> Markdown version of [/events/world-congress-2026-north-america/sessions/1768-taming-rogue-agents](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1768-taming-rogue-agents). 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).

---

# Taming Rogue Agents: Observability-Driven Evaluation for Production Reliability


- **Event:** World Congress 2026 North America

## Description

Moving from a viral demo to reliable enterprise AI is the hardest hurdle in modern software engineering. Because agents are inherently non-deterministic, validating performance requires a granular look at the "why" and "how" behind every action. 

This session explores how observability redefines agentic evaluation beyond binary pass/fail testing, shifting the focus from the result to the entire reasoning chain. Featuring a live demo using Arize Phoenix and LangGraph, we’ll showcase how to trace complex loops and automate evaluations in real-time. 

What you’ll learn: 

Beyond Output: Why judging final answers alone is a recipe for silent failure. 

Live Implementation: Using Arize Phoenix with LangGraph to visualize traces and debug agentic "thought processes". 

The Playbook: An incremental framework for evaluation-first development. 

Are you ready to stop guessing and start measuring? Join us to master the art of agent evaluation. 

## Speakers

### [Anagha Rumade](https://www.wearedevelopers.com/@anagha-rumade)

Vice President - Applied AI/ML Lead at JPMorgan Chase
### [Anjana Umapathy](https://www.wearedevelopers.com/@anjana-umapathy)

Vice President - Applied AI ML Lead, Manager at JPMorgan Chase
### [Apoorva Jaiswal](https://www.wearedevelopers.com/@apoorva-jaiswal)

Vice President - Applied AI ML Lead at JPMorgan Chase & Co.


## Related talks at this congress

- [Closing the Visibility Gap: Lessons from Safety Critical Agentic Systems](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1408-closing-the) — Vivek Pandit
- [Your Evals Passed. Your Agent Just Emptied a Database.](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1684-your-evals-passed) — Tejas Pravinbhai Patel
- [Evals Are Infra: Building AI Systems Developers Can Actually Trust](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1701-evals-are-infra) — Phoebe Wang
- [DeepAgents: Build Multi-Agent AI Systems That Actually Work](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1694-deepagents-build) — Anagha Rumade, Anjana Umapathy, Apoorva Jaiswal

## Watch remotely

Can’t make it to San José? Watch this session live with Pro. You also get:

- All full videos, bookmarks, and playlists
- World Congress livestreams

[See pricing](https://www.wearedevelopers.com/pricing)

## Links

- [Get tickets](https://www.wearedevelopers.com/world-congress-north-america/tickets)