Turn the next business decision into a clear plan.
A long to-do list rarely tells you what deserves your attention. Start with one decision, describe the constraints, and ask for work you can actually review.
Start with the decision, not the whole business
For a small repair shop considering Saturday appointments, the useful question is whether a limited trial can test demand without committing to permanent staffing. Give the AI your opening hours, available capacity, and what would make the trial worthwhile. Use illustrative numbers if the real figures are sensitive.
Combine comparison with a small experiment
In PromptForge, choose a decision approach and a phased plan. Ask the model to compare a short pilot with keeping current hours. Require assumptions, an owner for each action, and a stop condition. A recommendation should explain what evidence would reverse it.
Keep responsibility with the people doing the work
Check scheduling constraints and the underlying figures before acting. The useful output is a decision brief you can discuss with your team. A confident paragraph cannot establish that customers will book or that the trial will be profitable.
Take this into your next prompt
A useful plan names the unknowns before assigning the work.
A WORKED EXAMPLE
From a request to a recipe.
See how a user’s brief and multiple skill tiles work together.
01 · Sample request
Help a fictional bicycle repair shop decide whether to test Saturday appointments. One mechanic can work four hours each Saturday for four weeks. Compare a limited pilot with weekday-only service. Do not assume demand or profitability. Tell me what to check before deciding.
02 · Selected skills
Diagrams & SystemsCompare alternatives side by sideStep 1
ResearchOrganize evidence for a claimStep 2
ProductivityCreate an actionable checklistStep 3
Your prompt recipe3 selected
1Compare alternatives side by side
2Organize evidence for a claim
3Create an actionable checklist
03 · A possible result
WORKED EXAMPLE · STRUCTURED TEXT
Saturday appointments: test or wait?
A reversible decision · Four-week pilot
Saturday appointments: test or wait?
Criterion
Side-by-side comparison
Decision check
Customer demand
Pilot: measures actual bookings in a limited window. Weekdays only: weekend demand remains unknown.
UNKNOWN TODAY
Staffing commitment
Pilot: needs four agreed hours each Saturday. Weekdays only: no additional shift.
CONFIRM ARRANGEMENTS
Financial threshold
Pilot: compare completed appointments and extra costs. Weekdays only: retain current operating pattern.
SET BEFORE BOOKING
Customer demand
Pilot: measures actual bookings in a limited window. Weekdays only: weekend demand remains unknown.
Decision check
UNKNOWN TODAY
Staffing commitment
Pilot: needs four agreed hours each Saturday. Weekdays only: no additional shift.
Decision check
CONFIRM ARRANGEMENTS
Financial threshold
Pilot: compare completed appointments and extra costs. Weekdays only: retain current operating pattern.
Decision check
SET BEFORE BOOKING
Before starting: confirm staffing, calculate the break-even appointment count, and decide when to stop. Proceed only if those prerequisites can be met.
Prepared example for the request and recipe shown. Copy the compiled prompt and paste it into your preferred AI chat. The tools available there determine whether you receive graphics, diagram instructions, or structured text.
See the compiled prompt
TASK
Help a fictional bicycle repair shop decide whether to test Saturday appointments. One mechanic can work four hours each Saturday for four weeks. Compare a limited pilot with weekday-only service. Do not assume demand or profitability. Tell me what to check before deciding.
DELIVERY STANDARD
Deliver the requested work itself, with the most useful result first. Use a deliberate hierarchy, concise section headings, readable spacing, and concrete details. Use tables for genuine comparisons, numbered steps for sequences, and checklists for actions when they improve usability. Preserve continuous prose for emails, stories, speeches, translations, and other narrative deliverables. Honor explicit length, tone, style, medium, and exact-format requirements; valid JSON, CSV, code-only, or final-only requests must not gain an introduction, decorative formatting, or extra commentary. Avoid a wall of undifferentiated text, ornamental filler, invented metrics, and generic advice. Use the supplied facts, show material assumptions, and check labels, calculations, citations, and internal consistency before returning the result. Never imply an artifact was rendered, a test was run, or a source was consulted unless that happened.
Treat the selected skills as one coherent brief. Style, tone, persona, critique, and editing selections modify the main deliverable; they do not each require a separate essay or artifact. Combine compatible visual approaches into a unified composition. Give genuinely different requested deliverables clear boundaries, and follow the selected recipe resolution where requirements conflict. Match each section to its audience and purpose, and remove repeated material. Use available creation or rendering tools for a finished visual, chart, slide deck, workbook, or other requested artifact. If the necessary tool or input is unavailable, disclose the specific limitation and provide a clearly labeled, usable production alternative rather than presenting a text description as the finished artifact.
APPROACH
1. Compare alternatives side by side
Compare alternatives side by side using the same decision criteria. Separate supplied facts from assumptions. Make any recommendation conditional on the evidence and show what would change it.
2. Organize evidence for a claim
Connect each claim to the supplied evidence. Distinguish what a source establishes from interpretation, and identify missing information. Do not manufacture citations or imply that unavailable sources were consulted.
3. Create an actionable checklist
Create an actionable checklist with a specific action, suggested owner, and observable completion check for each item. Separate prerequisites from optional follow-up work.
QUALITY CHECK
Use specific, useful language. State material assumptions and uncertainties. If essential information is missing, ask a focused question before proceeding. Do not invent facts, results, or completed actions.
