Give Your AI Agents Eyes & Ears — Hands-on Workshop (Delhi)

This hands-on workshop is designed for AI engineers, startups, and creative professionals interested in building real-time perception capabilities for AI agents. The session will address the missing piece in modern agent stacks: perception, enabling agents to see, understand, and act on the real world continuously.

What to Expect Led by Ashu, founder of VideoDB, participants will learn how to convert continuous media inputs (screen, mic, camera, RTSP, files) into structured context that AI agents can effectively utilize. The workshop will cover:

• Understanding what "perception" means for agents: continuous, temporal, multi-source, searchable, and actionable.
• Supporting three input modes with a unified mental model: files, live streams, and desktop capture.
• Building searchable memory for agents to retrieve results with playable evidence.
• Transitioning from batch video AI to real-time event streams for immediate agent reactions.

Who Should Attend

• Engineers developing agents requiring continuous and temporal awareness.
• Individuals exploring skills for OpenClaw and aiming to equip it with perception capabilities.
• Research teams focused on physical AI, AI companion robots, and wearables.
• Product teams building meeting bots, desktop copilots, monitoring/operations tools, and QA/compliance solutions.

Attendees can expect production-grade demos, reusable takeaways, and a dedicated networking session to connect with top builders in agentic perception, video, multimodal AI, and frontier technology. Refreshments will be provided.