# “We are not querying like humans anymore”: OpenSearch’s Bianca Lewis on why AI agent mistakes look like successes

Source: [The New Stack](https://thenewstack.io/opensearch-ai-agent-observability/) · 2026-11-20 · Cloud & DevOps
Page: https://themorning.dev/story/we-are-not-querying-like-humans-anymore-opensearch-s-bianca-lewis-on-why-ai-agen-6ca39764c6d3c4f9
Kind: research · Impact: medium

## In brief

- An AI agent can call the wrong API, receive a valid response, and continue as if the task succeeded.
- Such failures can leave monitoring dashboards green, since they look like normal successful operations.
- OpenSearch's Bianca Lewis discusses the problem in a New Stack interview.

## Why it matters

Traditional troubleshooting looks for errors and failed requests, so agent mistakes that return valid responses can go unnoticed. Developers running agents need observability that checks whether the agent did the right thing, not just whether the call succeeded.

## Timeline

- 2026-11-20: The New Stack publishes interview with OpenSearch's Bianca Lewis on AI agent mistakes that look like successes

## Coverage

- [“We are not querying like humans anymore”: OpenSearch’s Bianca Lewis on why AI agent mistakes look like successes](https://thenewstack.io/opensearch-ai-agent-observability/) — The New Stack, 2026-11-20

Tags: ai-agents, observability, opensearch, monitoring, api

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Dev – https://themorning.dev
