---
title: "Small Talk With Prasun Kumar, CEO and Founder of Oppex AI"
description: "Oppex AI builds AI agents that help developers resolve production incidents by gathering context before the engineer is paged. The agents collect logs, cloud metrics, database health, affected customers, recent code changes, and past incident history, then present a recommendation. Because developer logs are not plain English, the team constructs a knowledge graph of how the entire system connects. They harden the agent by pitting it against a chaos monkey that breaks test systems without revealing the method, forcing the agent to learn. The 15-person team has launched the product with early enterprise customers and aims to bring mean time to resolve under 10 minutes, eventually moving toward autonomous system healing."
---

# Small Talk With Prasun Kumar, CEO and Founder of Oppex AI

[Jetbrains](https://yomu.fyi/company/jetbrains) · Mitsal Athaya · Sep 23, 2026

**Type:** Explainer

## Summary

Oppex AI builds AI agents that help developers resolve production incidents by gathering context before the engineer is paged. The agents collect logs, cloud metrics, database health, affected customers, recent code changes, and past incident history, then present a recommendation. Because developer logs are not plain English, the team constructs a knowledge graph of how the entire system connects. They harden the agent by pitting it against a chaos monkey that breaks test systems without revealing the method, forcing the agent to learn. The 15-person team has launched the product with early enterprise customers and aims to bring mean time to resolve under 10 minutes, eventually moving toward autonomous system healing.

## Context

This is an interview with Prasun Kumar, CEO of Oppex AI, as part of JetBrains’ Small Talk series for their startup program. It covers the founding story, technical approach, and future vision of the product.

## Takeaways

- Oppex AI’s agent collects logs, cloud metrics, database health, affected customers, recent code changes, and past incident history before waking the developer, providing a contextual recommendation.
- The team hardens the agent using a chaos monkey that breaks test systems without revealing the method, forcing the agent to learn through repeated failures in a test environment.
- The current workflow is human-in-the-loop; the next goal is AI-recommended, human-approved fixes, and eventually fully autonomous system healing without human intervention.

## FAQ

### How does Oppex AI collect information about a production incident?

The agent automatically gathers logs, cloud metrics, database health, affected customers, recent GitHub changes, and past incident history before waking the developer, then assembles a recommendation.

### How does Oppex AI harden its agents for reliability?

They use a chaos monkey that breaks test systems without telling the agent how, forcing the agent to learn and improve through repeated failures in a controlled environment.

### Which JetBrains tools does the Oppex AI team use?

About 90% of their work is in IntelliJ IDEA, with WebStorm for frontend, PyCharm for Python, DataGrip for data, and JetBrains AI Assistant alongside.

**Tags:** [AI](https://yomu.fyi/topic/ai), [AI Agents](https://yomu.fyi/topic/ai-agents), [Incident Response](https://yomu.fyi/topic/incident-response), [IntelliJ IDEA](https://yomu.fyi/topic/intellij-idea)

- Source: [Jetbrains](https://blog.jetbrains.com/startups/2026/09/small-talk-oppex-ai)
- Source URL: https://blog.jetbrains.com/startups/2026/09/small-talk-oppex-ai
- Ingested by Yomu: 2026-09-23T18:00:12.416Z

[Read original post](https://blog.jetbrains.com/startups/2026/09/small-talk-oppex-ai)