Run a tiny paid app with Claude drafting support replies, changelogs and a weekly usage digest
A founder with about four focused hours a week has Claude draft feedback replies, a changelog line and a post each week for $2 a month. The product has 3 paying users and $4 MRR.
Evidence: The author reports this. We have not checked it beyond reading the source.
The business problem
A part-time solo founder with a day job and a child cannot keep up with support, changelog and marketing writing for a small paid product.
What was tried
Each week the founder pastes user feedback into Claude through the API. Claude acts as support agent, changelog writer and social media manager: it drafts replies to feedback, writes a two-sentence changelog entry and one build-in-public post. It also writes a plain-English digest of user behaviour, first drafts of emails, and suggested feature priorities drawn from support threads. The founder edits the drafts and sends them.
What was reported (mixed)
The author says first drafts were about 80 percent usable, take about 12 minutes to edit, and save roughly two hours a week of context switching. AI cost about $2 a month against 13 users, 3 paying and $4 MRR after three months. He calls the project technically profitable.
Limitations
Self-reported, with no screenshots or code. The scale is very small, and the author says plainly that Claude cannot create word of mouth or decide what the product should become. The author sells the product the post links to, so the post is also promotion. The post date shows no year.
What you need
An Anthropic API key and a way to paste in feedback; the source names no other tools.
Sources
- DEV Community (subprime2010) ↗ Firsthand write-up, publication date unknown
Source published: unknown. Last reviewed here: October 16, 2026. Spot a mistake? Tell us.
Tools in this workflow
- Claude API: Drafts replies, changelog, posts and digestTry Claude API
Related workflows
Run AI VPs of marketing and customer success on Replit for about $254 a month, with 3 to 5 hours of weekly upkeep
SaaStr describes two in-house AI agents that run a Monday marketing standup and manage 100+ conference sponsors, with the invoice costs and the human maintenance time it admits they still need.
Build a website-derived support knowledge base with Firecrawl and Gemini, then use it to answer Gmail inquiries in n8n
An n8n tutorial maps and scrapes a business website, has Gemini organise the content into a Google Doc, and connects that knowledge base to a Gmail agent. The example is a lawn-care business, with reusable support mechanics.
Save AI-written customer replies in Gmail Drafts, flag missing facts and notify Slack before a person sends
An n8n builder shares a Gmail reply workflow that filters automated senders and leaves sending to a person. The linked JSON adds business context, missing-fact placeholders, draft checks and Slack notifications.
Brief your team on every Stripe cancellation with an AI agent that checks support tickets and account history
A Tines example workflow fires on a Stripe cancellation, lets an AI agent look up the customer's support tickets and account history, and posts a structured churn brief to Slack.