — act, review, or ignore — with a reason for every review and an override for every act.
• Confidence Score Patterns: All confidence visualization techniques used here — numeric, color, language, gauges — became the foundation of the Confidence Score Patterns library.
• Human-in-Loop Patterns: The override and feedback mechanisms became core examples of keeping humans in control when AI makes recommendations.
• ML Explainability Patterns: The reasoning surfaces and feature importance visualizations that buyers used to understand algorithm decisions directly informed the explainability patterns library.

I write about this on The Trust Layer ↗