Gaurav Maheshwari

@mgaurav

From ReAct to Multi-Agent System - Our Journey of building an Observability agent

Submitted Jun 25, 2026

At Oodle AI, we have been building AI agents for faster incident debugging, helping engineers with day-to-day oncall/operational tasks. Our journey started about 1.5 years back with a Langchain ReAct based agent. Today, we are running multi-agent orchestration to allow our customers to just ask questions on top of their observability data. This session will go over our learnings in running this system in production and key inflection points in our design.

Key Takeaways

  1. Practical learnings around context management, tool design, latency optimizations for a multi-agent system.
  2. Building a unified system which can serve many clients with a shared backbone - in-product AI assistant, MCP clients, Slack bots etc.
  3. Agentic systems are much beyond AI layer on top of existing data layer/APIs. To make them work in production, you often need to design your entire stack to make it AI-friendly.

Target Audience

  1. All engineers - everyone who handles oncall :)
  2. AI practioners - people building agentic systems.
  3. SRE/DevOps engineers who are building in-house AI SRE tools.

Speaker Bio

Gaurav Maheshwari is Founding Engineer & India Site Lead at Oodle AI - an Observability startup building a new data layer for Observability for Agentic Era. He has previously worked at Rubrik and Goldman Sachs. Beyond work, poetry and cricket interests him.

Draft slides: to be added

Elevator Pitch: to be added

Comments

{{ gettext('Login to leave a comment') }}

{{ gettext('Post a comment…') }}
{{ gettext('New comment') }}
{{ formTitle }}

{{ errorMsg }}

{{ gettext('No comments posted yet') }}

Hosted by

Jumpstart better data engineering and AI futures