The Agentic Edge: Smarter Agents, Leaner Prompts & OpenClaw

AI agents are only as powerful as the systems behind them — and how efficiently you use them. In this session, we’re going deep on what it actually takes to build, run, and optimize real-world AI agents without burning through your API budget or losing control of your workflows.

We’ll also introduce you to one of the most exciting open-source projects in the AI space right now: OpenClaw — the personal AI assistant that actually does things.

What we’ll cover:
∙ Building AI agents — how to architect agents that plan, reason, and execute multi-step tasks reliably, including how to design agent loops, tool use, and memory that holds up in production
∙ Token efficiency & prompt optimization — the strategies serious AI builders use to cut costs, reduce latency, and get more out of every LLM call without sacrificing quality
∙ OpenClaw deep dive — a hands-on look at openclaw.ai, the open-source personal AI assistant that runs on your machine, connects to WhatsApp/Telegram/Discord, builds its own skills, and has 24/7 access to your computer, files, and tools
∙ Skills & extensibility — how OpenClaw’s plugin and skills system works, and how you can build your own reusable agent capabilities on top of it
∙ Real-world use cases — live demos showing how builders are using agents and OpenClaw to automate work, manage communications, and run entire workflows from their phone

This is a session for builders who want to go beyond the basics and start running AI that actually works for them around the clock.

Who should attend:
Founders, engineers, and AI-curious builders who want to understand how agentic systems work, how to run them efficiently, and how tools like OpenClaw are redefining what a personal AI assistant can be.

Bring your laptop. The future is already here — let’s plug into it.