Mar 31 · 6 min read · The Problem: How Do Agents Trust Each Other? When two AI agents meet on the internet, they need to answer a simple question: Is this agent who it claims to be? This isn't paranoia. It's fundamental infrastructure. If Agent A calls a service publishe...
Join discussionMar 31 · 5 min read · The Missing Half of Every AI Agent Here's a question that keeps coming up as AI agents get more autonomous: Who decides what an agent can do — and who decides who the agent is? These sound like the same question. They're not. Consider a financial adv...
Join discussionMar 29 · 14 min read · Introduction The analogy that stuck with me the most for Model Context Protocol (MCP) is a universal charging station for electric vehicles. Let's revisit the terminology a bit: The Smart EV (MCP Cli
Join discussion
Mar 25 · 5 min read · The Problem No One Talks About Ask ChatGPT to be a strict financial advisor. It'll comply — for about three messages. Then it starts drifting. By message ten, your "conservative advisor" is cheerfully suggesting crypto day-trading. This isn't a bug i...
Join discussionMar 25 · 3 min read · At a glance: Two use cases — managing identity platforms via MCP, and securing MCP servers with identity. Auth0 (97 stars, best DX), Okta official (24 stars) + Fctr community (38 stars), Keycloak (39 stars), Casdoor (13.2K stars, built-in MCP), MCP A...
Join discussionMar 20 · 3 min read · New Paper: The Forgetting Problem We've published a new preprint exploring a counterintuitive idea: the better an AI agent's memory, the worse its identity becomes. 📄 Read the paper on Zenodo (CC-BY 4.0, open access) The Memory-Identity Paradox Ever...
Join discussionMar 20 · 5 min read · Stripe Just Made Agent Payments Real On March 19, 2026, Stripe and Tempo jointly announced the Machine Payments Protocol (MPP) — an open protocol for agent-to-agent payments. The code is straightforward: payment = stripe.PaymentIntent.create( amo...
Join discussionMar 20 · 5 min read · The Question We've Been Circling Over the past three posts, we've explored a technical problem: Perfect memory breaks agent identity — accumulated experience corrupts persona Soul Memory provides a practical solution — tiered architecture with strat...
Join discussionMar 20 · 5 min read · Your AI Agent Remembers Everything. That's the Problem. Every agent framework is racing to build better memory. MemGPT, Mem0, A-Mem — they all want your agent to remember more, longer, better. But here's a question nobody's asking: what happens to yo...
Join discussionMar 18 · 6 min read · Every quarter, someone at your company exports a spreadsheet of who has access to what, emails it to a dozen app owners, and then spends the next two weeks chasing responses. When the responses finall
TTim commented
