Anthropic's growth marketer cut ad creation from 30 minutes to 30 seconds with Claude Code
A growth marketer at Anthropic with no coding background used Claude Code to build a Figma plugin for ad creative and a Google Ads copy workflow. Ad production went from about 30 minutes to about 30 seconds per ad.
- Organization
- Anthropic
- Industry
- AI
- When
- Jan 2026
- Evidence
- Vendor case study
- Agents and tools
- Claude CodeFigmaGoogle Ads
Reported outcome
Work that took about 30 minutes per ad now takes about 30 seconds; the plugin can make up to 100 ad variations at once.
- ~30 min → ~30 secTime per ad
- up to 100Variations per run
Caveats
Published by the company that sells the agent. Treat numbers as marketing until confirmed elsewhere.
- Anthropic makes Claude Code, so this is a vendor story about its own team.
- Time saved is self-reported by the marketer. Ad performance results are not given.
What the agent does
Two workflows:
- Ad copy. The agent reads a CSV of current ads and results, finds weak ads, and writes new headlines and descriptions within Google Ads character limits. It exports an upload-ready CSV.
- Ad creative. A Figma plugin finds ad frames and swaps in new headlines and descriptions, making many variations in one click.
Why it matters
The builder was a marketer, not an engineer. Before, each variation meant copying frames and pasting text by hand. The agent removed the copy-paste work.
What to copy
- Look for jobs where you copy and paste between two tools. Agents remove that well.
- Put hard limits (character counts, brand words) in the prompt and check them in code.
- Keep a human picking the final ads.
Starter prompt
Written by us.
Here is a CSV of our current ads with impressions, CTR, and conversions:
{csv}
1. List the 5 weakest ads and say why in one line each.
2. For each, write 3 new headlines (max 30 characters) and 2 descriptions
(max 90 characters). Count characters and show the count.
3. Never use these words: {banned_words}.
4. Output a CSV with columns: ad_id, headline_1..3, description_1..2.
Sources
- How Anthropic's Growth Marketing team cut ad creation time from 30 minutes to 30 seconds — Anthropic, Jan 2026
- How Anthropic teams use Claude Code — Anthropic, 2025
Added Oct 16, 2026. Spotted an error? Send a correction.
Get new use cases weekly
One short email. Sources included.
Related use cases
Spotify's Honk background agent merges fleet-wide code migrations: 1,500+ PRs and counting
1,500+ merged AI-generated PRs; 1,000 merged PRs took three months at first and about ten days later on.
Rakuten engineer let Claude Code work alone for 7 hours on a vLLM feature
Seven hours of mostly autonomous coding in one run. Rakuten reports 99.9% numerical accuracy versus the reference method.
Amazon says its Rufus shopping assistant is on track for $10B+ in extra yearly sales
Amazon expects over $10B in annualized incremental sales; shoppers who used Rufus were 60% more likely to buy.