Forward Deployed Engineering at Ramp: Scoping and Agents
- Source
- youtube.com
- Author
- AI Engineer
- Date
Context
Ramp's customer-facing engineers use an to clarify incoming feature requests before turning them into specifications. In the team's account, requests varied from detailed explanations to a single line. A Notion agent began by asking follow-up questions, then evolved to conduct several exchanges before preparing a specification.
The speaker estimates that this saved about one-fifth of the team's scoping time, while acknowledging that harder work remains in assembling product and deciding what to build. The concrete advance is earlier clarification: submitters can answer missing questions immediately, so engineers receive a better-developed request when they exercise judgment over the final scope.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
“Always be scoping and scale with tokens.”
“you're going to get a token maxing slop cannon”
“The future of FD needs both.”
videoHow to Write Your First AI Eval - SallyAnn DeLucia, Arize AI
videoBuild Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind
videoHow to Build an AI Code Review Agent - Daksh Gupta, Greptile
videoHow to Build Voice Agents That Don't Fall Apart When You Interrupt - Jesse Hall, LiveKit
Checking sign-in…
Loading comments…