Abdul Hannan ShaikhSoch.Blog by Abdul Hannan Shaikh
AI product management   15 April 2025   5 min read
Read as markdown

The PRD Format I Use for AI Features

A standard PRD has user stories, acceptance criteria and mockups. An AI-feature PRD needs four sections those do not cover: the rubric, the hallucination tolerance, the cost ceiling, and the fallback path. The shape I landed on after a year of refining it.

On this page
  1. 1. The rubric
  2. 2. Hallucination tolerance
  3. 3. Cost ceiling
  4. 4. Fallback path
  5. What the template doesn't change
  6. One thing I'd warn against
  7. Further reading

About a year ago I was reviewing a PRD for an AI feature my team was about to ship. It had user stories, acceptance criteria, three mockups, a list of edge cases, and a paragraph at the bottom that read, in essence, "the LLM will return a good answer". I sent it back.

The problem wasn't that the PRD was bad. It was that the template we used didn't have the right slots for AI work. The deterministic-software template silently treated the model as a black box that would Just Work. For features with deterministic output, that's fine. For features that fail in distinct ways (wrong answer, slow answer, expensive answer, made-up answer), you need slots that name those failures.

I've been iterating on a template since. It has four sections the team's original format didn't. Sharing them here in case they're useful.

1. The rubric

Before any user story, the PRD opens with a rubric. Three to five criteria, each with a 1–5 scale, each tied to a concrete check.

For a customer-support AI:

The rubric is the contract. It defines what "good" means for this feature before anyone designs the UI or specs the prompt. Without it, every reviewer judges the feature against their own private criteria and arguments don't converge.

It's the single highest-leverage section in the PRD. I've watched one save twenty hours of "the AI is wrong / no it isn't" debate.

2. Hallucination tolerance

This sounds dramatic. It's not. Every AI feature has a tolerable rate of fabricated content, even if that rate is zero. The PRD needs to state it explicitly.

Three buckets I use:

Each bucket implies different infrastructure. Zero-tolerance needs retrieval + citations + confidence thresholds + escalation. Best-effort needs almost none of that. The PRD picks the bucket. Engineering builds to it.

3. Cost ceiling

The boring section. Also the section I see PMs skip and then get burned by.

I write it as a per-call cost target and a monthly total. Example:

This forces the cost conversation up front. AI features have a marginal cost that grows with usage. PMs who don't model it ship features that look great in pilot and quietly hemorrhage budget at scale.

4. Fallback path

What happens when the model is slow, expensive, down, or just wrong?

I make engineering and design map this in the PRD itself. Three failure modes get explicit handling:

The fallback is what makes the feature usable under realistic operating conditions. Skip it and your support team becomes the fallback. They will notice.

What the template doesn't change

User stories, acceptance criteria, mockups, dependency lists, success metrics: all still there. The four AI-specific sections sit on top. The total PRD length goes up by maybe 40%. That's a fair price for catching the four most common AI-feature failure modes in review instead of in production.

One thing I'd warn against

Don't write the rubric after the feature is built. Write it before. The whole point is to commit to a definition of "good" while it's still possible to discover that you haven't built it yet.

If you find yourself writing the rubric to match outputs you've already seen, you're optimising for shipping, not for being right. That's a meta-failure the rubric was supposed to prevent.

I'll know the template is wrong when a feature ships clean against all four sections and still flops with users. That hasn't happened yet. The day it does, I'll write a follow-up.

Further reading


Abdul Hannan Shaikh
Open to mentoring and advisory
Abdul Hannan Shaikh

Senior technical PM at APIMatic. Nine years in B2B SaaS.

Keep reading