← All workflows

Produce a researched post, audio version, and social graphics in one morning

The solo founder content machine

Perplexity finds the angle. Claude writes it. ElevenLabs reads it. Canva makes it look like you have a team.

5 min read

The bottleneck in solo founder content isn't ideas. It's execution time. A good blog post used to require: an hour of research, two hours of drafting, another hour of editing, time to commission or find images, and a separate recording session if you wanted audio. That's a half-day for one piece. Multiply it by a publishing cadence and it's not sustainable.

This workflow collapses that half-day into a morning. It doesn't remove the human judgment — you still choose the angle, still edit for voice, still decide what lands. But it eliminates the mechanical parts that slow everything down.


Step 1 — Find the real angle with Perplexity

Don't start with a blank doc. Start with a question. Open Perplexity and ask something you actually want to understand, not something that sounds good for SEO. The model synthesises sources and surfaces the parts worth writing about.

The output you're looking for: three or four concrete claims you can verify, plus a few source threads worth pulling on. Not an outline — an angle. What's the specific, honest thing you can say about this topic that most coverage misses?

PerplexityRESEARCH

The only way I search for anything now; it gives me the real sources so I can actually trust what I'm reading.

Step 2 — Draft with Claude, in your voice

Paste your Perplexity notes into Claude with a brief prompt: "Write a 900-word post on [topic] in a direct, non-promotional tone. The argument is [your angle]. Use the following research." Then edit it.

The edit is the work. Claude produces a solid first draft that you'd be embarrassed to publish without revision. That's intentional — it's a scaffold, not a finished piece. Read it once for structure, once for voice. Your edits take fifteen minutes. The draft you'd have written cold takes two hours.

ClaudeAI CHAT

The AI that actually thinks before it speaks — brilliant for long-form reasoning, writing, and analysis that holds up under scrutiny.

Step 3 — Audio with ElevenLabs

Paste the final text. Choose a voice that doesn't sound like a corporate announcement. Download the MP3. This takes four minutes, including the time it takes to listen back and confirm it doesn't have weird emphasis on the wrong syllables.

Upload it to your podcast host or embed it directly in the post. Not every reader becomes a listener, but the ones who do have a completely different relationship with your work.

ElevenLabsAUDIO

The moment you hear it speak, you stop thinking about AI — it just sounds like a person. Best-in-class voice generation for anyone who wants their words to actually land.

Step 4 — Graphics with Canva Magic Studio

You don't need original photos. You need a header image that doesn't look like a stock photo, a pull quote card for social, and maybe a simple diagram if the post has a conceptual structure. Canva's AI generation handles the first two in under five minutes. Describe the vibe, not the content. "Dark background, editorial, no people" is more useful than a literal description of the post topic.

Canva Magic StudioIMAGE GEN

Every design tool you have ever needed, now with AI woven through it sensibly. Accessible without being patronising — it meets you exactly where you are and asks nothing complicated.


What you've produced by noon

A researched, edited blog post in your actual voice. An audio version that extends the reach of that post. Two or three social assets ready to schedule. Total time spent: two to three hours, most of which was reading, editing, and thinking — not typing from scratch.

The point isn't that AI wrote your content. It's that the mechanical overhead no longer justifies the output rate. You can write more, publish more, and still spend the afternoon building the thing you're actually writing about.

← All workflowsBrowse all tools →