Grow a newsletter by starting in comments, moving fits into a DM sequence, and having Claude find patterns in the replies each week
A newsletter creator describes comment-first outreach that moves ideal readers into a short DM sequence, plus a weekly Claude analysis of comments, DMs and survey answers that feeds content ideas and offers.
Evidence: The author reports this. We have not checked it beyond reading the source.
The business problem
A solo creator with little time needs to find out what their audience struggles with and start real conversations, but reading every comment and DM by hand does not scale.
What was tried
Start conversations in the comments of relevant posts. If a commenter fits the ideal customer profile, move them into a DM sequence: a question about their struggle, a deeper question about their goal, then an invitation to book a call. Log each stage of the pipeline and review it for common objections. Each week, paste comments, DM threads and survey answers into Claude to find recurring struggles, the goals behind them and what stops people acting, and use the patterns for content ideas, DM openers, landing pages and offers. Keep context on voice, audience and offers in Claude, but write the final words, stories and jokes yourself.
What was reported (positive)
The creator reports growing from zero to almost 2,000 Substack subscribers in about eight months and credits consistency made possible by the workflow. No conversion, call-booking or revenue figures are given.
Limitations
An interview in a curated series, with self-reported results. The story does not separate the effect of the comment-first method from the AI analysis or other factors, and gives no conversion rates. The creator sells coaching and a growth programme, so the account favours his method. He says that before using AI, manual analysis did not scale and he lost insights.
What you need
An active audience on a platform with comments, a Claude account, and a place to log DM conversations. Time for daily comment and DM conversations.
Sources
- AI Workflow Stories on Substack (interview with William Leroux) ↗ Firsthand write-up, published July 16, 2026
Source published: July 16, 2026. Last reviewed here: October 14, 2026. Spot a mistake? Tell us.
Tools in this workflow
- Claude: Finds recurring struggles in comments, DMs and survey answers each weekTry Claude
Related workflows
Install an open-source library of 200+ go-to-market skills for Claude Code covering SEO, outreach, ads research and competitor tracking
A maintained repository packages go-to-market tasks as skill files for coding agents, including SEO research, lead finding and enrichment, outreach drafting, content, competitor tracking and social monitoring.
Run four OpenClaw agents for content, leads and ops on Gemini's free tier, with a quality gate and a hard cap on requests
A solo developer in Taiwan describes four OpenClaw agents on a home machine that draft social posts, reply to comments, research, scan for leads and monitor endpoints, using Gemini's free tier at about 105 of 1,500 daily requests.
Draft a training course outline with Claude Projects: your own voice documents, 16 design questions, then edit every step
A learning and development professional loads her voice, expertise and story documents into a Claude Project, gives it her outline structure and about 16 design questions, and edits the draft outline and workbook text it returns.
Run a small SaaS feedback loop with Claude: a weekly PostHog survey digest, weekly release summaries and browser-based product testing
A course-creation software company asks new free users to rate their first result, has a scheduled Claude job turn the answers into a weekly issue list, has Claude summarise each week's releases for the team, and has Claude test the product in a browser like a new customer.