AI product
Ramp Labs is Ramp's applied research group and research blog, covering AI systems for finance and related agent technologies. Its published work includes post-training Qwen 3.5 models for financial question answering, KV-cache compression and cartridge techniques, large agentic swarms for penetration testing, transfer between post-trained models, self-improving monitoring, and semantic tagging. Ramp Labs also publishes evaluations such as Ramp Accounting Bench, which tests models on accounting tasks using professionally created workflows and grading rubrics.
1 use taken from transcripts — each links to the moment in the video.
Ramp's applied research group, whose work went into products like Ramp Sheets (a spreadsheet agent for finance professionals), token spend management, and Ramp Router. Its blog publishes research on post-training a Qwen 3.5 model for financial question answering, KV-cache 'cartridges', agentic swarms of 10,000 parallel agents for pentesting, learning transfer between post-trains, self-improving monitoring, and semantic tagging.
1 in the library.