Skip to content
← All posts
·1 min read

LLMs in production: where the real work is

Beyond the demo — what it actually takes to run an LLM-powered feature in production: evaluation, cost control, latency, and failure modes.

AILLMProductionArchitecture

A working demo of an LLM feature takes an afternoon. A production-grade one takes a system. Here’s where the real engineering work hides.

Evaluation before everything

If you can’t measure quality, you’re guessing. Build evals early:

  • Unit-level: does the prompt produce the expected output for known inputs?
  • Pairwise / LLM-as-judge: rank outputs against a rubric.
  • End-to-end: trace the full user scenario, not just the model call.

Evals are the tests of the AI world. Skip them and every change is a leap of faith.

Cost and latency are features

A model that’s 5% better but 10× slower and 10× more expensive is often the wrong choice. Track token cost per request as a first-class metric. Cache aggressively. Route simple queries to cheaper models.

Failure modes you’ll actually hit

  1. Hallucinated tool calls — the model calls a tool with plausible-looking but wrong arguments.
  2. Context bloat — stuffing the prompt until quality degrades (yes, more context can hurt).
  3. Silent regressions — a model upgrade silently changes behavior. Evals catch this; vibes don’t.

The takeaway

The LLM is one component. The system around it — evals, cost control, observability, fallbacks — is where a production feature is won or lost.