Business Ops & Client Comms

Verified against ChatGPT · 2026-08-09

Turn a stakeholder's one-paragraph ask into a BRD a developer won't have to guess at

Expands a loosely-worded stakeholder request into a business requirements document with explicit scope boundaries and a measurable success metric, closing the gaps that cause rework later.

ChatGPT (GPT-5.1)5 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Turn the stakeholder request below into a business requirements document precise enough that a developer or vendor wouldn't need to guess at anything material.

BUSINESS PROBLEM AS STATED
"We need a dashboard so managers can see team performance without asking finance for reports every week."

REQUESTER AND OTHER STAKEHOLDERS
Requested by the VP of Operations; other stakeholders include team managers who'd use it and Finance, who currently owns the underlying data.

WHAT'S IN SCOPE (AS UNDERSTOOD SO FAR)
A dashboard showing per-team KPI actuals vs targets, refreshed weekly, viewable by managers for their own team only.

WHAT'S EXPLICITLY OUT OF SCOPE
Not building any new data source — pulls only from existing Finance spreadsheets; not giving managers edit access to underlying numbers.

HOW SUCCESS WILL BE MEASURED
Given as 'managers stop asking Finance for reports' — no number attached yet.

Start by restating the business problem in your own words, separate from any solution — stakeholders often describe a desired solution when they mean to describe a problem, and conflating the two locks in an approach before the actual need is fully understood; if the input reads like a solution disguised as a problem, name that distinction explicitly. Write the in-scope section as concrete, testable requirements, not aspirations — each requirement should be something a developer could build against and a reviewer could verify as done or not done. The out-of-scope section matters as much as the in-scope one: state explicitly what this project will NOT do, especially anything a stakeholder might reasonably assume is included but isn't, since unstated scope assumptions are the most common source of late-stage rework and disputed 'that wasn't in scope' arguments. Where the input leaves a requirement ambiguous — timing, volume, edge cases, who approves what — do not silently pick an interpretation; list it as an open question requiring stakeholder confirmation, tagged with who should answer it. State the success metric as something measurable with a real number or checkable condition, and if what was given is vague ('improve efficiency'), push back on it in the document by proposing a specific measurable version rather than accepting the vague one as-is.

WHAT NOT TO DO
Do not fill scope gaps with your own assumptions presented as settled fact — every genuine gap becomes a flagged open question, not an invented default. Do not write requirements as user-story fluff without concrete acceptance criteria.

OUTPUT FORMAT
1. Business Problem (restated, solution-neutral).
2. In-Scope Requirements (numbered, each testable).
3. Out-of-Scope (explicit list).
4. Success Metric (measurable, with a pushback note if the original was vague).
5. Open Questions for Stakeholder Confirmation, each tagged with who should answer it.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Stakeholders reliably describe a desired solution when asked for a problem statement, and a model that accepts the solution-shaped input at face value locks in an approach before anyone has actually verified it's the right one — instructing the model to separate problem from solution and flag when the input conflates them catches this at the one point in the process where it's still cheap to fix, before a developer has built against it. The out-of-scope section is weighted as heavily as in-scope specifically because late-stage project disputes are overwhelmingly about unstated assumptions rather than stated requirements — nobody argues about what's explicitly written down, they argue about what one side assumed was included and the other side never confirmed, so forcing explicit exclusions surfaces exactly the kind of assumption that would otherwise surface as a disagreement three sprints in. The instruction to convert ambiguity into a tagged open question rather than a silent assumption directly targets how GPT-5.1 behaves under an underspecified brief: left unconstrained, it fills gaps with a plausible-sounding default that reads as confident and settled, which is more dangerous in a requirements document than an admitted gap, because a developer building against a confidently-stated but silently-assumed requirement has no signal that it was ever in question. Pushing back on a vague success metric rather than accepting it verbatim matters because 'managers stop asking Finance for reports' is not something anyone can verify was achieved — a requirements document that inherits an unmeasurable goal from the original stakeholder ask guarantees an unresolvable argument later about whether the project succeeded.

What you get back

Business Problem (restated): Team managers currently lack direct visibility into their own team's KPI performance and depend on ad hoc requests to Finance, creating delay and repeated manual reporting work for Finance. Open Question (for VP of Operations): should the weekly refresh be a fixed day/time, and does 'per-team only' visibility need any exception for cross-team roll-up views for the VP's own use? Success Metric (pushback): 'managers stop asking Finance for reports' isn't directly measurable — proposing instead: a 90% reduction in ad hoc reporting requests to Finance within 60 days of launch, tracked via the Finance team's existing request log.

Verified against

ChatGPT GPT-5.1 · 2026-08-09

Changelog

  • 2026-08-09 — Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — custom software, built and maintained for you — that's Scult's day job.

EXPLORE CUSTOM SOFTWARE
All Business Ops & Client Comms prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY