Create a candidate product research plan from a budget
Author: AILesson8 min setupTested with:ChatGPTReviewed: 2026-08-28
Quick answer
Define a search space, evidence hierarchy, total-cost ceiling, shortlist gates, and verification tasks before naming products. Provide: Use case and requirements, Budget and purchase boundaries, Research access and evidence standard. Expected result: A budget-bounded product research protocol with queries, source matrix, shortlist schema, and stopping rules.
1
Add your context
Your text stays in this browser. AILesson Prompts does not send it to a model or server.
2
Your prompt
Unfilled fields remain visible as placeholders, so you can still copy and edit the prompt
Create a product research plan bounded by the actual need and total budget. Do not recommend a current product until its exact model, region, seller, price, availability, compatibility, warranty, and return terms have been verified from dated sources.
User, tasks, environment, must-haves, preferences, incompatibilities, safety/access needs, lifetime, and existing equipment:
[need]
Total cash ceiling, currency/date, accessories, tax/shipping, maintenance, financing, condition, seller, warranty, return, and deadline:
[budget]
Region, source hierarchy, browsing date, version matching, review bias, hands-on tests, exclusions, and decision owner:
[research]
Translate the need into measurable must-pass tests, ranked preferences, unknowns, and disqualifiers. Reserve budget for required accessories, delivery, tax, setup, consumables, likely maintenance, and contingency before setting a device-price ceiling. Define the search space without brand assumptions. Build an evidence hierarchy: official exact-model specifications/manuals and authorized seller terms; independent standardized tests; repairability/support evidence; bias-aware owner reports; hands-on verification. Design queries and a candidate ledger with exact identifiers, region/version, source/check date, facts, test results, total cost, missing evidence, and status. Never merge similar model years or copy retailer claims as independent evidence. Specify shortlist gates, contradiction handling, used/refurbished checks, privacy/safety, return-window tests, and stop rules. Return research sequence, source matrix, budget ledger, comparison schema, verification questions, and decision conditions—including “no suitable option within budget.”
Private by defaultPrompt assembly happens locally in your browser. Avoid placing confidential information into any AI service unless your organization allows it.
From input to outcome
A worked example
See how concrete context turns this recipe into a usable result
Actual input
Use case and requirements
A university student needs a laptop for four years of writing, browser research, Zoom, Python coursework, and occasional small datasets. Must: ≤1.5 kg, at least 16 GB RAM, user can run required x86-64 course environment or an officially supported equivalent confirmed by department, 8-hour real light-work target to test, readable 13–14.5 inch display, webcam, replaceable charger available locally. Prefers quiet, repairable, no gaming GPU. Existing USB-A mouse and HDMI monitor need adapters if absent. No claim that a brand guarantees reliability.
Budget and purchase boundaries
CNY 7,000 total cash by 30 Sep 2026 in mainland China. Include tax, delivery, required adapter, sleeve, optional three-year support only if terms are useful, and CNY 500 contingency. New or manufacturer-refurbished from authorized seller; no marketplace used. At least 7-day return with no activation surprise, written warranty, no financing. Software subscriptions excluded.
Research access and evidence standard
Browse current sources as of research date. Official exact SKU/manual/support and authorized seller terms primary; independent battery/noise/display testing secondary; repair documentation and owner reports contextual. Match CPU/RAM/storage and region. Department must confirm course environment. Hands-on/return-window tests allowed. Exclude sponsored listicles without methods. Student decides with parent.
Example output
Budget gate: reserve CNY 500 contingency, a provisional 200 for sleeve, and 300 for adapters until ports are known. This leaves a maximum CNY 6,000 device-and-delivery envelope; support cannot be included until its price and useful coverage are verified. These are planning allowances, not current prices.
Research sequence: first ask the department for the exact environment, architecture constraints, virtualization/container support, exam software, and minimum RAM/storage. Until confirmed, architecture compatibility is a blocking unknown. Search current authorized-seller inventory only after defining 13–14.5 inch, ≤1.5 kg, ≥16 GB exact regional SKUs within the 6,000 envelope. For each SKU capture official weight, ports, charger part, memory/storage serviceability, webcam, warranty and return/activation terms; then seek independent method-described light-work battery, sustained performance, fan noise, display and webcam tests for that exact configuration. Owner reports can reveal questions but not failure rates.
Shortlist only candidates passing weight, memory, environment, seller, warranty, return, and reconciled total-cost gates. Hands-on/return-window protocol: reproduce course install with non-sensitive data, browser/Zoom workload, external monitor/mouse and required adapter, keyboard/display comfort, standby/wake, charger availability, and timed battery under recorded settings. Stop with “no suitable option” rather than dropping a must-have; alternatives are extend deadline, revise budget with the decision owners, or have the department approve a different environment.
Why this works
1
A reserved total-cost ceiling prevents a seemingly affordable device from failing once required accessories and upkeep are included.
2
Exact-model evidence and pass gates reduce version mixing and popularity-driven shortlists.
Check the result
Are must-pass requirements testable and separated from preferences and brand assumptions?
Does the device ceiling reserve every required and likely total-cost category?
Will every candidate retain exact model/region, dated sources, contradictions, missing evidence, seller terms, and hands-on tests?
Use it with confidence
Frequently asked questions
Practical answers about when to use this recipe, what to provide, and where human review still matters
What should I prepare before using “Create a candidate product research plan from a budget”?
For “Create a candidate product research plan from a budget,” prepare Use case and requirements, Budget and purchase boundaries, and Research access and evidence standard. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.
When is the “Create a candidate product research plan from a budget” result not ready to use?
The result is not ready if it does not yet deliver the stated outcome—A budget-bounded product research protocol with queries, source matrix, shortlist schema, and stopping rules—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.
Which AI tools have recorded tests for “Create a candidate product research plan from a budget”?
The published test record for “Create a candidate product research plan from a budget” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.
ChatGPT