Ramp logo

How Ramp Uses Gemini

5 engineering articles about Gemini from Ramp's engineering team

Articles

Filter:
Ramp logo
Ramp
Beginner
How our LLM gateway uses Thompson sampling over lognormal latency posteriors to pick the fastest, most reliable model route per request
Ramp logo
Ramp
Intermediate
How we built an accounting benchmark to develop Ramp Stack, our agentic accounting assistant, and what we learned about frontier models, skill ablation, and memory along the way.
14 min read
Includes Code
--
Ramp logo
Ramp
Intermediate
Marketing to agents is becoming as important as marketing to humans. We ran an experiment embedding tracked incentives on ramp.com pages addressed to AI agents. Here's what we learned.
Ramp logo
Ramp
Intermediate
How and why we built a real-time AI spend and usage pipeline for finance teams.
9 min read
Includes Code
--
Ramp logo
Ramp
Intermediate
How we compare the performance of large language models on real financial tasks at Ramp, and why benchmarks built for production use cases matter.
10 min read
--

You've reached the end! All 5 articles loaded.