Submissions
Utkarsh Kanwat

Utkarsh Kanwat

@utkarshkanwat

AI Research Engineer at AutonomyAI, building AI agents that work on their own for long stretches. Electrical Engineering, IIT Bombay.

  • Joined Oct 2026

After the Prototype - agents, applied AI, and models put to work

Your Agent Can Run as Long as You Can Check It

Coding agents can now work for hours without help, but in most other kinds of work an agent still needs a person to step in every so often. It’s the same models in both cases, so the model isn’t what decides how long an agent can run. The checks around it are. Every step an agent takes builds on its last output, and small mistakes pile up unless something outside the agent catches them. The agent… more
  • 9 comments
  • Submitted
  • 03 Oct 2026
Type of submission: 30 mins talk

Rootconf 2026 Annual Conference

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

The Fifth Elephant 2026 Winter Edition

Your Agent Can Run as Long as You Can Check It

Submission type: Talk/session proposal - 30-40 mins more
  • 0 comments
  • Submitted
  • 03 Oct 2026
I am submitting: To speak I have a submission for: Showcase - a cool idea I have built/working on - 20 mins

Enterprise AI in Production: Mumbai Call for Proposals

Keeping an Autonomous Coding Agent Reliable on Long Tasks: Lessons from Production

Keeping an Autonomous Coding Agent Reliable on Long Tasks: Lessons from Production. What actually breaks when an AI agent runs long, multi-step tasks for enterprise teams, and the checks that raised our long-task success rate from 74% to 86%. more
  • 4 comments
  • Submitted
  • 15 Oct 2026