Ex24 — Roadmap Builder

Choose a short sequence of product work that addresses a supported need.

Start with your task

Start with the Stakeholder Map and User Stories if needs are unclear. A roadmap is a decision about what to pursue and why; it is not a promise that a list of features will ship on invented dates.

For help supplying the stakeholder notes the assistant should use, see Give AI Text or a File to Work From. Unknown estimates still remain unknown.

You need: Stakeholder needs or problem evidence, candidate work, constraints and capacity knowledge. Unknown estimates remain unknown.

Build

Copy this into your assistant, replace the bracketed inputs, and provide the relevant material. Approve the approach before acting.

New to using or adapting a prompt? Ask for What You Want shows how.

Copy this prompt

Help me make a practical roadmap for [product/work outcome]. Evidence and stakeholder needs: [notes]. Candidate work: [list]. Constraints/capacity: [known facts and unknowns]. First separate supported needs from hypotheses, ask only for missing facts that could change the decision, and propose a simple comparison method for my approval.

Compare candidates by expected useful outcome, evidence strength, effort uncertainty, dependencies and consequences of delay. Do not assign precise scores or dates without inputs; unknown is not zero. Suggest a small Now/Next/Later sequence or another fitting format.

Explain rejected/deferred options, the tradeoff behind the first choice, and what we need to learn. For each near-term item include an observable outcome, dependency and review trigger. Ask me to choose or revise the sequence before finalizing it. Do not call stakeholder agreement or validated impact established without evidence.

Before I approve the comparison method, challenge it briefly: are needs supported, does capacity constrain the choice, are dependencies visible, and how could unknown effort or benefit change the sequence? Let me choose corrections before ranking work.

Check the result

Paste this review prompt into the same chat with the actual result and evidence. In a new chat, include your task, source material, result and observed checks. Choose the corrections before requesting a replacement artifact.

Use the evidence from your work with this review prompt.

Copy this prompt

Review this roadmap against the supplied evidence and constraints: [roadmap and source notes]. Is the first work item tied to a real need? Examine unsupported benefit/effort estimates, hidden dependencies, conflicting stakeholder needs, overcommitted capacity and features masquerading as outcomes.

Identify which assumptions could change the order and test sensitivity using plausible ranges only when labeled as scenarios. Suggest the smallest evidence-gathering step or scope correction. Let me decide what changes, then recheck the revised sequence and dependencies. Do not rewrite, supply replacement code or artifacts, or apply changes yet.

Explain the supported corrections and wait for my choice. Distinguish demonstrated failures from inferred causes; do not invent test history.

Choose, revise, and use

Choose a feasible first item and name what observation will tell you it helped. Record the reason for a consequential choice with Decision Record if useful. Revisit when evidence, capacity or dependencies change; avoid polishing a roadmap in place of learning.

Carry it forward

Apply the comparison to a new request. Can you explain why it enters now, waits, or replaces an existing item?

This is alpha material. Report unclear instructions or errors through a public issue or email help@bigleverinstitute.org. Share only redacted or fictional material.