← Back to all workflows
WF-02 · Content

Founder-led Content Engine

把创始人的想法变成持续输出的内容系统:一次输入(voice memo、会议、deck),多平台输出(LinkedIn、X、newsletter、blog)。不是模板填空,而是有 brand voice 的批量生产。

For
Solo founders, indie builders
Input
Voice memos, decks, customer calls
Output
LinkedIn / X / Newsletter / Blog drafts
Stack
Claude · Notion · Granola · Buffer

The bottleneck isn't writing.

Most founder content dies because capturing the raw thought takes more time than writing the post itself. A great LinkedIn opinion is a 30-second insight that needs 45 minutes to type up. The fix isn't a better prompt — it's removing the typing.

Three layers: capture → distill → publish.

Capture. Granola or Otter records every customer call. A 90-second voice memo on the morning walk goes into a Notion inbox. Slack rants get forwarded too. Anything that already happened becomes input.

Distill. A Claude project loaded with brand voice (10–20 prior posts as examples) takes the raw input and produces three outputs: a LinkedIn post, an X thread, and a newsletter section. The prompt is the same every time; the input is what changes.

Publish. Drafts land in a Notion content calendar. Founder spends 15 minutes on Monday picking what ships and tweaking voice. Buffer or Typefully schedules the queue.

Why this beats agency content.

Agencies write about you. This system writes from you — the angles, jokes, and pet peeves are already in your voice memos. The model is a transcriber-with-taste, not an author.

Realistic cadence.

3 LinkedIn posts, 2 X threads, 1 newsletter section per week — sustained for months — from roughly 90 minutes of founder time.


The full Claude project, voice prompt, and Notion calendar template ship in the weekly. Browse the other 5 workflows in the loop.