// blog
Writing
Notes on building, evaluating, and shipping AI functions.
- 6 min read
How to evaluate an LLM prompt before shipping it
Evaluating an LLM prompt means running it against a fixed dataset and blocking the deploy when the pass rate falls below your threshold. Here's how.
- 6 min read
How to add automatic model fallback to your AI app
Automatic model fallback switches your AI feature to a backup the moment the primary fails. Here’s the failure modes, the DIY path, and the runtime approach.
- 6 min read
The best way to host an AI feature as a function
The best way to host an AI feature as a function is an AI function runtime: versioning, eval gates, model fallback, and tracing without rebuilding the shell.
- 6 min read
LLM cost optimization in production
LLM cost optimization means running on the cheapest model that clears your quality bar. Here’s how quality-floor model selection works in production.
- 5 min read
What is prompt versioning?
Prompt versioning tracks every change to an LLM prompt—instructions, model, parameters, schema—as an immutable snapshot you can evaluate, compare, and roll back.
- 7 min read
The Eight Pillars of a Production-Grade Agent
The gap between a demo agent and a production agent is eight operational pillars wide. What they are, and how a runtime provides the shell so you don't rebuild it per function.
- 6 min read
fn: Functions, Not Prompts
Why we built a runtime that treats AI features as versioned functions instead of prompts copied between branches.