For PE deal teams and corp dev: 10 Claude prompts that build a full sector overview from public filings, market size, players, margin pools, the shift incumbents miss. Replaces the McKinsey market map engagement.
Free — runs in your own ClaudeMedium setup · 4 steps10 ready-to-run prompts
Three minutes, four steps, nothing to install by hand
Claude sets it up for you. You just paste.
Never used Claude? It is free and takes 30 seconds to open. Copy the instruction below, paste it into Claude, and it reads this page and walks you through everything, one question at a time.
1
Tell Claude how to talk to you
One tap. It changes how much Claude explains, and how slowly it goes. You can change it any time.
2
Copy your setup instruction
A short instruction plus a link to this page lands on your clipboard. First copy asks for your email once. That unlocks every button across the whole library.
3
Open Claude in a new tab
Free account, no card, 30 seconds. This tab stays open so you can come back.
Claude reads this page, asks one question about your work, then guides you step by step until your first output is right. If anything looks wrong, tell Claude what you see, and it fixes it with you.
▸Prefer the full prompt instead of the link? (optional)
I am comfortable copy-pasting and following instructions, but I am not a developer.
There is nothing to install for this one and no commands to type: it all happens inside Claude. If any instruction below implies a Terminal, translate it into the equivalent click path for me instead.
- Plain English. Define jargon the first time it appears.
- One step at a time, then wait for me to confirm before the next one.
- Tell me what success looks like at each step, and diagnose any error before moving on.
Follow the instructions below with those rules applied.
If you can browse the web, open and read this page in full first, it has the complete guide and every prompt you will run (the vault is under the-vault anchor): https://consultance.ai/library/sector-overview-engine#the-vault . If you cannot open links, tell me and I will paste the page in, do not guess the prompts.
I want to INSTALL the real setup so Claude builds a sector overview from the actual filings, not just a chat demo. Walk me through it step by step, do not skip the install. Treat me like a deal-team lead, corp-dev, or CFO who has never built a Claude Project or installed an Office add-in, and define every term once.
One honest thing up front: this vault is about 60% of the build. It reads the filings you load and cites every number. The last 40%, pulling the filings automatically, keeping the map live, wiring it into your deal tooling, is the proper integration, and that is the part consultance wires into production. You can run the whole map by hand today with what is below; the wiring is a call, not a prompt.
This is NOT a Terminal or coding install. There is nothing to compile. It is two paths: a private Claude Project for the filings (recommended) and an optional Excel add-in for the market-size and player tables.
## Path 1 (RECOMMENDED) — a private Claude Project for the sector map
This is where the 10-Ks, 10-Qs, S-1s, annual reports, and investor decks live so every prompt reads from one governed place.
Walk me through ONE step at a time, waiting for me to confirm each:
1. **What I need.** A Claude account. Pin **Claude Opus 5**. Nothing to install for this path. (Opus 5 is the model name, the current frontier for this work; pin it in the model picker.)
2. **Create the mapping workspace.** In Claude, create a new **Project** named for the sector or the deal. A Project is a private workspace with its own knowledge that other chats cannot see. Your target list, deal notes, and any private data stay in your own tenant.
3. **Load the filings.** Drop the 10-Ks, 10-Qs, S-1s, annual reports, and investor presentations for the players into the Project knowledge. A 10-K is a company's annual filing; a 10-Q is quarterly; an S-1 is the filing before an IPO. Public filings only, nothing you are not allowed to hold.
4. **Run the vault.** Run prompt 01, pick why you need the map, the sector and geography, and your data source (A) upload (or (D) connector if you pull from Capital IQ, FactSet, or EDGAR under your own access). Then run 02 to 10 in order: frame the market, size it, rank the players, trace the margin, flag the shift, build the one chart, the reconciliation self-check, the overview page, and the Q&A hardening.
5. **Gate it.** Run prompt 08 before the overview ships. A reconciliation FAIL (a share table that does not sum, an uncited headline number) is a number to fix, not a footnote.
6. A named human signs the overview. This is a working tool, not investment advice.
## Path 2 (OPTIONAL) — Claude for Excel add-in for the tables
If I want the market-size table and the player ranking to live in real formulas:
1. In Excel (Microsoft 365 desktop or web): **Home** or **Insert** tab, **Add-ins** or **Get Add-ins**, search **"Claude"**, **Add**. Tell me where the button is in my version.
2. Sign in to the docked Claude side panel.
3. In vault prompt 01 choose data source (C) Excel add-in. For prompt 03 (market size) and prompt 04 (player ranking) say "build this into my workbook as real formulas," so the tables recompute and the prompt 08 tie-out runs on live cells.
4. Pin **Claude Opus 5** for the framing, sizing, and write-up.
## First session after setup — the drill
Once I am set up, do not leave me at a blank prompt. Walk me through the highest-value run:
- **The input:** the filings for the three or four players I already know in the sector, loaded into the Project.
- **First prompt to run:** prompt 01 (the router), then prompt 03 (size the market from disclosed numbers).
- **What good output looks like:** a market-size table where every cell cites a filing and a page, a low-high range instead of a false-precision point, and every estimate labeled ESTIMATE with its method.
- **The check before I trust it:** run prompt 08 (reconciliation self-check). If the player shares do not sum to 100 percent or a headline number is uncited, fix it before the overview ships.
## Rules for walking me through this
- One step at a time. Define every term once: Project, knowledge, 10-K, 10-Q, S-1, MD&A, margin pool, ESTIMATE flag, `<review_gate>`, `{{TOKEN}}`.
- Do NOT tell me a step is "not possible." If the Excel add-in is missing, check Excel for Microsoft 365, try Excel on the web, or AppSource. For the Project path there is nothing to install.
- Public filings only. Never paste material non-public information or anything I am not allowed to hold into a public Claude window. Use a Project with your tenant controls.
- A named human signs the overview. Claude reads the filings and ties the numbers; a person owns the call. Not investment advice.
- The official EDGAR, Capital IQ, and FactSet docs are a bonus path if I want to wire a data pull later, never required to run the vault by hand.
First message: ask me "Path 1 (Claude Project for the filings, recommended) and do you also want Path 2 (Excel add-in for the tables)? And which sector are you mapping, and is it for a pitch, diligence, or a board review?" Then start step 1.
Step 2 · run it on your data
Step 1 set it up. These 10 prompts do the work.
the vault
The 10 prompts
Grab the whole pack as one file, or tap any prompt below to copy it on its own. Placeholders that look like {{THIS}} get swapped for your own numbers — and if you ran Step 1, Claude fills them in for you.
One .md file · all 10 prompts, numbered, in order · nothing left out.
<role>You are a sector-coverage team in one: a McKinsey engagement manager who frames the market, an equity-research analyst who reads the filings line by line, and a private-equity deal lead who only cares about where the money actually pools. You build a market overview the way a strategy team does: state the question, show the disclosed number behind every claim, and defend the map.</role>
<onboarding>
Before any analysis, set up the engagement. Ask me to confirm each block. Offer the options. Do not assume.
1. WHY THE MAP — what is this for?
(A) A pitch or a deal I am marketing (banker / advisor)
(B) Diligence on a target or a sector I am about to enter (PE / corp dev)
(C) A board or strategy review of a market I already play in (CFO / strategy lead)
(D) A screen to find where to hunt next (GP / sourcing)
2. SCOPE — what are we mapping?
Sector or theme: {{SECTOR}}
Geography: {{GEOGRAPHY}}
The named players you already know: {{KNOWN_PLAYERS}}
The one question the map must answer: {{CORE_QUESTION}}
3. WHERE DO THE FILINGS LIVE? Pick all that apply. This decides how the next prompts run.
(A) I will upload the filings (10-K, 10-Q, S-1, annual reports, earnings decks, investor presentations) into this Claude project's knowledge.
(B) I will paste the raw disclosures (revenue lines, segment tables, MD&A) into the prompt.
(C) I have the Claude add-in for Microsoft Excel, build the market-size and player tables in my workbook.
(D) I pull from a governed data source (Capital IQ, FactSet, EDGAR full-text, a market database) under my own access.
(E) A mix of the above.
4. OUTPUT BAR — confirm: every market-size and revenue figure is cited to the exact filing and page it came from, every estimate is labeled ESTIMATE with its method, private or paywalled sources are named not quoted, and a number I cannot source is a gap I flag, not a number I invent.
</onboarding>
<rules>
- Public filings and disclosed figures only. Never fabricate a revenue, a share, or a market size. If it is not in a filing or my input, ask or label ESTIMATE / DISCLOSURE GAP with the method.
- Match every later prompt to the data source I chose in step 3.
- Cite every figure back to the source filing and page. An uncited number does not ship.
- Always end with "Next step:" and the next prompt to run.
</rules>
Confirm my blocks back to me, then wait for prompt 02.
<role>Engagement manager framing the market before anyone counts a dollar.</role>
<task>
Using the data source from prompt 01:
1. Define the market boundary for {{SECTOR}} in {{GEOGRAPHY}}: what is in, what is out, and the one-line reason for each edge. A map with a fuzzy boundary is worthless.
2. Segment the market the way the buyers and the filings actually describe it (by product, by end customer, by channel), not by a textbook taxonomy.
3. State the core question from prompt 01 as the question this whole map exists to answer.
4. List the public sources you will read to size and populate the map, ranked by reliability.
</task>
<constraints>Use the data source from prompt 01. Every segment must be one a real player reports or a filing describes. Flag any segment you are inventing to make the map tidy.</constraints>
<review_gate>State the boundary and the segmentation, and name the single question the map answers, before sizing anything.</review_gate>
Then "Next step:".
<role>Equity-research analyst sizing the market from the bottom up, out of filings.</role>
<task>
For the market framed in prompt 02:
1. Build the market size from disclosed revenue: sum the segment revenue the named players report, then bridge to a total-market estimate and show the bridge.
2. Where a player is private or does not break out the segment, estimate from the nearest disclosure (a comparable public peer, a filed customer count, a stated price) and label it ESTIMATE with the method and the source.
3. Give three-year historical growth from the filings and the one disclosed driver behind it (price, volume, mix).
4. State the range, not a false-precision point: the defensible low and high, and what moves the number between them.
</task>
<output_format>A MARKET-SIZE TABLE: segment, disclosed revenue, source filing and page, ESTIMATE flag where used. Then the total with its low-high range.</output_format>
<constraints>Use the data source from prompt 01. Top-down analyst reports are a cross-check, never the primary number. Every cell traces to a filing or a labeled estimate. No uncited total.</constraints>
<review_gate>Show the bottom-up bridge and the low-high range. Do not present a single point number as fact.</review_gate>
Then "Next step:".
<role>Deal lead ranking the field by what the filings actually disclose, not by brand or vibes.</role>
<task>
For the players in scope:
1. Rank them by disclosed segment revenue (or the closest disclosed proxy), largest to smallest. Show the number and the source for each.
2. For each material player: the segment revenue, the growth rate, and the one line on what they actually sell into this market.
3. Compute the share concentration: what the top three and top five hold, and whether the market is consolidating or fragmenting on the disclosed trend.
4. Flag the players everyone names that are smaller than their noise suggests, and the quiet ones larger than their profile.
</task>
<output_format>A PLAYER TABLE: player, disclosed revenue in this market, growth, share, source. Ranked. ESTIMATE flag where a figure is derived.</output_format>
<constraints>Use the data source from prompt 01. Rank on disclosed revenue, never on headcount, funding, or press. Name the filing behind every rank.</constraints>
<review_gate>State the top-three share and whether the market is consolidating or fragmenting, with the numbers behind the call.</review_gate>
Then "Next step:".
<role>Private-equity analyst following the profit, not the revenue.</role>
<task>
From the filings:
1. Pull the disclosed segment or company margin for each material player: gross and operating where disclosed, and the trend over three years.
2. Identify where in the value chain the margin actually sits (the manufacturer, the platform, the distributor, the service layer) and why the filings say it sits there.
3. Separate the players earning a structural margin from the ones renting it (a temporary price umbrella, a subsidy, a one-off).
4. Name the pool a buyer would actually want to own, and the reason it is defensible.
</task>
<constraints>Use the data source from prompt 01. Margin claims come from disclosed financials, not from a narrative. If a player does not disclose segment margin, say so and bound it from the nearest proxy.</constraints>
<review_gate>State where the margin pools and whether it is structural or rented, with the disclosed margins behind the call.</review_gate>
Then "Next step:".
<role>Strategist reading the filings for the change the market has not priced.</role>
<task>
1. Read the MD&A, risk factors, and capex disclosures across the players for the structural shift underway (a channel moving, a technology substituting, a regulation landing, a customer disintermediating).
2. Separate the shift the incumbents are quietly funding (watch the capex and the language) from the one they are publicly dismissing.
3. State who wins and who is exposed if the shift plays out, with the disclosed evidence for each.
4. Give the single non-consensus read the map supports, and the disclosed fact that would prove or kill it.
</task>
<constraints>Use the data source from prompt 01. Ground the shift in disclosed capex, risk-factor language, or a filed number, not in a hunch. Label the non-consensus call as a view, with its falsifier.</constraints>
<review_gate>State the shift, who is exposed, and the one disclosed fact that would disprove the call.</review_gate>
Then "Next step:".
<role>Engagement manager designing the single exhibit that carries the whole map.</role>
<task>
From prompts 03 to 06, design the ONE chart the board will remember: usually a market-map quadrant (share vs growth, or margin vs share) or a value-chain margin bridge.
1. Pick the chart form that answers the core question from prompt 01 in one look.
2. Specify it fully: axes, the metric on each, every player plotted with its disclosed number, and the source note.
3. Write the one-sentence takeaway that sits under the chart, the line the board repeats in the next meeting.
If I am in Excel add-in mode, build the chart data table in my workbook. Otherwise output a clean, plot-ready table plus the chart spec.
</task>
<constraints>Use the data source from prompt 01. Every plotted point is a disclosed or labeled-estimate figure with a source. One chart, not five. The takeaway must be defensible from the plotted data alone.</constraints>
<review_gate>State the chart form, the takeaway line, and confirm every plotted point is sourced.</review_gate>
Then "Next step:".
<role>You are a map reviewer. Your only job is to catch inconsistency and arithmetic errors before the overview reaches the committee or the board. You trust nothing; you recompute.</role>
<task>
Re-derive the key numbers a SECOND way and reconcile against the earlier prompts. Do not copy earlier outputs, recompute, then compare.
1. Market size: the bottom-up total (prompt 03) reconciles to the sum of the ranked player revenues plus the estimated private tail (prompt 04). Show both, show the delta.
2. Shares: the player shares (prompt 04) sum to 100 percent of the total market (prompt 03), including the residual "all others". Confirm.
3. Margin: the pooled-margin call (prompt 05) is consistent with the disclosed margins in the player table, not a separate narrative. Show the tie.
4. Sourcing: every headline number in the map (size, top-three share, the pooled margin, each plotted point) traces to a named filing or a labeled ESTIMATE. List any uncited number.
5. The shift call (prompt 06) has its named falsifier attached. Confirm.
</task>
<output_format>A RECONCILIATION TABLE: one row per check (1 to 5), columns = check, value A, value B, delta, PASS/FAIL. Then a one-line verdict.</output_format>
<review_gate>Any FAIL stops the ship. Tell me what to fix; do not present the overview with an open FAIL or an uncited headline number.</review_gate>
Then "Next step:".
<role>Coverage lead writing the one-page sector overview that opens the pack.</role>
<task>
Synthesize prompts 02 to 08 into the page every pitch, board deck, and diligence pack opens with:
1. The headline read up top: the market, its size and range, and the one-line answer to the core question.
2. Market size and growth, with the bridge and the range.
3. The players ranked by disclosed revenue, and the concentration call.
4. Where the margin pools and whether it is structural.
5. The shift underway, who wins, who is exposed, and the falsifier.
6. The one chart, with its takeaway line.
7. The two-line "so what" for the reader: the deal, the board decision, or the hunt this map points to.
One page of substance. Plain English. Every number sourced. No filler.
</task>
<review_gate>Every figure traces to a filing or an earlier prompt. Do not write this page if prompt 08 left any check on FAIL, fix it first. A named human owns the call; this is a working tool, not investment advice.</review_gate>
Then "Next step:".
<role>The skeptic on the other side of the table: the IC member, the board chair, the seller's banker.</role>
<task>
Stress the overview before it is defended live:
1. Generate the ten hardest questions a sharp reader asks (Where did the market size come from? Why is that player ranked there? Is that margin real or a one-off? What kills your shift call?).
2. Answer each from the disclosed data in the map, or mark it a known gap with the honest bound.
3. Flag the two places the map is weakest and what one extra filing or data pull would firm them up.
4. Produce the short defensibility note: the sources, the estimates and their method, and the named human sign-off line.
</task>
<constraints>Use the data source from prompt 01. Answer from the map's own sourced numbers. A weak spot named honestly beats a confident bluff, mark the gaps.</constraints>
<review_gate>List every remaining gap in its own block. The overview ships with the gaps disclosed, never hidden.</review_gate>
Then "Next step:".
Got the prompts. Want them wired into your actual stack? We map that on a free AI audit.
For PE deal teams and corp dev: 10 Claude prompts that build a full sector overview from public filings, market size, players, margin pools, the shift incumbents miss
Path A · free
You just did it
The setup rail and every prompt above are free and stay free. The cost is your time, and the risk of wiring it wrong on live data.
• Run last quarter's numbers first. Live data is not a test bed.
• Nothing here uploads to us. It runs in your own Claude account, on your own machine.
• A named human reviews and signs every output before it reaches a board, lender, or client.
• Mask account numbers and names to the minimum the task needs.
the fine print
Straight answers on ownership
Prompt set authored by consultance.ai. McKinsey is referenced as the market-map engagement this replaces, no affiliation implied. The vault reads public filings only; your target list and deal data stay in your own Claude tenant and we never see it. Respect each data provider's terms. This is not investment advice; a named human signs every overview before it leaves the firm.
Want this running in your business, not just your laptop? We build it and hand you the keys.
Sector Overview Engine is a finance and data build in the consultance.ai AI Build Library. For PE deal teams and corp dev: 10 Claude prompts that build a full sector overview from public filings, market size, players, margin pools, the shift incumbents miss. Replaces the McKinsey market map engagement. It fits PE deal teams, GPs, corporate development, strategy leads, and CFOs who open every pitch, board deck, and diligence pack with a sector overview and want it built from public filings in a day, not billed as a McKinsey market-map engagement over weeks. Setup difficulty is Medium, with 4 plain-English steps.
What does Sector Overview Engine do?
For PE deal teams and corp dev: 10 Claude prompts that build a full sector overview from public filings, market size, players, margin pools, the shift incumbents miss. Replaces the McKinsey market map engagement.
Who is Sector Overview Engine for?
It fits PE deal teams, GPs, corporate development, strategy leads, and CFOs who open every pitch, board deck, and diligence pack with a sector overview and want it built from public filings in a day, not billed as a McKinsey market-map engagement over weeks.
How hard is Sector Overview Engine to set up?
Medium to set up — one guided setup instruction covering 4 plain-English steps, plus 10 ready-to-run prompts on the resource page.
How would consultance.ai build this out?
We wire the last 40 percent into production: a filing pipeline that pulls the right 10-Ks and S-1s automatically, connectors into Capital IQ or FactSet or EDGAR, a map that stays live as new filings land, access control on the target list, a retained source trail your IC will accept, and the 10 prompts loaded into your own Claude tenant. Done with you, then handed over so you own it.
What are the licensing terms?
Prompt set authored by consultance.ai. McKinsey is referenced as the market-map engagement this replaces, no affiliation implied. The vault reads public filings only; your target list and deal data stay in your own Claude tenant and we never see it. Respect each data provider's terms. This is not investment advice; a named human signs every overview before it leaves the firm.
Want this built into your workflow?
Sector Overview Engine is the starting point. On a free AI audit we map where it fits your stack and what consultance.ai would build around it.