Hypothesis & MECE

Problem Structuring

For: Engagement managers and consultants scoping a new problem

Issue tree builder: from vague client ask to testable hypotheses

New engagement, vague problem statement. Build the issue tree and the week-one analysis plan before the team burns days boiling the ocean.

Copy & paste into your own LLM · open in archive →

You are an engagement manager structuring a new client problem. I will paste the raw ask and context. Produce:

A) PROBLEM STATEMENT — restate the ask as one specific, measurable, time-bound question, using the client's own words where possible. List what the question deliberately excludes.

B) ISSUE TREE — 3 levels, MECE at each level, every branch phrased as a testable hypothesis (not a topic). Present as a table: hypothesis, data needed to prove or kill it, likely source, effort (S/M/L).

C) WEEK-ONE PLAN — the 5 analyses ranked by kill-power: which would change the overall answer fastest if the hypothesis fails.

Inputs: [PASTE CLIENT ASK / RFP EXCERPT / KICKOFF NOTES] · [INDUSTRY + CLIENT CONTEXT] · [ENGAGEMENT LENGTH + TEAM SIZE]

Rules: Do not invent client facts or market numbers — mark every assumption as an assumption and keep them in a separate list. Verify data availability with the client before committing the plan. Never include client-confidential material beyond what I pasted, and anonymize the client in your output.

Why it works: An issue tree is only useful if the branches are testable — 'understand the market' is a topic, not a hypothesis. Ranking week one by kill-power operationalizes the 80-20 rule: you spend the first week on analyses that could change the answer, not the ones easiest to start.

Useful? 👍 Yes👎 No

From Data to So-What

Research & Synthesis

For: Research leads synthesizing interviews, surveys, and desk research

Interview synthesis: 12 transcripts into findings your partner will sign

Two weeks of expert interviews sit in a folder. Get to defensible findings — with quote-level evidence — before the midpoint readout.

Copy & paste into your own LLM · open in archive →

You are a consulting research lead synthesizing qualitative interviews. I will paste anonymized interview notes or transcripts. Produce:

A) FINDINGS TABLE — maximum 6 findings, columns: finding (one sentence, so-what phrasing), supporting evidence (interviewee number + short verbatim quote), count of interviewees supporting it, confidence (strong / emerging / single-source).

B) CONTRADICTIONS — where interviews genuinely disagree: both positions, who holds each, and what evidence would resolve it.

C) GAPS — the 3 questions still unanswered and which type of interviewee could answer each.

Inputs: [PASTE ANONYMIZED NOTES/TRANSCRIPTS, LABELED BY INTERVIEWEE NUMBER + ROLE TYPE] · [THE ENGAGEMENT QUESTION THIS RESEARCH SERVES]

Rules: Do not invent, merge, or paraphrase quotes into stronger claims — every finding must trace to at least one pasted line, and single-source findings must carry the single-source label. Verify counts before the readout. Keep all names out — interviewee numbers and role types only.

Why it works: Synthesis fails two ways: cherry-picked quotes or unfalsifiable mush. Source-counting plus confidence labels stops one loud interview from becoming 'the market says', and the contradictions section is where partners actually add value in review.

Useful? 👍 Yes👎 No

Storyline & Slides

Client Deliverables

For: Consultants turning finished analysis into partner-ready documents

Pyramid-principle storyline: from findings to a board-ready narrative

The analysis is done; the deck is not. Turn findings into an action-titled storyline the partner can review in 10 minutes.

Copy & paste into your own LLM · open in archive →

You are a senior consultant drafting a deck storyline using the pyramid principle. I will paste the findings and the recommendation. Produce:

A) GOVERNING THOUGHT — the one-sentence answer to the client's question.

B) STORYLINE — 8 to 12 action titles that read as a complete argument when read alone, grouped situation -> complication -> resolution. Present as a table: slide number, action title, the exhibit that proves it (spec, not sketch), data source.

C) PRESSURE-TEST — the 5 hardest questions the client CFO would ask, and which slide answers each. Write "gap" where none does.

Inputs: [PASTE FINDINGS + RECOMMENDATION] · [AUDIENCE + DECISION THEY MUST MAKE] · [MEETING LENGTH]

Rules: Do not invent data or exhibits — where evidence does not exist yet, write "exhibit needed" with what it must show. Verify every number that appears in an action title against the model before circulation. Strip client-confidential identifiers from the storyline.

Why it works: Action titles that carry the whole argument are the fastest partner-review loop in consulting — if the titles do not hold, no exhibit will save the deck. Mapping CFO questions to slides finds the gaps before the room does, while they are still cheap to fix.

Useful? 👍 Yes👎 No

Sessions That Decide

Workshop & Facilitation

For: Consultants designing and running client workshops and steering sessions

Workshop designer: an agenda engineered to end in a decision

You own a 3-hour steering workshop next week. Design the agenda, exercises, and pre-read so it ends with a decision instead of a parking lot.

Copy & paste into your own LLM · open in archive →

You are a facilitation designer engineering a client workshop that must end in a decision. I will describe the decision and the room. Produce:

A) AGENDA — a table: block, duration, exercise format (silent brainstorm, dot-vote, 2x2 sort, breakout-and-readback), input required, and the output artifact each block must produce.

B) DECISION MECHANISM — state explicitly how the final call gets made: criteria, who decides, what happens on a tie. This goes in the agenda, announced up front.

C) PRE-READ OUTLINE — 2 pages maximum: the decision, the options, the data each attendee must arrive knowing.

D) FAILURE MODES — the 3 most likely ways THIS group derails (e.g., senior-voice domination, relitigating scope, data disputes) with one concrete facilitation move to counter each.

Inputs: [THE DECISION TO BE MADE + OPTIONS ON THE TABLE] · [ATTENDEES: ROLE + LIKELY STANCE] · [DURATION + FORMAT (ROOM/REMOTE)]

Rules: Do not invent attendee opinions — stances I have not given you are "unknown: probe in the opening check-in". Verify logistics constraints before finalizing. Keep client-confidential material out of the pre-read outline.

Why it works: Workshops fail in the design, not the room. Naming the decision mechanism up front is the single highest-value move — most groups argue about options endlessly because nobody agreed how the call gets made — and per-block output artifacts kill the sticky-note theater.

Useful? 👍 Yes👎 No

On Scope, On Story

Engagement Management

For: Engagement managers running teams, scope, and the client relationship

Weekly client status: progress, risks, and the scope-creep firewall

Friday status is due. Turn the team's raw week into a status the sponsor actually reads — and a scope conversation before it becomes a scope fight.

Copy & paste into your own LLM · open in archive →

You are an engagement manager writing the weekly status to the client sponsor. I will paste the team's raw updates. Produce:

A) STATUS ONE-PAGER — sections: headline (one plain-language sentence on where the engagement stands), progress vs plan (done / due / slipped, each slip with its reason), decisions needed from the client (each with a deadline and the cost of delay), top 3 risks (likelihood x impact).

B) SCOPE WATCH — every request this week that sits outside the SOW, sized S/M/L, with a recommended response: absorb / trade / change order.

C) NEXT WEEK — 3 commitments maximum, each verifiable.

Inputs: [PASTE TEAM UPDATES] · [SOW SCOPE SUMMARY] · [WORKPLAN STATUS] · [OPEN CLIENT ASKS]

Rules: Do not invent progress or soften slippage — slipped means slipped, with the reason stated. Verify the decisions-needed list with workstream leads before sending. Never include individual staff performance notes or client-confidential HR matters in the status.

Why it works: Status reports rot into optimism theater. Cost-of-delay on each client decision flips the dynamic — the sponsor sees their own bottleneck in writing — and a weekly, sized scope watch turns creep into a business decision instead of a month-three billing dispute.

Useful? 👍 Yes👎 No

Which section is most useful to you this week?

One tap — it shapes which prompt leads next week.

What would you like to see more of?

Prompt of the Week (Pro)

This week's bonus: a proposal-qualification screen that pressure-tests an RFP against your firm's win profile — scope clarity, budget signals, incumbent presence — before you spend a weekend on a deck you were never going to win.

Your searchable archive

Every prompt we’ve shipped, organized by section and task.