Promo Scenario Co-Pilot
End-to-end retail promotion planning — from campaign brief to post-mortem analytics. Built in 14 hours at a hackathon.
The Problem
Retail promo planning runs on gut feel, spreadsheets, and last year's playbook. Marketing teams can't quickly model "what if we run 20% off for two weeks vs. buy-one-get-one for one week?" — they guess, launch, and hope.
The Approach
Six specialized agents covering the full promo lifecycle: Promo Briefing transforms natural language into structured campaign specs. Data & Baseline Forecast builds projections from historical sales. Scenario Lab compares 2–3 approaches with KPI estimates. Optimization Engine balances sales, margin, and profitability. Creative Companion generates asset specs. Post-Mortem Analytics evaluates actual vs. projected.
The 14-hour constraint forced ruthless prioritization — every agent had to deliver real value, not just exist. Phoenix Arize tracing let us debug agent decisions in real time during the hackathon.
The Result
Working end-to-end system in 14 hours. Full campaign lifecycle from natural-language brief to performance analytics.
My Role
Co-creator with Anton Iemelianov. Designed the agent architecture, built the FastAPI backend, and made product decisions about which agents were essential vs. nice-to-have under extreme time pressure.