Ramp engineering blog

Loading
Agentic Credit Analysis
Ramp's engineering team describes an agentic pipeline that makes autonomous credit decisions by analyzing financial statements. The post covers how the system is designed to automate credit underwriting using agent-based workflows. The body provided is largely unreadable metadata, so this summary is based on the title and feed summary only.
Building Laminar: Ramp's Managed Agents Platform
Ramp's Builders blog post introduces Laminar, the company's in-house agent harness, built after evaluating agent platforms on the market and deciding to own the core loop. The article body could not be read, so this summary relies on the title and page metadata only, and its technical depth is unverified.
How we built OCA, our AI on-call assistant
Ramp describes OCA, an AI on-call assistant that investigates incidents, recommends next steps, communicates through Slack, answers follow-up questions, and prepares code fixes.
Integrations That Write Themselves
The post explores integrations that can be generated and maintained autonomously. It highlights an agentic approach to reducing the manual effort required to build integrations.
Apache Arrow Cut Snowflake Fetch Memory Growth by Up to 79%
The post explains how replacing row-by-row Snowflake result materialization with Apache Arrow reduced fetch-memory growth by up to 79%. The change doubled the usable training-data window for an ML workflow without increasing cluster size.
Agentic Risk Operations
Ramp describes its plans for building agentic risk operations and the direction of its program.
Stack Benchmarking
Ryan Stevens explains how Ramp built an accounting benchmark for its agentic accounting assistant, Stack. The post examines frontier-model performance, skill ablation, and memory design.
Agentic identity: modeling agents to keep users in control
The post introduces agentic identity as a way to model software agents acting on users’ behalf. It explains how this approach can help finance teams adopt agents while preserving user control in increasingly autonomous organizations.
Financial Benchmarks
Ramp compares large language models on real-world financial tasks and explains why production-oriented benchmarks are more useful than generic evaluations. The post highlights how task relevance and operational context can improve model assessment.
An Internship on Ramp’s Forward Deployed Engineering Team
The post recounts Alex Noviello’s internship on Ramp’s Forward Deployed Engineering team, including work on automatic hotel receipt retrieval. It offers a high-level view of the internship and engineering problem without technical implementation details.