HeyContext

The problem

At the time, AI usage was still conversational, not agentic. Going back and forth with a chat assistant was slow and tedious, with context getting lost in the noise.

What I built

A single user prompt generated a family of agents in a coordinated dependency graph. Each agent had a role, tools, and structured artifacts to work on. They communicated through A2A notes, so agent D could see what agents A, B, and C had learned without paying the time and token cost of direct cross-agent conversation.

My favorite system was the crystal dam: conversational context accumulated until it hit a token count or time threshold. When the dam broke, we processed it into stardust, shards, and crystals, memory artifacts users could actually see and inspect.

Proof

Went live with hundreds of users within a month, no ad spend.

What I learned

Inventing vocabulary is one of the best parts of developing brand new systems. It also makes the architecture easier to reason about.

Architecting and running production multi-agent systems with memory, routing, handoff notes, and live users.