Submissions
Unavailable

This livestream is restricted

Already a member? Login with your membership email address

Rootconf 2026 Annual Conference

Platforms for AI, and AI for Platforms

Tickets

Loading…

Accepting submissions

Not accepting submissions

Tushar Naik

Tushar Naik

Sanjay Kuniya

How PhonePe’s in-house Code Review platform (Arnold) helped control the Code Flood

Learnings from building an in-house Code Review platform more
  • 2 comments
  • Confirmed & scheduled
  • 09 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Alosh Denny

Alosh Denny

We Burned 48 GPU Hours Finding Out How Few Bits A Model Needs

One-line summary. I spent a year answering one question, how few bits a language model actually needs, and the infrastructure I answered it on failed in five different ways that had nothing to do with machine learning. This talk is both halves: the research, the day a container spent training on a tenth of its corpus while every dashboard stayed green, and the question underneath both, which is w… more
  • 1 comment
  • Confirmed & scheduled
  • 29 Sep 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Suraj Nath

Suraj Nath

TraceQL Internals: Building a Query Language for Distributed Traces

Title: TraceQL Internals: Building a Query Language for Distributed Traces more
  • 0 comments
  • Confirmed & scheduled
  • 29 Sep 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Aditya Singh

Aditya Singh

Beyond SSE: Building Resumable Agent Streams

Rootconf 2026 Proposal Draft Session title Beyond SSE: Building Resumable Agent Streams more
  • 4 comments
  • Confirmed & scheduled
  • 17 Sep 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Gaurav Maheshwari

Gaurav Maheshwari

Surviving the query-pocalypse!

Proposal template We have a new user persona - AI Agents. What does it mean for platform availability, reliability & performance? more
  • 3 comments
  • Confirmed & scheduled
  • 26 Sep 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Vikash Kumar

Vikash Kumar

When ML Serving Becomes a Distributed Systems Problem

Deploying an ML model is easy. Operating hundreds of them reliably is not. more
  • 1 comment
  • Confirmed & scheduled
  • 01 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
heetgala

heetgala

Stop Shipping AI on Vibes: AI Evals for Agents

About this session Every team building with LLMs has lived the same story. The demo works beautifully, everyone’s impressed, it ships. Then a real user asks a slightly different question and the answer comes back confidently wrong. more
  • 3 comments
  • Confirmed & scheduled
  • 07 Oct 2026
I am submitting: To show a demo I have a submission for: A talk - 30-40 mins
Manas Chaturvedi

Manas Chaturvedi

From AI Agents to AI Platform: Lessons From Building an In-House Multi-Agent Platform

From AI Agents to AI Platform: Lessons From Building an In-House Multi-Agent Platform more
  • 2 comments
  • Confirmed & scheduled
  • 04 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
KANIKA SINGHAL

KANIKA SINGHAL

When Agents Go Rogue: Building a Zero-Trust Agent Mesh

When Agents Go Rogue: Building a Zero-Trust Agent Mesh more
  • 6 comments
  • Confirmed & scheduled
  • 18 Sep 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Anant Shrivastava

Anant Shrivastava

Setting Up Your Own Private AI Infrastructure: How Hard Could It Be?

Setting Up Your Own Private AI Infrastructure: How Hard Could It Be? more
  • 2 comments
  • Confirmed & scheduled
  • 01 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Hemant Kumar

Hemant Kumar Author

Sahil Joseph Editor

Benchmarking AI SRE agents before they touch production

Summary Over the past few months we’ve been evaluating AI SRE agents with several of our customers: OpenSRE, HolmesGPT, K8sGPT and a handful of others. We started with the things any SRE would check before trusting one of these on a real incident. That only took us so far, so we built a benchmark on top of the open-source SREGym framework, where the agent’s diagnosis is graded against what actual… more
  • 5 comments
  • Confirmed & scheduled
  • 05 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Jitendra

Jitendra

Upgrade Broke My Query… Break Free with AI [ Detect, Debug, Fix with AI-Assisted Self-Service Platform ]

Session title Upgrade Broke My Query… Break Free with AI Detect, Debug, Fix with AI-Assisted Self-Service Platform more
  • 2 comments
  • Confirmed & scheduled
  • 08 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Adithya Parthasarthy

Adithya Parthasarthy

3 Weeks to 3 Hours: Building an AI Co-Pilot for Kubernetes Upgrade Preparation

3 Weeks to 3 Hours: Building an AI Co-Pilot for Kubernetes Upgrade Preparation at Booking.com more
  • 1 comment
  • Confirmed & scheduled
  • 08 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
saurabh hirani

saurabh hirani

Hermes in Production: Building an AI Infrastructure Engineer That We Could Actually Trust

One-line summary How we built and productionized Hermes for a customer in the AI-powered industrial operations and fleet intelligence space: an infrastructure agent that investigates real systems, reasons about changes, and creates production-ready GitOps PRs while keeping execution deterministic, auditable, and safe. more
  • 2 comments
  • Confirmed
  • 05 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Nikhil Baba Bobba

Nikhil Baba Bobba

Grounding the Agent: How to Let LLMs Reliably Operate Infrastructure

Session title Grounding the Agent: How to Let LLMs Reliably Operate Infrastructure more
  • 1 comment
  • Confirmed & scheduled
  • 09 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Naween Ghimire

Naween Ghimire

Tejas Bajaj

Tejas Bajaj

100+ clusters used by 100+ teams, and a platform that’s starting to run itself

Title 100+ clusters used by 100+ teams, and a platform that’s starting to run itself more
  • 0 comments
  • Confirmed & scheduled
  • 09 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins

Vivek Kalyanarangan

Decoding at a million tokens when the KV cache lives in host memory: what actually bounds the step

Decoding at a million tokens when the KV cache lives in host memory: what actually bounds the step more
  • 5 comments
  • Confirmed & scheduled
  • 17 Sep 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Nikhilesh Chamarthi

Nikhilesh Chamarthi

What breaks on the way to 1,000 agents: long-running jobs, narrow privilege, many tenants

One-line summary A typical production agent runs for a long time, with someone’s authority, next to other companies’ agents. Each part of that sentence broke something on Slash, Razorpay’s agent platform, and this talk is what broke, what we chose, and what you can copy. more
  • 3 comments
  • Confirmed & scheduled
  • 09 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Md Tarique Yaseen Khan

Md Tarique Yaseen Khan

Agents Are Easy, Memory Is Hard

Agents Are Easy, Memory Is Hard: What Our SRE Agent Is Allowed to Remember, and How We Check It more
  • 4 comments
  • Confirmed & scheduled
  • 06 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Anant Shrivastava

Anant Shrivastava Facilitator

vivek kumar sahu

vivek kumar sahu

AIBOM Birds of Feather session

As organizations increasingly build, deploy, and consume AI systems, the need to understand what goes into these systems is becoming more important. AI Bills of Materials (AIBOMs) are emerging as a way to document this information, but the industry is still figuring out what an AIBOM should contain, how its components should be classified, and how this information can be collected and maintained. more
  • 0 comments
  • Confirmed & scheduled
  • 10 Nov 2026
Jainin Shah

Jainin Shah BOF facilitator

From Vibe Coding to Production: How do we run untrusted apps safely?

AI-assisted development is making it easier to build useful applications quickly. Getting an app running, however, leaves several questions unanswered: what can it access, how could it fail, and who is responsible when other people start depending on it? more
  • 0 comments
  • Confirmed & scheduled
  • 12 Nov 2026
Utkarsh Kanwat

Utkarsh Kanwat

Your Agent Can Run as Long as You Can Check It

Session title Your Agent Can Run as Long as You Can Check It more
  • 1 comment
  • Confirmed & scheduled
  • 03 Oct 2026
I am submitting: To speak I have a submission for: A talk - 30-40 mins
Alosh Denny

Alosh Denny Facilitator

Vivek Kalyanarangan Facilitator

Birds of Feather (BOF) session: Fewer bits, more questions: making quantization work across models, runtimes and hardware

Fewer bits, more questions: making quantization work across models, runtimes and hardware more
  • 0 comments
  • Confirmed & scheduled
  • 15 Nov 2026

Bharadwaj Embar

Shailesh Jain Facilitator

Enterprise AI, Birds of Feather session

Enterprise AI, Birds of Feather session Facilitated by Shailesh Jain, Principal Engineer, Nutanix more
  • 0 comments
  • Confirmed & scheduled
  • 20 Nov 2026
One year entry to Rootconf's programmes and activities

Hosted by

We care about site reliability, cloud costs, security and data privacy

Supported by

Platinum Sponsor

Nutanix is a global leader in cloud software, offering organizations a single platform for running apps and data across clouds.

Silver sponsor

Engineers at Roku Bengaluru, building the tech behind the #1 TV streaming platform in the US and Mexico. Come say hello at our meetups.

Bronze Sponsor

Internet infrastructure APIs for IP geolocation and more

Community Sponsor

Real-time Observability & Governance layer for AI agents