Diagrams, algorithms, and handcrafted heuristics have long played a role in constructing AI agents, but are these traditional scaffolding techniques holding us back? Many current approaches lean too heavily on manual design, neglecting the “bitter lesson” that history has taught us: leveraging massive computation and generic methods often trumps tailored engineering. What if we could rethink our scaffolding strategies for AI agents—aligning them with decades of insight from the broader AI research community? In this talk, Rahul Sengottuvelu, Head of Applied AI at Ramp and co-founder of Cohere.io, will explore how embracing the bitter lesson can transform our approach to building AI agents. Attendees will gain actionable strategies to design more robust, scalable systems that minimize over-engineering while maximizing the power of general-purpose learning.

Recorded live at the Agent Engineering Session Day from the AI Engineer Summit 2025 in New York. Learn more at https://ai.engineer and purchase tickets to our next event, the AI Engineer World's Fair, in SF June 3 - 5 here: https://ti.to/software-3/ai-engineer-worlds-fair-2025

About Rahul

Rahul Sengottuvelu is the Head of Applied AI at Ramp. Before that, he co-founded Cohere.io, a customer support automation platform that used advanced AI to resolve support tickets more accurately. Cohere.io was acquired by Ramp in May 2023. He is also the author of Jsonformer, a constrained decoding library for LLMs.

AI Engineer

The author, Rahul Sengottuvelu, shares insights from his experience working with large language models (LLMs) and how they have evolved from early stages to present-day AI agents. He discusses the challenges faced with earlier models, the importance of building scalable systems that improve with more compute, and the practical applications at Ramp, a finance platform. Sengottuvelu exemplifies the development of agents using a CSV parsing task and explores how AI can significantly enhance backend systems. He also presents a futuristic approach where LLMs could potentially act as backends, showcasing a live demo of an AI-driven email client.

Rethinking how we Scaffold AI Agents - Rahul Sengottuvelu, Ramp