Use AI for the edges of a weekly newsletter, not the body: transcription, proofreading, subject lines and reader-reply themes
A newsletter operator records a voice note, writes the issue by hand, and uses AI only for transcription, a light proofread, subject line options and a monthly analysis of reader replies.
Evidence: The author reports this. We have not checked it beyond reading the source.
The business problem
A newsletter written every week takes hours, but AI-written bodies tend to read generically and may cost opens.
What was tried
On Monday, record a 30 to 40 minute voice-note walk and transcribe it with Whisper into several thousand words. On Tuesday, write the draft by hand from the marked sections, then run a light AI proofread limited to errors. Ask AI for eight to ten subject line variations and pick one in about a minute. Send on Wednesday. Once a month, export reader replies and ask Claude for recurring themes and questions, which shapes most of the next month's topics, and have it scan the archive for older issues to resurface.
What was reported (mixed)
The author reports about 15,000 subscribers, a 65 to 72 percent open rate and an 8 to 12 percent click-through. AI-written subject lines won 14 of 19 sends over four months, while AI-drafted bodies with AI subject lines cut opens by about 6 points across three sends. Reply analysis takes about 5 minutes against an afternoon by hand.
Limitations
Self-reported figures from a consultant who promotes her services on the page. The page is internally inconsistent: it gives both 15,000 and 22,000 subscribers and describes the subject line process two ways. The author says the AI newsletter tools she tried lasted no more than eight weeks, that AI-suggested sponsors and cross-promotions were usually poor fits, and warns against AI list cleaning. The three-send body test is a very small sample.
What you need
An email platform with open and click reporting, a transcription tool, and an AI assistant. The reply analysis needs a few hundred replies to be useful.
Sources
- Lilach Bullock (marketing and AI consultant) ↗ Firsthand write-up, publication date unknown
Source published: unknown. Last reviewed here: October 12, 2026. Spot a mistake? Tell us.
Tools in this workflow
- Claude: Finds themes in reader replies and surfaces older issuesTry Claude
- Whisper: Transcribes the Monday voice noteTry Whisper
- Kit: Sends the issue and reports open and click ratesTry Kit
Related workflows
Keep your voice in AI-assisted writing: two profile files, a three-pass cleanup that cuts 30 to 50 percent, then rebuild the voice by hand
A former freelance writer describes a three-step process for writing client and personal content with AI: set up values and voice files once, strip invented and generic text in three passes, then rebuild it with his own stance and stories.
Rebuild a company website in about three weeks with Claude for planning and design and Claude Code for the build
A marketer used Claude to plan and design each page and Claude Code to build and update a hard-coded company site himself, alongside his regular job.
Rank an AI-assisted article for a competitive keyword: study page one, rewrite 80 percent of the draft, then have Claude check for stuffing
A writer explains how an article reached first place on Google for a competitive phrase: analysing page-one results, drafting with a long prompt, rewriting most of it by hand, and using Claude to catch keyword stuffing and errors.
Write articles in your own voice with Claude: dictate, outline, score with three custom skills, edit heavily, then repurpose
An online marketer describes her weekly article workflow: dictating thoughts into a Claude project, outlining, scoring the draft with three custom skills, heavily editing in her own CMS, and repurposing each piece into social posts.