> Markdown version of [/events/world-congress-2026-europe/sessions/1350-agents-that-own](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1350-agents-that-own). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Agents That Own Their Inference: Building Production AI Agents on Dedicated GPUs


- **Date:** Friday, Jul 10, 2026
- **Time:** 14:45–16:45 (120 min)
- **Room:** Room M1 (60 Seats)
- **Event:** World Congress 2026 Europe

## Description

Every production agent today is renting its intelligence. You're paying per token, sending your customer's data to someone else's servers, and hoping the provider doesn't rate-limit you during your launch. For most teams, that's fine. But for a growing number of teams in regulated industries, with high-volume products, latency-sensitive workloads, or rising token bills, it's starting to look like a liability.

In this 120-minute hands-on workshop you'll get a dedicated GPU and build an agent that runs on infrastructure you control. You'll stand up vLLM, point your agent at it, and drive concurrent load through the stack until you can see batching, KV cache pressure, and throughput limits in the metrics. Then you'll optimize the deployment to improve throughput while keeping per-request latency in line.

The focus isn't agent frameworks. It's the inference layer underneath them. You'll leave with working code and a real understanding of continuous batching under real concurrency, KV cache tradeoffs, vLLM's metrics, and the bottlenecks that only show up when you operate the inference server yourself.

## Speaker

### [Duan Lightfoot](https://www.wearedevelopers.com/@duan-lightfoot)

Senior Developer Advocate at Akamai


## Related talks at this congress

- [Build a Production-Ready AI Agent in 90 Minutes](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/957-build-a-production) — Tamas Piros
- [Build a Production-Ready AI Agent in 90 Minutes](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1664-build-a-production) — Tamas Piros
- [Accelerating AI Inference at Scale: A Deep Dive Into NVIDIA Dynamo on Kubernetes](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1061-accelerating-ai) — Anshul Jindal, Mohak Chadha
- [Tour de Force: Open-Source LLM Inference Optimization from Simple to Sophisticated](https://www.wearedevelopers.com/events/world-congress-2026-europe/sessions/1094-tour-de-force-open) — Christin Pohl