> Markdown version of [/events/conference-india-2026/sessions/1997-ultron-your-agent](https://www.wearedevelopers.com/events/conference-india-2026/sessions/1997-ultron-your-agent). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# ULTRON: Your Agent Has No Hands - Real-Time Voice, MCP, and Ten Phones on Stage


- **Event:** Conference India 2026

## Description

I say "unlock my phone and search YouTube for X" out loud. 10 physical Android phone sitting on the table does it - while an orb on screen reacts to my voice in real time. That demo has been watched over 10 million times and garnered over 300 stars on GitHub; this talk is the architecture underneath it, running live on stage.

Three things had to work. First, real-time voice: a WebRTC session to a real-time speech model, where I learned the hard way that the model finishes generating well before the audio finishes playing - so an event-driven state machine gets ahead of the actual voice, and you have to drive state off the output audio itself. Second, hands: a Model Context Protocol (MCP) server bridging the voice agent to ADB and the device's accessibility tree, with fast deterministic scripted actions for the common cases and an autonomous observe-decide-act-verify loop for everything else. Third, honesty about what I built -  including the moment I realised my agent's system prompt tells it to dismiss Android's own permission dialogs, and what that means for anyone thinking about shipping this.

Expect real architecture, real code, live devices on stage, and a candid account of where this design is genuinely unsafe and why I drew the line where I did.

## Speaker

### [Sagar Tamang](https://www.wearedevelopers.com/@sagar-tamang)

AI Engineer at Twospoon | Masters from IIT Patna | Builder with over 150k followers on Instagram


## Related talks at this congress

- [React Under Fire: Rendering Performance for Streaming Agent UIs](https://www.wearedevelopers.com/events/conference-india-2026/sessions/1992-react-under-fire) — Abhirupa Mitra
- [Build a Zero-Cost AI Agent in Your Browser](https://www.wearedevelopers.com/events/conference-india-2026/sessions/1980-build-a-zero-cost-ai) — Aishwarya Mathuria, Nishant Thakur
- [What I Got Wrong Shipping an MCP Server for Live Infrastructure](https://www.wearedevelopers.com/events/conference-india-2026/sessions/1999-what-i-got-wrong) — Pritesh Kiri
- [Teaching AI Coding Agents to Build It Right the First Time](https://www.wearedevelopers.com/events/conference-india-2026/sessions/1995-teaching-ai-coding) — Sajeetharan Sinnathurai

## Watch remotely

Can’t make it to Bengaluru? Watch this session live with Pro. You also get:

- All full videos, bookmarks, and playlists
- World Congress livestreams

[See pricing](https://www.wearedevelopers.com/pricing)

## Links

- [Get tickets](https://www.wearedevelopers.com/conference-india/tickets)