It is Tuesday, 11pm, and the investor has four windows open at once. The pitch deck says monthly churn is 1.8%. The spreadsheet from the data room puts the September 2024 cohort closer to 3.1%. And 37 minutes into a reference call, a former customer's ops lead admits their team basically stopped using the product halfway through last year. Three answers to the same question, and he is copying all of them into one cell of a Notion table by hand. Forty-one cells to go.
He is a Series A investor with two weeks until the investment committee, and 40 pitch-deck slides, 130 data-room documents, 6 reference-call transcripts and 3 market reports to get through before then. This case shows how he gets through it. Everything goes into one Consilience workspace, and instead of building that comparison table cell by cell, he asks for it and gets it back, with every claim, number and quote linked to the document it came from. This is a hypothetical scenario, not a real customer story.
The material: pitch deck, data room, and interviews
The material is all there. The claims sit in the pitch deck, the numbers that back them up or knock them down sit in data-room files, and the remarks that cut against the numbers sit somewhere in the middle of a call transcript. All that's left is going back and forth between the three, finding the same item in each, and lining them up.
- 40 pitch-deck slides — 6 metrics slides, 3 on market size, 2 on the competitive landscape. The rest is team and vision.
- 130 data-room documents — monthly revenue sheets, a cohort retention spreadsheet, 14 supply contracts with major customers, 9 sets of board minutes, a draft reps-and-warranties schedule.
- 6 reference-call transcripts — 3 current customers, 2 churned customers, 1 former employee. 40 to 60 minutes each; roughly 8,000 words apiece once written out.
- 3 market reports — 2 paid research PDFs, 1 public industry report.
- The investor's own notes — 3 meetings, 2 to 3 pages each.
How it works today
He pages through the deck, pulls out every claim worth checking, and builds a table. To fill the "evidence" column, he opens the data room. He hunts for the cohort sheet among 130 files with names like "v3_final_revised.xlsx," opens it, checks the number, copies it into the table, and writes which file and which tab it came from into the cell next door. Every single claim costs one round trip.
The transcripts don't turn up in search at all. He remembers someone saying something important on a call, but not where inside 6 files × 50 minutes. Hit Ctrl+F for "churn" in the transcripts and nothing comes back, because the founder's word for it isn't the customer's word for it.
Ten of the fourteen days go to copying evidence over next to claims. The judgment gets squeezed into the last three.
How the material goes in
Kick off extraction and go to bed. While the 130 documents come in, the only work left for a human is registering the vocabulary.
Throw all three folders in whole
Open "Extract sources" (
⌘⇧I/ Ctrl+Shift+I) from the sidebar and drag in thedeck/,dataroom/, andcalls/folders. Progress runs as five stages, from "Reading your files" to "Organizing into themes". All 130 originals stay on disk, and no file is modified.Paid reports go in as links
On the same screen, use "Add manually" → "Add URL" for the 3 market reports. When more material lands in the data room a few days later and sits there untouched, the Activity center raises an "Build this workspace's knowledge graph?" card.
Teach it the VC vocabulary
Open the graph with the titlebar's "Open knowledge graph" button and pick "Domain vocabulary" in the left rail. The panel's header reads "Teach the AI your field". Register this deal's language here: churn, logo churn, net revenue retention, cohort, change-of-control clause. This is also where you say that the founder's "churning" and the customer's "stopped using it" point at the same thing.
Read it all again
Press "Re-extract everything". Read a second time with the vocabulary in hand, and the transcript's "basically stopped using it" — the line Ctrl+F never caught — attaches to churn.
Wrap it in a case
After the first conversation, right-click that chat in the sidebar and choose "Pin as case…". In the driving question field ("What is this case about?"), type: does the data room and the calls support this company's churn claim?
How you ask
"put the founder's churn claims next to the data-room numbers"
→ A 3-row table.
Row 1: deck claim "1.8% monthly churn" — source "Pitch deck · slide 12"
Row 2: cohort sheet, 2024-09 cohort at 3.1% — source "cohort_retention.xlsx · tab 2"
Row 3: call quote "basically stopped using it in the back half"
— source "Reference call 4 · line 412"
"any customer named on a reference call that isn't in the revenue sheets?"
→ Two. Click the note link on a row and the original opens.
One: mentioned on a call as "contract ended last year", no row in the sheets.
One: the call and the sheet spell it differently, so it landed as two entities.
You decide whether to merge them under "Also known as" on the entity page.
"@churn pull together what people said about it"
→ The "In your words" section on the entity page.
4 verbatim sentences: 2 from the founder, 2 from churned customers.
Each one carries who said it and the source note and line.These answers exist because the "Extract sources" step tied 130 documents and 6 transcripts into one knowledge graph (a map that connects concepts as points and lines). A single point — churn — has the deck's claim, the cohort sheet's number, and the call's quote each attached to it by a line. A row in the table is one of those lines, unfolded.
The numbers in the table trace back to the source text. Hover a connection chip on the entity page and the sentence that states the fact is quoted, captioned "{note} · line {n}". Click it and the sheet opens at the spot where 3.1% came from.
What changes
| Before | Now |
|---|---|
| To check one deck claim, hunt for the right sheet by filename across 130 data-room files | Mention "@churn" and the data-room numbers attached to that claim come along, with the source sentence quoted |
| Ctrl+F through 6 transcripts × 50 minutes. If your search term isn't the speaker's word, nothing comes back | Working from the vocabulary you registered in "Teach the AI your field", the founder's "churning" and the customer's "stopped using it" attach to the same point |
| Copy claims, evidence, and contradictions into a Notion table by hand, and write the source into the cell next door | One line of question comes back as a table, with a "{note} · line {n}" link already on every row |
| A week later, material gets added to the data room and you re-skim to find what moved | Reopen the case and the new-evidence strip tells you which pinned entities picked up evidence |
What's left is the judgment. Whether to work from the deck's 1.8% or the cohort's 3.1%, and how much weight the call's contradiction carries, is the investor's call. What this workflow takes off his plate ends at finding the relevant passage in all three sources and gathering them into one table.
Try this workflow with your documents
Learn the steps behind this workflow, then try them with your own sources.
Open the lesson ↗