All workFILE 04 / 04

DTC & commerce

AI video ad production pipeline

Shipped at Ad Platform (in-house) · led by Parik Ahlawat

01

The problem

DTC brands need fresh video ads faster than a human team can script, shoot, and cut them. Creative volume is the bottleneck on every ad account.

02

The constraint

Volume can't come at the cost of the brand: nothing runs on an ad account until a person has seen it, so the automation has to leave a clean approval gate.

03

The system

A 13-state production pipeline that scripts, generates across 11 video models, and voices ads end to end, with human approval gates before anything reaches Meta Ads.

FIG. 01 · SYSTEM FLOW · 7 NODES · 7 FLOWS

Brand & product brief → Scripting model. Scripting model → 11 video-gen models (shots). 11 video-gen models → ElevenLabs voiceover. ElevenLabs voiceover → Human approval gate. Human approval gate → Meta Ads launch (approved). Scripting model → 13-state pipeline log. Human approval gate → 13-state pipeline log (state)

04

The human in the loop

A human signs off before any ad launches; the pipeline handles the 13 states around that decision, not the decision itself.

05

The outcome

A pipeline that lifted weekly ad output 5×, with a human signing off before anything launches.