Shipping AI

Evals are the seatbelt, not the science fair

You do not need a giant benchmark to start. You need a small set of cases that catches the exact ways your AI feature embarrasses you in production.

~5 minAI
scroll
01 · the smell

Vibes are a terrible release gate

The prototype feels good because you know the happy path. Production finds the weird path immediately: short prompts, angry prompts, copied tickets, partial context, old product names, and users who ask three things at once. That is why an eval set is not academic overhead. It is a tripwire.

zsh · before release

A small replay beats a confident demo.

guardrails armed

Hit the button and watch the hidden AI surface area light up.

02 · the set

Start with the failures you fear

A useful first eval set is not huge. It is honest. Include common requests, edge cases, policy boundaries, prompt injection attempts, and examples from real support tickets after removing private data. Each case should say what good looks like in plain language.

evals/cases.json

Readable beats clever. If a product manager can review the case, you are on the right track.

03 · the judge

Score behavior, not eloquence

Pretty answers can still be wrong. The rubric should check concrete behavior: cites the right source, refuses the forbidden task, asks the missing question, routes the risky topic, or returns structured JSON. Let style be a smaller score. Accuracy gets the veto.

Do the boring checks first: exact match, schema match, source match, refusal match. Bring in an LLM judge only when rules cannot express the behavior.stdout rule of thumb
AI launch switchboard
sloppy
shippable0
fragile: the model is still freelancing without enough checks

Flip the switches and watch the story turn into a tiny operating model.

04 · the habit

Run evals whenever the system changes

The model changed? Run evals. The prompt changed? Run evals. The docs changed? Run evals. The retrieval code changed? Definitely run evals. You are building a moving system, so quality has to move with it.

source trail