Notes on Jedi Knights

Learning-first

Tue, 14 Jul 2026 00:00:00 +0000

The usual advice for building event streaming into a system is short: don’t. Use Kafka. Use Redpanda. Use NATS. Use a managed service. The problem is solved; the incumbents are good; the operational literature is deep. Building your own broker is, by every reasonable metric, a bad idea.

We built Holocron anyway. Not because we thought we could beat Kafka — we can’t, and we’re not trying to — but because “use Kafka” answers a different question than the one we were asking.

One event, two consumers

Tue, 14 Jul 2026 00:00:00 +0000

The obvious way to add paid tiers to a product is to bolt on Stripe Billing, sprinkle metering calls through the code, and ship. The path is well-documented, the vendor is excellent, and it works. It’s also the wrong shape for a system that already emits structured events for a different reason — every metering call you add is a second instrumentation of a thing the codebase is already telling you about.

Tools, not endpoints

Tue, 14 Jul 2026 00:00:00 +0000

The obvious way to build an MCP server is to open your REST client, wrap each endpoint in a tool, and ship. Every route becomes a function, every parameter becomes a JSON Schema field, every response becomes whatever the upstream API happened to return. Two afternoons and you’re done.

Don’t.

We’ve now built three of these — one for ECNL youth soccer, one for the NWSL, one for the NFL — and the servers that survive contact with real agents look almost nothing like a mirror of their upstream APIs. The caller is not a script written by someone who read your docs. The caller is a model that will pattern-match your tool signatures and confabulate the rest. Every shape you get wrong is a hallucination generator.

When the caller is a coin flip

Tue, 14 Jul 2026 00:00:00 +0000

You cannot unit-test your way out of the anxiety of shipping something an LLM will call. Unit tests answer did this function return the right value for these inputs? The question that keeps you up at night is different: will the model, in a phrasing we didn’t anticipate, hallucinate an argument, or reformat our output in a way that changes what it means? You can raise coverage to 100% and that question stays exactly as loud.