Back to Devoured - October 21, 2026
DEVOURED
Building Laminar: Ramp's Managed Agents Platform

Building Laminar: Ramp's Managed Agents Platform

AI Ramp
Ramp built 'Laminar', an in-house agent harness designed for production observability, multi-tenant security, and session management.
What: Laminar features a custom interface for tool calling, message steering, session compaction, and observability. Developed in six weeks by a small team, it demonstrates the trend of large organizations building proprietary 'harnesses' to standardize agentic product development.
Why it matters: Even as generic agent frameworks improve, companies like Ramp are opting to build bespoke infrastructure to ensure they have the observability and security controls needed for high-stakes enterprise workflows.
Decoder
  • Harness: In the context of LLM agents, a software wrapper that manages the execution environment, including tools, session history, and model interaction logic.
Original article

Laminar is an in-house agent harness for Ramp's agentic products. It features secure conversation history storage, session compaction, standard interfaces for tool calling, message queuing and steering, subagents, multiplayer chat support, observability tooling, and much more. The first version of Laminar was built in six weeks with a small team of obsessive, experienced engineers who worked with and steered the agents. Its code was generated entirely by agents using the most powerful models available at the time. While building in-house has become cheaper, Ramp still needs good engineers to be on-call, keep the platform healthy, and figure out what product teams actually need and how it fits into the bigger picture.

Explore all 55 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi