Turn a vague request into a structured discovery conversation before generating the deliverable.

Tip

Use a Reverse Interview. Instead of asking AI to immediately create a proposal, strategy, coaching plan, campaign, or analysis, instruct it to interview you first. Require one question at a time, explain why each question matters, and stop when it has enough information to produce the requested result. End the discovery phase with a summary of what it heard, unresolved assumptions, and your approval to proceed.

Why It Matters

Most disappointing AI output begins with an underspecified request. Business leaders know the situation but often omit the context a model needs: decision criteria, audience maturity, constraints, existing assets, risk tolerance, success measures, and what has already failed. A Reverse Interview converts tacit knowledge into explicit requirements. It also mirrors the strongest consulting behavior: diagnose before prescribing.

Business Impact

The time investment occurs before drafting, but the savings appear in fewer rewrites and stronger decisions.

·    Planning estimate: invest 8-15 minutes in discovery to avoid 30-90 minutes of revision on complex work.

·    Reduce proposal, campaign, and content rework by surfacing constraints before the first draft.

·    Improve client experience because recommendations reflect the actual situation rather than generic assumptions.

·    Create a reusable discovery transcript that can inform scope, delegation, and measurement.

Three Specific Use Cases

Small Business: A coach asks AI to conduct a discovery interview before creating a premium group program, including audience, transformation, delivery constraints, proof, pricing logic, and risk.

Enterprise: A transformation lead uses a Reverse Interview to define an AI use case before requesting a business case, identifying data, process volume, owners, controls, and success measures.

Personal Productivity: A professional lets AI ask about energy, deadlines, dependencies, and priorities before building a realistic weekly plan.

Example

A consultant initially asked AI to create a statement of work from a short client description. The draft looked polished but assumed training, integration, and support that had never been discussed. The consultant restarted with a Reverse Interview. Twelve focused questions uncovered the decision maker, required systems, security review, timeline, excluded work, and success metric. The resulting proposal required one minor edit instead of a full rewrite.

Ready-to-Use Prompt

Do not create the deliverable yet. First, conduct a Reverse Interview so you understand the business problem.

Requested deliverable: [PROPOSAL / STRATEGY / PLAN / CONTENT / ANALYSIS]
Desired business outcome: [OUTCOME]

Interview rules:
1. Ask one question at a time.
2. Ask no more than [10-15] questions unless I approve more.
3. Prioritize questions that could materially change the recommendation.
4. Briefly explain why each question matters.
5. Do not ask for information already provided.
6. If I do not know an answer, offer 2-3 practical options rather than inventing one.

Cover these areas when relevant:
- Audience or stakeholder
- Current process and pain point
- Desired outcome and success measure
- Constraints, budget, timeline, and resources
- Existing assets or systems
- Risk, privacy, security, or compliance
- What has already been tried
- Non-negotiables and exclusions

After the final question, provide:
A. What I heard
B. Confirmed requirements
C. Open assumptions
D. Recommended scope
E. A PROCEED / CLARIFY / ESCALATE status

Wait for my approval before creating the deliverable.

Pro Tip

Ask the AI to rank its questions by decision impact before beginning. For client work, save the approved discovery summary as the front page of the project so every later deliverable traces back to the same requirements.

Common Mistake

The common mistake is allowing the AI to ask a long questionnaire all at once. That creates rushed answers and missed follow-up questions. Ask one question at a time so each response can shape the next question. The second mistake is skipping the summary-and-approval step; without it, the AI may still proceed on a misunderstood premise.

Measure Success

·    Material revisions per deliverable after the first draft.

·    Requirement completeness: percentage of required fields confirmed before drafting.

·    Cycle time from initial request to approved deliverable.

Avoid Using This When

Do not use a general-purpose Reverse Interview to collect highly sensitive personal, health, financial, employment, or regulated information unless the tool and workflow are approved for that data. Do not let the interview become a substitute for direct stakeholder research when affected people need to be heard.

Best Tool For

ChatGPT and Claude are especially effective for adaptive, one-question-at-a-time discovery. Microsoft Copilot is useful when the interview must be followed by work in Microsoft 365. Gemini is useful when the resulting plan will draw from Google Workspace files. A customized project, Gem, or notebook can preserve the interview method for repeated use, but the interview still needs a human to confirm what was understood.

Create one governed briefing kit that improves every future AI conversation.

Every time you retype your audience, offer, tone, rules, and examples, you are paying a context tax.

Tip

Build a reusable Context Pack for one recurring workflow. Include the business objective, intended audience, approved facts, terminology, brand voice, decision rules, examples of acceptable work, examples of unacceptable work, required output format, and a short list of boundaries. Store it in a persistent AI workspace such as a project, notebook, or customized assistant. Before each task, add only the information that is unique to that situation. Review the pack on a schedule so the AI is not relying on stale pricing, policies, or positioning.

Why It Matters

AI quality often appears inconsistent because the briefing is inconsistent. A Context Pack moves critical knowledge out of one person's memory and into a repeatable operating asset. It reduces prompt length, improves first-pass quality, accelerates onboarding, and helps protect a coach's methodology or a consultant's delivery standard. The real advantage is not a longer prompt. It is a clearer source of truth.

Business Impact

Measure the time avoided and the reduction in corrections. Use a two-week baseline before estimating ROI.

·    Planning estimate: remove 10-20 minutes of repeated briefing from each recurring task.

·    At six tasks per week, a 15-minute reduction returns about 1.5 hours before counting less rework.

·    Improve first-pass consistency across proposals, content, client recaps, research briefs, and internal documents.

·    Reduce key-person dependency because approved context can be reused by other team members.

Three Specific Use Cases

Small Business: A consultant creates a Client Proposal Context Pack with approved services, pricing rules, proof points, exclusions, proposal structure, and sample language.

Enterprise: A product team builds a launch notebook containing the strategy, customer research, terminology, risk register, approved claims, and decision owners.

Personal Productivity: A professional creates a career-search project with a master resume, target roles, quantified accomplishments, preferred tone, and application tracker conventions.

Example

An executive coach was repeatedly correcting AI-generated session recaps because the language sounded generic and occasionally crossed into advice the coach would not give. The coach created a Context Pack with the coaching philosophy, prohibited claims, preferred reflection questions, sample recaps, confidentiality rules, and the exact recap structure. Average editing time fell from 28 minutes to 11 minutes across the next ten recaps while the coach retained final review.

Ready-to-Use Prompt

You are working inside a reusable Context Pack for [WORKFLOW NAME].

Use the approved context below as the primary source of truth. Do not invent missing business facts.

Business objective: [OBJECTIVE]
Audience: [AUDIENCE]
Approved facts and terminology: [FACTS / GLOSSARY]
Brand or communication standard: [VOICE / STYLE]
Decision rules: [RULES]
Required output format: [FORMAT]
Approved example: [PASTE EXAMPLE]
Unacceptable example or pattern: [PASTE EXAMPLE]
Boundaries: [PRIVACY / LEGAL / POLICY / CLAIMS]

Before doing the task:
1. List any missing information that could materially change the result.
2. Identify any conflict between the new request and the Context Pack.
3. State which context items you will apply.

Task-specific information:
[PASTE ONLY WHAT IS UNIQUE TO THIS TASK]

Deliver the requested output, followed by a short Context Audit:
- Context used
- Assumptions made
- Items requiring human verification

Pro Tip

Add source priority and expiration dates. For example: current pricing sheet overrides old proposals; signed policy overrides workshop notes; client-specific instructions override general style guidance. Include an owner and next-review date on every high-value Context Pack.

Common Mistake

The common mistake is uploading every document available and calling it context. More material can create more contradiction. Curate the smallest set that contains current, approved, high-value information. Remove duplicates, archive stale files, and label what is authoritative.

Measure Success

·    Average briefing time per recurring task.

·    First-pass acceptance rate: outputs approved with no material structural or factual correction.

·    Context correction rate: outputs changed because the AI used stale, conflicting, or missing context.

Avoid Using This When

Do not place confidential client data, employee information, trade secrets, or regulated information into a workspace that your organization has not approved. Do not let a Context Pack become an unattended archive. Stale prices, policies, legal language, or service promises can make consistent output consistently wrong.