# AI prompt portfolio builder Human Guide

## What This Is For
Builds statistically useful prompt portfolios for AI visibility, citation, sentiment, and recommendation tracking. It gives the agent a clearer input/output frame for AI prompt portfolio builder: what context to ask for, what decisions to make, and what usable artifact to return.

Use this as a human-readable version of the AI prompt portfolio builder agent skill. It is meant for marketers, operators, founders, and other non-coders who want the workflow without reading agent-specific implementation instructions.

## When To Use This
- Use this when you need a repeatable process for AI prompt portfolio builder.
- Use this when the task needs judgment, examples, constraints, or a clear output format rather than a one-off prompt.
- Use this when you want to hand an AI assistant enough context to produce a usable marketing artifact.

## When Not To Use This
- Do not use this when you only need a quick factual answer.
- Do not use this when the work depends on private data you cannot share with the assistant.
- Do not use this as a replacement for legal, compliance, financial, or medical review.

## What You Need Before Starting
- The goal or business outcome you want.
- The audience, customer segment, or market context.
- Any source material the assistant should respect, such as notes, briefs, examples, URLs, or brand guidance.
- Constraints such as tone, length, channel, deadline, region, or approval requirements.
- A clear definition of what a good final answer should look like.

## Step-By-Step Workflow
1. State the job clearly: "Use the AI prompt portfolio builder guide to help me with..."
2. Add context: audience, goal, offer, channel, source material, and constraints.
3. Ask the assistant to identify missing inputs before producing the final output.
4. Have the assistant follow the skill-specific guidance below.
5. Review the result against the final checklist and ask for revisions where needed.

## Skill-Specific Guidance
- Profound compared identical portfolios run once and ten times daily across 753 prompts and seven platforms for two weeks.
- Once-daily visibility estimates landed within about two percentage points of the heavier measurement.
- Additional runs reduced citation-share noise more than visibility noise, but could not remove day-to-day platform drift.
- Prompt portfolio composition mattered more than run frequency, especially for citation share.
- brand, products, audience, competitors, and business objective
- engines, models or surfaces, markets, languages, and personas
- real prompt-demand data when available
- customer research, search terms, sales calls, support questions, and category vocabulary
- monitoring budget and required decision cadence
- problem and solution research
- comparisons and alternatives
- recommendations and "best for" decisions

## Decision Points And Nuance
The original skill emphasizes: Research basis, Goal, Intake, Portfolio design, Workflow, Output.

Use these questions to steer the work:
- What is the intended audience or buyer?
- What source material must be preserved?
- What should the assistant optimize for: clarity, persuasion, accuracy, speed, creativity, or conversion?
- What examples represent the desired quality bar?
- What should the assistant avoid?

## Common Mistakes
- monitoring budget and required decision cadence
- Do not turn every keyword into a conversational prompt. Prefer observed demand and preserve the user's natural language.
- Add paraphrase variants only where wording sensitivity must be measured.
- Never compare periods that used materially different portfolios without recalculating a common cohort.

## Copy-And-Paste Prompt
```text
Use the AI prompt portfolio builder human guide.

My goal:
[Describe the business outcome]

Audience:
[Describe who this is for]

Context and source material:
[Paste notes, examples, links, or existing copy]

Constraints:
[Tone, length, channel, timeline, must-include items, must-avoid items]

Before producing the final output, ask me for any missing information that would materially improve the result.
```

## Final Checklist
- [ ] The output matches the original goal.
- [ ] The audience and context are reflected in the answer.
- [ ] Important constraints and source material were preserved.
- [ ] The assistant made the relevant decisions explicit.
- [ ] The final artifact is ready to use, review, or hand to the next person.

## Source
This guide was generated from the Profound skill entry for `ai-prompt-portfolio-builder`.

## Source Skill Notes
These notes preserve the nuance from the original skill. Use them as supporting reference when the workflow above feels too generic.

# AI Prompt Portfolio Builder

## Research basis

This skill operationalizes Profound's research, [Is once a day enough?](https://www.tryprofound.com/blog/is-once-a-day-enough), published July 8, 2026.

Key takeaways from the study:

- Profound compared identical portfolios run once and ten times daily across 753 prompts and seven platforms for two weeks.
- Once-daily visibility estimates landed within about two percentage points of the heavier measurement.
- Additional runs reduced citation-share noise more than visibility noise, but could not remove day-to-day platform drift.
- Prompt portfolio composition mattered more than run frequency, especially for citation share.

These results came from a large portfolio and specific setup. Small cohorts, experiments, and noisy citation questions may need repeated runs.

## Goal

Build a prompt portfolio whose composition matches the business question and whose cadence is sufficient to distinguish useful movement from noise.

## Intake

Collect:

- brand, products, audience, competitors, and business objective
- engines, models or surfaces, markets, languages, and personas
- real prompt-demand data when available
- customer research, search terms, sales calls, support questions, and category vocabulary
- monitoring budget and required decision cadence

## Portfolio design

Cover relevant intent families:

- category discovery
- problem and solution research
- comparisons and alternatives
- recommendations and "best for" decisions
- trust, risk, and validation
- pricing, availability, compatibility, and limitations
- implementation and troubleshooting
- local, shopping, or regulated intents when applicable

Do not turn every keyword into a conversational prompt. Prefer observed demand and preserve the user's natural language.

## Workflow

1. State the measurement question before selecting prompts.
2. Cluster demand by user job, intent, stage, product, audience, language, and market.
3. Assign business value and evidence quality to each cluster.
4. Select representative prompts without allowing one cluster or wording pattern to dominate.
5. Create three cohorts:
   - stable core for trend measurement
   - exploratory cohort for emerging demand
   - diagnostic controls for known outcomes
6. Add paraphrase variants only where wording sensitivity must be measured.
7. Keep engines, markets, languages, and personas as separate configurations.
8. Choose cadence:
   - default to once daily for a broad monitoring portfolio
   - add repeated runs for small samples, short experiments, or citation-share precision
9. Define minimum observation window, change-control rules, and review cadence.
10. Version the portfolio and document every addition, removal, or weighting change.

Never compare periods that used materially different portfolios without recalculating a common cohort.

## Output

Return:

1. Measurement question and scope.
2. Demand model with cluster, user job, stage, evidence, and business value.
3. Prompt portfolio with cohort, prompt, variants, engine, market, language, and rationale.
4. Coverage analysis showing over- and underrepresented clusters.
5. Cadence and sample plan.
6. Versioning rules and change log template.
7. Reporting guidance covering uncertainty, platform drift, and portfolio changes.