Paid Media · Case Study
How AI-Powered Descriptions Helped Our Client's PPC Ads Break Through Google's Shopping Feed
Note: Due to our contracts, the client in this case study must be anonymous.
Client Background
Our client is an animal health retailer and technology services company with veterinary clinics across the United States. They provide various animal health products — pet medications, practice management solutions, and related services — to support veterinarians and pet owners.
To drive incremental sales for their veterinary clinic partners, our client partnered with Greenlane to launch a large pilot project spanning Google Search, Display, Shopping, and Meta campaigns across 24 veterinary clinic storefronts nationwide.
The Challenge
The Google Shopping campaigns were limited in reach and visibility. The pet pharmacy space is highly competitive — multiple sellers offering identical medications, varying price competitiveness, and a mix of prescription and non-prescription items. Our client's ads struggled to break through, leading to low impression share, underwhelming click-through rates, and low sales.
After analyzing performance data, our team discovered a significant issue: Google's algorithm struggled to match our client's ads with relevant searches due to the quality of their product feed. Incomplete, auto-populated "boilerplate" descriptions on thousands of SKUs gave Google no additional context beyond the item title. Since Shopping relies heavily on product descriptions for keyword matching, our listings were deprioritized against competitors with richer feed content.
An example of a pre-optimization description:
Capsule size, color, shape, markings, or banding may vary from pictured image. Capsule – Quantities that exceed 180 days supply will not be processed and will create a delay in your order.
The client's feed contained over 8,000 SKUs, with 4,500+ needing optimization. Manual rewrites would have outlasted the pilot project entirely.
The Solution: AI Prompt Engineering at Scale
Instead of manual labor, we leveraged AI prompt engineering to revamp product descriptions at scale without sacrificing quality.
Building the AI Workflow
We cross-referenced trusted pet-focused resources (Chewy, PetSmart, and similar) to gather key product attributes: features, ingredient lists, health conditions treated, and benefits. The AI was instructed to include condition-specific terms — for example, every dog dewormer description should include "deworming" and enumerate the specific worm types treated (heartworm, tapeworm, roundworm, etc.).
Iterative Fine-Tuning
Outputs were reviewed for positive and negative examples. Well-written descriptions were reinforced; vague or non-compliant ones were flagged and used to correct the model's outputs. Vocabulary to include and avoid was clarified, with tone explicitly focused on pets rather than humans — critical for pharmaceutical products that exist in both human and veterinary markets.
Compliance & Accuracy
A carefully crafted disclaimer was appended to each description, clarifying the product's intended use for pets. This guided Google Shopping to match products with pet queries rather than human searches for the same medications. Team members spot-checked each other's work until the group was confident in quality and accuracy.
An example of an improved description:
Alendronate (from Sodium) in Almond Oil Suspension SF is specially designed for dogs to promote bone health and manage conditions like osteoporosis. This formulation delivers 5mg of Alendronate per mL in a palatable almond oil base, making it easy to administer. The 30mL bottle provides an ample supply for your pet's ongoing treatment needs. This product is intended for dogs only. Always consult your veterinarian before use to confirm it's suitable for your pet's specific condition.
The Results
The new descriptions were packaged into a Supplemental Feed for Google Merchant Center to override the original feed inputs. Impact was immediate and measurable:
- +52% impressions and +50% Shopping clicks after descriptions began rolling out in late October vs. an equal prior time frame.
- Clickthrough rates held steady across both periods, confirming that user intent quality was maintained despite the larger available search pool.
- +9% Impression Share and +13% Click Share — campaigns qualified for more available Shopping searches and captured a greater portion of that traffic.
- A second wave of description updates reinforced the gains, pushing impressions and clicks to their highest levels entering November.
Conclusion
This AI workflow produced optimized product descriptions that followed best practices, improved ad performance, and maintained accuracy across thousands of listings — all in just a few weeks. It's a repeatable approach that scales to any product catalog size.