Agentic SDLC at Uber — Uday Kiran Medisetty & Adam Huda, Uber
Source
youtube.com
Author
AI Engineer
Date
Context
Uber Engineering's AI agentAn 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.Full definition → infrastructure addresses the amount of information models must consume to perform development work. The publisher's talk description describes a gateway that turns internal APIs into agent tools and exposes them through a command-line interface, allowing responses to stay outside the model's context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →. It attributes a reduction of more than 40% in fleetwide model-tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → use to this approach.
The description also presents a shared map of software ownership and dependencies that replaces agents searching many separate systems for those facts. Together, the mechanisms target two costs: passing tool output through the model and repeatedly locating basic engineering context.
Terms in this piece · Glossary
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.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.