Intel / article

The Linkedin Generative Ai Application Tech Stack Extending To Build Ai Agents

Source: linkedin.com
Author: LinkedIn Engineering
Date: Published Sep 10, 2025

Context

LinkedIn built its agent platform around infrastructure already used for messaging. Long-running work becomes a sequence of messages with ordered delivery, accessible history, and retries when infrastructure fails. An adapter connects that messaging system to the software interfaces developers use to define agents. Client libraries then deliver progress and synchronize state across devices. This gives background agents a durable way to continue work beyond one user session and report back when a task progresses or finishes.

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 engineering — Deciding what an agent sees at each step — the discipline that replaced prompt engineering once context windows got large enough to fill badly.

Read the source www.linkedin.com