Research Blog by Ramp Labs

Shared science from the Ramp Labs team.

PorTAL: Portable Task Adaptation for LoRA

Learn a task adaptation once in a base-agnostic form, then port it to new frozen models by refitting only a thin per-base alignment — recovering ~98% of per-task LoRA's lift on an unseen model within the same family and ~94% across families.

Finding high-severity security issues with publicly available models

We pointed 10,000 coding agents at Ramp's backend and found seven confirmed high-severity vulnerabilities. A simple, model-agnostic pipeline for scaling security research with publicly available models.

Coding agents ignore their own budgets

Agents can't be trusted to manage their own token budgets. Spend control has to live in a separate, evidence-grounded system outside the agent doing the spending.

How we built Agent Fill

The story behind Agent Fill - an AI agent that automatically fills out forms by understanding context, extracting data, and navigating complex workflows.