AI Engineer at Character.AI — Solving multi-modal agentic problems end-to-end. Writing about agents, LLMs, and building things that matter.https://anjaygoel.github.io/https://anjaygoel.github.io/posts/hermes-multi-agent/https://anjaygoel.github.io/posts/hermes-multi-agent/HermesAgent has a built-in delegate_task tool. I found the problem with it — and built process-isolated sub-agents that actually retain what they learn.Fri, 15 May 2026 00:00:00 GMThttps://anjaygoel.github.io/posts/hermes-skill-management/https://anjaygoel.github.io/posts/hermes-skill-management/Real-world lesson from running Hermes at scale: too many skills makes your agent go nuts. Here's the system I built to fix it.Sat, 06 Jun 2026 00:00:00 GMThttps://anjaygoel.github.io/posts/part-0-overview/https://anjaygoel.github.io/posts/part-0-overview/Starting from first principles — an agent is just a workflow that thinks like a human. Here's the 10,000ft view before we build it.Wed, 01 Apr 2026 00:00:00 GMThttps://anjaygoel.github.io/posts/part-1-io/https://anjaygoel.github.io/posts/part-1-io/Building an agent starts with one question: how does it talk to the world? Text in, text out — and everything else is just a plugin.Fri, 10 Apr 2026 00:00:00 GMThttps://anjaygoel.github.io/posts/part-2-orchestration/https://anjaygoel.github.io/posts/part-2-orchestration/IO is hooked up but the model just answers questions. Orchestration is how you turn a chatbot into an agent that actually does things.Fri, 01 May 2026 00:00:00 GMThttps://anjaygoel.github.io/posts/part-3-skills/https://anjaygoel.github.io/posts/part-3-skills/Skills are user manuals for your agent's tools. Get them wrong and your agent spends more time confused than working.Sun, 10 May 2026 00:00:00 GMThttps://anjaygoel.github.io/posts/part-4-memory/https://anjaygoel.github.io/posts/part-4-memory/Memory in agents is just expanding the context window. Here's the simple mental model that makes it practical.Sun, 10 May 2026 00:00:00 GMT