HeyJaredFounders Agentic AI Playbook
Rethinking commerce. Agent-powered. Workflow-ready. Founder-led.
- Indexed issues, last 90 days
- 3
- Latest publication
- Sep 22, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 16, 2026
Latest issues
The Rare-Earth Problem in Agentic AI (opens the original)
Read excerpt
Many agentic AI demos depend on something that’s easy to overlook. One important piece of the system is assumed to be there whenever it’s needed. It might be a frontier model, a large context window, reliable tool use, or an API from a particular vendor.That’s the rare earth metal in the EV motor. It may be only one part of the system, but a lot can depend on it. If it becomes too expensive, slows down, or simply isn’t available, the agent may not have another way to get the job done.<p class
CrewAI vs LangGraph vs AutoGen: Which Agent Framework Should You Choose in 2026? (opens the original)
Read excerpt
Building AI agents has become much easier over the past year. The difficult part is no longer deciding whether to use an agent framework. It’s deciding which philosophy of agent development best matches the system you’re trying to build.Three frameworks dominate most production discussions today: CrewAI, LangGraph, and AutoGen. Although they solve many of the same problems, they approach them
Every AI Agent Has a Context Budget. Most Waste It. (opens the original)
Read excerpt
As inference becomes cheaper, managing context is becoming the defining challenge in production AI agents.Every AI agent operates within a fixed context budget. Only a small fraction of the information it could access belongs inside its context window at any given moment. The rest becomes a distraction.Everything about modern agent design follows from this constraint. As inference becomes cheaper, context has become the scarcest resource in production AI systems.Two years ago, most optimization
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.