Context Problem Solver

Fix prompts with wrong assumptions about your context

analysisbeginnerContext ManagementIndustry Specifics350-450 words

Customize Your Prompt

Fill in the variables to generate your personalized prompt

Problematic Prompt

Your Industry

Company Stage

Additional Context (Optional)

Preview

See how your prompt will look with the current variables

AI makes wrong assumptions about [Your Industry] and [Company Stage] with: "[Problematic Prompt]"

Role: Product Context Expert with deep industry knowledge.

Instructions:
1. Identify incorrect assumptions
2. Add explicit context constraints
3. Include negative examples (what NOT to assume)
4. Add verification questions
5. Industry-specific parameters

Specifics:
## Assumption Analysis
**Incorrect Assumptions:**
1. [Assumption and why it's wrong for [Your Industry]]
2. [Assumption and correction for [Company Stage]]

## Context Enhancement
**Industry Context:** [[Your Industry] specific constraints]
**Company Stage:** [[Company Stage] considerations]
**User Base:** [Characteristics that matter]
**Constraints:** [Resource/regulatory/technical]

## Revised Prompt with Guards
[Enhanced prompt with explicit context]

**Guard Rails Added:**
- "Note: We are a [Company Stage] [Your Industry] company, NOT..."
- "Our users are [specific], not [common assumption]"
- "Consider [industry-specific factor]"

## Validation Questions
AI should ask these if unclear:
1. [Clarifying question 1]
2. [Clarifying question 2]

Purpose: Ensure AI understands your specific context.

## Evidence and accuracy
- Use supplied facts and verified sources. Do not invent metrics, quotes, people, company details, commitments, or personal experience.
- Mark assumptions [ASSUMPTION], estimates [ESTIMATE: method], and unresolved questions [UNCERTAIN: reason]. Leave unavailable values unfilled rather than guessing.
- Explain confidence as high, medium, or low using the evidence available. These labels are judgments, not calibrated probabilities. Give numerical probabilities only when a stated method supports them.
- Treat preset weights, scores, timelines, and targets in this template as starting examples. Adapt them to the task and explain changes; they are not universal benchmarks or approved commitments.
- Define score scales and directions before calculating totals. Keep units, denominators, and time periods consistent. Do not average away a critical blocker.
- Use only exact supplied or verified quotes with attribution. Label requested fictional examples as illustrative. Distinguish observed behavior from inferred motives or causes.
- Use only the sections and rows the task needs. Write plainly, preserve necessary technical terms, and avoid unsupported benefits or forced specificity.
- Identify missing information needed for a decision. Recommendations remain proposals until reviewed by the responsible team.

## Evidence and accuracy
- Use supplied facts and verified sources. Do not invent metrics, quotes, people, company details, commitments, or personal experience.
- Mark assumptions [ASSUMPTION], estimates [ESTIMATE: method], and unresolved questions [UNCERTAIN: reason]. Leave unavailable values unfilled rather than guessing.
- Explain confidence as high, medium, or low using the evidence available. These labels are judgments, not calibrated probabilities. Give numerical probabilities only when a stated method supports them.
- Treat preset weights, scores, timelines, and targets in this template as starting examples. Adapt them to the task and explain changes; they are not universal benchmarks or approved commitments.
- Define score scales and directions before calculating totals. Keep units, denominators, and time periods consistent. Do not average away a critical blocker.
- Use only exact supplied or verified quotes with attribution. Label requested fictional examples as illustrative. Distinguish observed behavior from inferred motives or causes.
- Use only the sections and rows the task needs. Write plainly, preserve necessary technical terms, and avoid unsupported benefits or forced specificity.
- Identify missing information needed for a decision. Recommendations remain proposals until reviewed by the responsible team.

Context to include

• State the industry, company stage, and relevant constraints.
• State assumptions to avoid, such as an enterprise budget your team does not have.
• Identify missing facts the model should ask about before answering.
• Provide relevant details about users, budget, compliance, data sources, and markets.
• Ask the model to identify the assumptions behind each recommendation.

Common Context Mistakes

• Leaving the model to guess your industry or company stage.
• Omitting constraints that affect which recommendations are feasible.
• Asking for recommendations without relevant facts about geography, customers, or channels.
• Leaving out assumptions you know would be wrong for this task.

Context questions

Why might the advice miss my situation?

Check the assumptions behind it. Supply your industry, company stage, target customer, budget, and constraints before asking for recommendations.

Do I need negative examples?

They can help rule out inappropriate assumptions. For example, tell the model not to assume you have an enterprise sales team when that affects the task.

How to use this prompt