> Markdown version of [/events/world-congress-2026-north-america/sessions/1684-your-evals-passed](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1684-your-evals-passed). 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).

---

# Your Evals Passed. Your Agent Just Emptied a Database.


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

## Description

Green CI. Clean eval suite. Staged rollout looked fine.

Then your agent hit an edge case at 2am, chained three tool calls 
nobody anticipated, and did something irreversible. Your evals 
didn't catch it. They couldn't. They were never designed to.

This is the talk the agent ecosystem needs to have right now — 
because we've spent two years obsessing over eval quality and 
almost zero time on what happens *after* the agent is deployed 
and acting in the world.

**Evals are a pre-flight checklist. Your agent is already in the air.**

I'll show you exactly where the gap lives — and how to close it 
with a runtime verification layer you can bolt onto any agent 
stack this week:

- **Why the gap is structural, not a skill issue.** Evals test 
  known distributions. Agents encounter unknown ones. No eval 
  suite survives contact with real users at scale.

- **The failure taxonomy nobody publishes.** Tool call hallucination 
  under load, trust decay in multi-step chains, silent state 
  corruption between agent hops — with real examples from 
  production systems.

- **Runtime verification without the rewrite.** How to instrument 
  your execution graph with lightweight trust checkpoints — 
  behavioral tripwires that fire *during* execution, not in 
  your test suite.

- **Halt, retry, or escalate?** A decision framework for real-time 
  agent health that doesn't tank your latency or annoy your users.

You'll leave with a concrete verification architecture, a failure 
taxonomy you can use in your next incident retro, and serious 
second thoughts about that agentic pipeline you're about to ship.

## Speaker

### [Tejas Pravinbhai Patel](https://www.wearedevelopers.com/@tejas-pravinbhai-patel)

IEEE Award-Winning Researcher | Best Keynote Speaker | Sr. Software Engineer at Amazon | AI Systems & Agent Architect


## Related talks at this congress

- [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
- [Agents Can't Iterate Against Tests That Lie](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1700-agents-can-t-iterate) — Rocky Warren
- [Give the Agent a Budget, Not a Token](https://www.wearedevelopers.com/events/world-congress-2026-north-america/sessions/1695-give-the-agent-a) — Sachin Malhotra
- [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

## 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)