Azeem Azhar's Exponential View Entering the trillion-agent economy (ft. Rohit Krishnan)
109 snips
Feb 19, 2026 
Rohit Krishnan, writer and builder behind Strange Loop Canon and an engineer-economist-operator, joins to talk practical AI agents. They explore building and running persistent agents like Morpheus, tool stacks such as OpenClaw, and why writing remains the toughest task for LLMs. Conversation also zooms out to the infrastructure, identity, and exchange needed for a future of trillions of agents.
AI Snips
Chapters
Transcript
Episode notes
Onboard Agents Gradually
- Start with small, safe agent setups and give them limited scope before increasing access.
- Use a VPS or isolated folder to try OpenClaw, then incrementally add integrations like calendar or email.
Agent Lives On A Personal Laptop
- Rohit runs his OpenClaw agent on a personal laptop and treats it like a home for experiments.
- He allows it broad access and uses it for daily tasks, inbox triage, and interacting with running code.
Agent Writes Deep Market Report
- Azeem had his agent ingest 500 Prism analyses and produced a superior 10,000-word market report on Anthropic.
- He found the output better than comparable deep-research queries from other LLM tools.