Seventeen Transcripts. One Deadline. The Writer's Playbook.

You have a book due. Or a long feature. Or a chapter. It doesn't matter. The specifics change. The shape of the problem does not.

On your desk or in your Dropbox you have:

• Seventeen interview transcripts — some clean, some machine-generated and messy, some you typed yourself at 2 a.m. two summers ago.
• A stack of handwritten notebooks with shorthand you can mostly read.
• A folder of PDFs — journal articles, book chapters, a government report nobody has opened since the Obama administration.
• A spreadsheet you made when you thought you were going to be organized about this project.
• A Google Doc titled "Notes" that has 87 pages and no structure.
• An email from your editor that ends, gently, with "any thoughts on timeline?"

The deadline is Friday. It is now Wednesday. You have not started.

This is not a productivity problem. This is a sorting problem. The material is all there. It is sitting in so many shapes in so many places that the first draft feels impossible not because you can't write — you can — but because you can't hold it all in your head at once. So you open a blank document, stare at the cursor, make another coffee, and refresh Twitter.

Here is what actually works.

The move: turn the whole raw pile into one searchable brain

You do not need to write more. You need to see your material. All of it. In one place. Cross-referenced. With the ability to ask questions of it.

Upload everything — every transcript, every PDF, every rough note, every email exchange, every prior draft — into a single collection. Then stop reading and start asking. The themes, the quotes, the connections, the contradictions — they're all in there. Your job is to surface them, then make the judgment calls only you can make.

The playbook

Wednesday afternoon: load the brain

Open CorpGPT. In My Documents, create a collection for the project: "[Project Name] — Source Material." Drop in:

• All interview transcripts — cleaned or raw, both work.
• Every PDF — journal articles, reports, book chapters, archival scans (even image PDFs; the OCR handles it).
• Your rough notebook transcriptions — typed-up shorthand, bullet points, voice memos turned to text.
• Prior drafts and outlines — yours, not the final-draft-caliber writing, but the thinking-out-loud documents you've already produced.
• Background research — the Wikipedia rabbit holes you screenshot-saved, the Substack posts you bookmarked, the email threads with the subject expert.
• The editorial brief, proposal, or outline — whatever the contractual shape of the project is.

For interviews you haven't yet transcribed — drop the recording's audio file (MP3, M4A…, up to 50 MB; video isn't accepted) into the Sources pane (or use Record audio, your device's microphone, for the next in-person one) and turn the recording into a transcript with speaker labels in its Transcript tab. (With consent from the interviewees.)

Now every word of raw material you've produced on this project is in one place and searchable.

Wednesday evening: let the material describe itself

Before you write a sentence. Tick the collection in My Workspace and open the Make pane ("Make from these sources"), with Chat beside it. Ask for:

• A summary of each interview (Make → Summary) — so you can remember what each interview covered without re-reading all seventeen.
• A cross-interview theme map (Make → Mind map) — the themes that recur across the transcripts.
• A pulled-quotes sheet (ask Chat) — strong lines on each theme, grouped by theme, with the transcripts they came from in the source list under the answer. Chat reads the text without speaker labels, so check who said each line in that transcript's Transcript tab.
• A "contradictions and tensions" document (ask Chat) — where the interviews disagree, or where the official record conflicts with the primary sources. This is usually where the story lives.
• A proposed outline (ask Chat to draft it) — for the chapter, article, or book, built from the themes, with suggested quote placements.

An answer Chat draws from your transcripts names the transcripts it came from, and everything you make lists the transcripts it was built from, so you can check each line. Most Make formats read about ten passages that best match (a slide deck reads more), so the theme map is a first map, not a census of all seventeen. This is your raw material described, not written for you.

Print the theme map. Sit with it. Cross things out. Scribble in the margins. The act of reviewing the machine-generated map is itself the thinking — because now you're reacting to something instead of staring at a blank page.

Thursday morning: interrogate the material

Open Chat. Ask the questions a good editor would ask you:

• "Which interviews talk about [the central tension of the project], and what do they say?"
• "Which interview is the most specific about [specific scene or fact]?"
• "Where does [person / place / date] come up?"
• "Which interviews contradict each other, and on what points?"
• "What's the earliest and latest date mentioned in the source material?"
• "Pull anecdotes that involve [theme]."
• "Which interview has the strongest lines on [topic] — most quotable, most specific?"

An answer drawn from your transcripts names the transcripts it came from. Chat reads the transcript text without speaker labels, so it can't tell you who said a line — check that in the transcript's Transcript tab. It also reads the passages that best match each question, so when you need every mention, ask one transcript at a time. You're not hunting through a 47-page transcript to find the quote you half-remember. You're asking a question and getting an answer with its sources listed underneath.

This is the part where a week of work becomes an afternoon. Not because the writing is faster. Because the hunting is over.

Thursday afternoon: draft the chapter

Now you write. But you're writing with the material visible. Not from memory. Not from a blank document. You have:

• The theme map taped to the wall.
• The pulled-quotes sheet open in a second window.
• Chat open in a third, so when you need to check "did anyone actually say that about August of '09?" you can ask and open the transcript it names.
• Your outline in front of you.

You write the way writers have always written — sentence by sentence, voice on — but without the tax of holding seventeen transcripts in your head.

The draft comes out. It's 70% of the way there. Your voice. Your structure. Your judgment. But the raw material is doing the work it should have been doing from the start.

Friday morning: fact-check and pressure-test

Before you send to the editor, add the draft as a source and make one more pass through Chat:

• "Which transcript has a line close to this quote: '[quote]'?" — one quote at a time.
• "Are there any claims in this draft that aren't supported by the source material?"
• "What's the strongest counterpoint to the central argument? Is it represented fairly?"
• "Did I leave out any interviewee whose contribution was significant?"

Fix what comes up, and check each quote word for word against the transcript yourself — and who said it, in its Transcript tab. Now the draft goes out with a clean conscience.

Then: send it

You meet the deadline. Your editor opens the doc, reads it, and sends you an email that is longer than three words. That alone is a professional miracle. You go outside. It's still light.

Beyond the one chapter

Build a career-long writer's brain

The collection doesn't get deleted when the project ships. Next project, new collection — but the searchable archive of your interviews, your sources, your past drafts becomes a compounding asset. Six years from now when a new editor asks "didn't you interview someone about this back in 2025?", ask Chat — describe who you're looking for and Chat searches for the passages that best match and names the interview they're in.

Use My Courses to learn the subject a module at a time

You're writing about fiscal policy and you were a poetry major. My Courses turns the five densest PDFs in your research folder into a structured course — each module eight steps, from a summary to a quiz, built from those documents — to read and quiz yourself on before you write. The questions you can't ask the subject expert for fear of looking stupid — you ask Chat, at 11 p.m., in your sweatpants.

Let Chat and the Make pane handle the ancillary content

Once the chapter is written, the same collection produces — Chat drafts most of it from your files:

• The pitch letter for the feature version.
• The acknowledgments section (check it against your own list of the interviewees who appear).
• The fact-check memo for the publisher's attorney.
• The book-club discussion questions (or an FAQ from the Make pane).
• The Twitter thread when the piece goes live.
• The email to the interviewees with the quote you used, so they're not surprised.

Material you've already produced, shaped into the formats the world needs next. Not written for you. Drawn from what you already have.

Transcribe every interview going forward

For an in-person interview, Record audio becomes your default — it records your device's microphone, up to 50 MB (roughly 50 minutes). For a call or a longer session, upload the recording's audio file (MP3, M4A…, up to 50 MB). You focus on the conversation. The transcript lands in My Documents, with speaker labels in its Transcript tab. You never again hear yourself say "I'll transcribe it later."

The features doing the work

Make pane — per-interview summaries, cross-source theme maps (Mind map), FAQs, study guides. Each lists the sources it was built from.

Chat across everything — cited answers to cross-interview questions. The "where did X come up?" problem, made shorter. Describe the quote, the scene, the anecdote by intent, not keyword — "the part about her father" works — and Chat searches for the passages that best match and names the transcript they're in.

Record audio and audio uploads — interview transcription, with consent: record in-person interviews with your device's microphone (up to 50 MB, roughly 50 minutes), and upload the audio file for calls and longer sessions. Speaker labels show in each Transcript tab. Straight into your working brain.

My Courses — structured crash courses on your own research library: eight steps for each module, from a summary to a quiz. The subject-matter ramp you used to get by drinking coffee with a professor.

Why this actually works

Three forces are quietly doing the work here.

First, long-form nonfiction is a retrieval problem disguised as a writing problem. You have the material. You're not stuck on the sentence — you're stuck on not being able to find the three lines across seventeen transcripts that belong next to each other. The search-and-citation layer is exactly the tool the form has been missing since the tape recorder.

Second, blank-page paralysis breaks when the page is not blank. A machine-generated theme map and a pulled-quotes sheet are not writing — but they are something on the page that you can react to. Reacting is easier than generating. You start editing the theme map, then you start writing around the quotes, and at some point you're just writing. The trick is starting.

Third, citation discipline protects you. Quotes and claims can be traced back to the tape, because the transcripts are named as sources — check each one there. That's not just good craft — it's what keeps you safe when the subject calls, when the editor asks "where did this come from?", when the fact-checker has twenty questions, when a lawyer gets involved. The receipts were always the right answer. Now they're one click away.

What this can't do

Be honest.

CorpGPT does not write the chapter in your voice. It does not know which quote is the best quote, only which quotes exist and what they're about. It does not have taste, structure instincts, or ear for a good sentence. It does not feel the story. It does not know when a digression is load-bearing and when it's indulgent. It does not love the subject. All of that is still the writer.

It is, flatly, a very good research assistant. That's the job. The craft is still yours.

And: always disclose AI-assisted research tooling to your editor, your publisher, and where relevant, your interviewees. Transparency is cheap. Surprise is expensive.

The bottom line

Seventeen interview transcripts. One deadline. And you haven't started.

Drop them in. Get summaries, themes, pulled quotes, tagged to the source. Write the chapter. Hit the deadline.

Your editor will almost certainly not say thank you. But they will read the draft. Twice. And then they'll ask about the next one. That's as close to thank you as this job gets.

Open CorpGPT. Upload the pile. Write the chapter.

---

Keep reading

• Brand Says Bold. Legal Says Careful. — how marketing managers draft campaigns and prepare them for brand and legal review.
• How Are You Different From [Competitor]? — how sales reps prepare cited battlecard answers before the call.
• Prep the Hiring-Manager Intake — how recruiters turn the JD and scorecard into a reading checklist and prep the intake.
• Answer Once. Help Forever. — how HR managers answer handbook questions with cited answers.
• Another Meeting to Recap the Last Meeting — how PMs ship meeting recaps.
• Client Deck Tomorrow. It's 8 PM. — how consultants synthesize four reports into a draft deck.
• It's 9 PM and You're Not a Lawyer — how small business owners review vendor contracts.
• Ten Minutes Between Sessions — how therapists study their training material and CE and draft psychoeducation handouts, with client information kept out.
• Beat the Binder: The Nurse's 12-Hour Shift Playbook — how nurses study unit policies with cited answers.
• Eighty Pages of Policy. Find the Clause. — how insurance agents find a clause in a long policy form and read what it says.
• Two Minutes Before the Client Call — how financial advisors prepare for client calls from the fund documents they uploaded.
• Tax Code Changed. Again. — how accountants translate new tax rules.
• 200-Page Contract at 4:45 on a Friday — how lawyers find the clauses that matter in a weekend ambush.
• Doctors: Study Your Guidelines, Draft the Admin — how physicians study the guidelines they uploaded and draft the non-patient admin, away from patient care; answers name the source document, and the page, slide or section when CorpGPT can place it.
• Find the Guideline Behind 'Will I Qualify?' — how mortgage brokers find the guideline section behind a client's question and read it; the lender makes the call.
• Turn One Chapter Into a Week of Lessons — how teachers build a full week of materials from one chapter.
• Your Client Wants 30 Listings by Saturday — how real estate agents review 30 disclosure PDFs.
• Cram 400 Pages Before Morning — the student version of the same playbook.
• Ninety-Minute Interview. Show Notes by Tuesday. — how indie podcasters draft the post-production package from one episode's transcript.
• Sixty Videos In. Did I Already Post This? — how content creators turn their back catalog into a searchable content brain.
• Sixty Papers. One Lit Review. One Weekend. — how researchers turn a stack of PDFs into summaries, themes, citations, and gaps.
• Three Investor Meetings. Three Different Decks. — how founders tailor a pitch per investor.
• 47-Page Brief. Proposal Due Friday. — how freelancers turn dense briefs into a first proposal draft.
• Your Kid Just Asked About Algebra. — how parents help with homework using the actual textbook.
• Medicare Sent a Letter. 12 Pages. Tiny Font. — how older adults turn any letter into a plain-English one-pager.
• See all use cases — writers, marketers, sales reps, recruiters, HR, PMs, consultants, small business owners, therapists, nurses, doctors, insurance agents, advisors, accountants, lawyers, brokers, agents, teachers, students, and more.
• Plans & pricing — a free Trial to start, no credit card required.