An interview with a good subject is one of the most content-dense raw materials available. In forty-five minutes of conversation, a knowledgeable person will share insights, frameworks, experiences, and opinions that would take months to accumulate independently. The problem is that most interviews become one article, maybe a few social posts, and then the transcript sits in a folder never used again. AI repurposing changes the economics of this dramatically.
This guide walks through a systematic workflow for extracting twelve pieces of content from a single interview — the tools, the prompts, and the sequencing that makes it practical rather than just theoretically appealing.
Start With a Good Transcript
Everything downstream depends on the transcript quality. A clean, accurate, speaker-labelled transcript is the foundation that every subsequent piece builds on. Use Otter.ai for direct recording integration with Zoom or Meet, AssemblyAI or Whisper for audio files you upload, or a combination — transcribe in one tool and clean up obvious errors before doing anything else. The fifteen minutes spent reviewing and correcting the transcript before passing it to AI is worth more than any amount of prompt engineering on a noisy or inaccurate source.
Once you have a clean transcript, the first AI task is insight extraction — not summarisation. “Identify the ten most interesting, counterintuitive, quotable, or practically useful insights from this interview, and for each one quote the relevant passage from the transcript.” This step produces the content inventory you’ll draw on across every derivative piece. It also surfaces insights the interviewer may have glossed over during the conversation but that land powerfully when read in isolation.
📤 Twelve Content Pieces From One Interview
The Anchor Piece Comes First
The anchor piece is the full-length treatment — the article, Q&A, or narrative piece that presents the interview in its most complete form. Write this first, or use AI to generate a strong draft that you then edit into shape. The anchor piece serves two purposes: it’s the canonical version of the interview content that you can link to from every derivative, and it’s the source material that makes generating the derivatives faster and more consistent.
When AI generates derivative content, it produces better results working from the anchor piece than working directly from the raw transcript — the anchor piece has already been shaped into coherent narrative, the insights have been organised, and the language has been tightened. Derivatives adapted from a good anchor piece are typically closer to publication quality than derivatives generated directly from a raw transcript.
Generating the Derivatives Efficiently
The prompt structure for each derivative format follows the same pattern: give the AI the anchor piece (or the relevant section of the transcript), specify the format precisely, and include any platform-specific constraints. For a LinkedIn post: “Write a LinkedIn post based on the insight about [topic] from this article. 200–250 words, professional but conversational, ends with a question that invites comments. Don’t use bullet points.” For a short video script: “Write a 60-second spoken script on the insight that [quote or paraphrase]. First person, direct to camera, conversational register. Don’t use bullet points or headers — this should read naturally when spoken aloud.”
The key discipline is specificity — vague format instructions produce generic outputs that require significant editing. The more precisely you describe the format, the register, the length, and the platform, the closer the AI output is to something you can publish with light editing rather than heavy rewriting.
Platform Adaptation Matters
The same insight presented in the same way across LinkedIn, a newsletter, a short video, and a podcast episode will feel off on at least three of them. Each platform has different reader expectations, attention spans, and engagement patterns. A LinkedIn post that performs well leads with a strong hook and ends with a question. A newsletter piece can take longer to establish context. A video script needs to work as spoken language, not written language. Email has different conventions from social. AI is good at adapting for platform when instructed clearly, but it defaults to a generic format when not — always specify the platform in the prompt rather than assuming it will infer the right register.
⚡ The AI-Assisted Interview Repurposing Workflow
The interview repurposing workflow is also a quality filter. When you run the same content through multiple formats for multiple audiences, the insights that survive the translation — the observations that make a good LinkedIn post, a good video clip, a good newsletter section, and a good article section — are the genuinely strong ideas from the conversation. The ones that don’t adapt well to multiple formats often turn out to be less interesting or less universal than they seemed in the original conversation. The repurposing process surfaces the strongest material and lets the rest recede naturally.
Start with your last five interviews or recorded conversations. Transcribe whichever one hasn’t been fully repurposed yet. Run the insight extraction prompt. Write one derivative piece from the output. That single afternoon produces concrete evidence of whether the workflow delivers value on your specific content type — which is worth more than any framework for deciding whether to commit to it at scale.
Spacing the Distribution
One interview should not produce twelve pieces published in the same week. The goal is a month or more of sustainable content from a single production effort. A rough distribution: publish the anchor piece in week one. Space the social content across weeks one and two. Send the newsletter piece in week two or three. Release the video clips over weeks three and four. Use the FAQ or slide content as evergreen material that doesn’t need to be published on a specific timeline.
This spacing serves two purposes. It keeps your content calendar fed without requiring continuous production. And it maximises the reach of each piece — not every person in your audience sees every piece of content, so distributing the same interview insights across formats and platforms over several weeks reaches people that a single article or video never would have. The interview that felt like one content asset is actually a month of presence for the effort of one conversation.