Free assessment · updated 2026

Is your AI prompt production-ready?

A prompt that works in five hand-tests can still fail catastrophically on the sixth real input. This is the 12-point assessment that separates a demo prompt from one you can put in front of a customer — scored, so you get a number and a verdict, not just a feeling.

Why this matters in 2026: as models move to metered API billing, a prompt that fails 1-in-20 doesn't just annoy a user — it bills you for a retry and erodes trust at scale. Reliability is now a cost lever, not just a quality one.

How to score it

Run one real, important prompt through all 12 checks below. Score each one:

  • 0 — not addressed at all
  • 1 — partially handled, or only by luck
  • 2 — deliberately engineered and verified

Add them up for a score out of 24. Your verdict is at the bottom.

The 12 points

01

Input containment

User-supplied text is wrapped in clear delimiters (XML tags, triple quotes) and never concatenated raw into your instructions.

This is the boundary between your logic and someone else's data. Without it, a user (or a scraped web page) can smuggle in "ignore previous instructions" and hijack the prompt. It's the SQL-injection of the AI era.

0 raw concatenation1 some delimiting2 strict, consistent containment
02

Instructions live in the system role

Rules, persona, output schema, and policy sit in the system prompt; only the variable task goes in the user turn.

Separation makes instructions far harder to override and is what makes prompt caching possible — which is where the 2026 cost savings come from (next point).

0 everything in one user blob1 mixed2 clean system/user split
03

Cache-aware ordering

Your heaviest, unchanging content (reference docs, policies) comes first; the variable bits come last.

Prompt caching only fires on a byte-identical prefix — and it can cut input cost by roughly 90% and shave latency on repeated calls. One stray character at the front breaks the cache and you pay full price again.

0 variables interleaved1 partly ordered2 stable-first, variable-last
04

Reasoning style matches the model

Standard models are asked to show their work step by step; reasoning / extended-thinking models are given the goal and success criteria, not prescribed steps.

Force step-by-step scaffolding onto a reasoning model and you fight its own process; skip it on a standard model and you lose accuracy on anything multi-step.

0 no reasoning guidance1 one-size-fits-all2 matched to model type
05

One job per prompt

Multi-step work (analyze → compare → rewrite) is a chain of focused prompts, not one mega-prompt doing everything.

A single prompt juggling five jobs is impossible to debug and overloads the model's attention. Atomic steps fail loudly and in one obvious place.

0 one giant prompt1 loosely split2 clean atomic chain
06

An explicit output contract

You specify the exact shape — keys and types, e.g. {"items":["string"],"count":int} — with a separate field for the model's thinking so it never pollutes the parsed result.

"Give me a list" produces a different shape every run and breaks the code that consumes it. A contract makes output something you can parse with confidence.

0 freeform1 loose format2 typed schema + thinking field
07

Concrete negative constraints

Prohibitions are specific — "Do not output markdown fences. Do not add a preamble." — not vague pleas like "don't be wordy."

Models handle explicit "do not X" far better than abstract style requests. Vague negatives get ignored; concrete ones stick.

0 none1 vague2 specific prohibitions
08

Programmatic validation first

Before any quality judgment, automated checks confirm the output parses and has every required field; a structural failure scores zero and triggers a retry.

Catch broken output in code, not in front of a customer. Quality only matters once the shape is valid.

0 eyeballed1 manual spot-checks2 automated structural gate
09

An adversarial test set

You keep a "golden set" of 20–100 cases — roughly 70% realistic, 30% nasty (empty input, gibberish, injection attempts, very long context).

Five happy-path tests will never surface the failure that shows up once in twenty runs. The adversarial 30% is where production breaks.

0 ad-hoc testing1 happy-path only2 realistic + adversarial set
10

Layered success metrics

You have pass/fail thresholds on three layers: structure (does it parse), accuracy (are the facts right), and style (tone/brevity — judged by a model where it's subjective).

"Looks good" is not a metric. You can't keep the winning prompt variant if you can't measure which one actually won.

0 vibes1 one metric2 structure + accuracy + style
11

Versioned, with regression tests

Prompts are versioned like code, and every change re-runs the whole golden set before it's promoted.

Fixing one edge case silently breaks another — the regression trap. And when the underlying model updates, an untested prompt can degrade overnight without a single code change on your side.

0 no versions1 versioned, no re-test2 versioned + full regression
12

Model fit & a human gate

Temperature matches the task (low for extraction/JSON, higher only for creative work), instructions are tuned to the model's dialect, and high-stakes outputs route to a human below a confidence threshold.

Full automation on a critical path is how a quiet 5% error rate becomes a public catastrophe. The best systems tee up the decision; a human signs off where it counts.

0 defaults, full auto1 some tuning2 tuned + human-in-the-loop

Your score

21–24
Production-ready. Ship it — with monitoring and a versioned prompt library so it stays that way.
14–20
Risky. It works today and will embarrass you later. Close every 0 and 1 before it sees real traffic.
0–13
Not ready. High odds of a quiet, expensive failure. Engineer it before it touches a customer.

Don't score prompts by hand. Make them test themselves.

Scoring once is step one. The Autoresearch Playbook turns these 12 points into an automated loop: an AI agent writes prompt variants, scores each against these exact criteria, keeps the winner and reverts the rest — overnight, and for $0 on a local model for non-training work.