A $7K per Month AI App Portfolio Run Nights and Weekends With Claude Code
A full-time data scientist ships features solo with Claude Code across a three-app portfolio that peaked at $100K annual run rate and 2.5 million registered users, all built after work
Continue exploring this workflow
The Strategy
Ramsri Goutham Golla has not quit his day job as a data scientist, which makes this portfolio a genuinely part-time, nights-and-weekends operation rather than a full-time founder story. His three products, Questgen.ai (an AI quiz generator), Supermeme.ai (an AI meme generator), and AiArtist.io, span content-generation niches that are simple enough for a solo builder to ship quickly but have real, recurring demand from teachers, marketers, and casual creators. What makes this replicable rather than exceptional is his development process: he uses Claude Code to vibe code new features directly, letting the model handle a large share of the implementation work so a single person keeping a day job can still ship at a reasonable pace. Growth comes primarily through SEO and open-source launches rather than paid acquisition, keeping customer acquisition costs low across a portfolio of low-price, high-volume products. The pricing model, $10 to $50 a month subscriptions across the three products, combined with relatively cheap underlying LLM API costs for the actual generation tasks, produces margins in the 60 to 70 percent range after paying for the AI models doing the actual work. That margin profile is healthier than many AI-wrapper products that get squeezed by rising model costs. Questgen alone has generated more than $150,000 in lifetime revenue, and the combined portfolio has reached 2.5 million registered users, though current combined monthly revenue sits around $6,500 to $7,000, below the portfolio's peak of roughly $100,000 in annualized run rate reached at some point in 2025.
How It Works
Identify simple, high-frequency content-generation use cases with clear recurring demand: quizzes for educators, memes for marketers and casual users, AI art generation for creators.
Build and ship new features using Claude Code as the primary implementation tool, letting it handle a significant share of the actual coding work.
Keep the day job and treat the products as a nights-and-weekends operation, pacing feature development around available time rather than a full-time schedule.
Price products in the $10 to $50 a month range, low enough for individual buyers to self-serve without a sales process.
Grow primarily through SEO content and open-source project launches rather than paid advertising, keeping acquisition costs low.
Monitor margins carefully against underlying LLM API costs, aiming to keep 60 to 70 percent of revenue after paying for the AI generation work itself.
Track lifetime and monthly revenue per product separately to understand which parts of the portfolio are actually driving the numbers.
Results
Ramsri Goutham Golla reports current combined monthly revenue of roughly $6,500 to $7,000 across the three products, with a peak of around $100,000 in annualized run rate reached in 2025, over 2.5 million registered users across the portfolio, and more than $150,000 in lifetime revenue from Questgen alone. These are self-reported figures published on Indie Hackers and have not been independently verified.
Our Take
The part-time framing is what makes this worth including: this is not a story about quitting a job to build a startup, it is proof that a disciplined nights-and-weekends operator using Claude Code to accelerate implementation can build a real, multi-product portfolio without giving up salaried income. The margin discipline, keeping 60 to 70 percent after LLM costs, is also a more honest and useful detail than most portfolio stories that skip straight to top-line revenue. The dip from a $100K annualized peak down to a $7K per month run rate is worth noting rather than glossing over; portfolios of low-price content tools can decay as competition and platform algorithm changes shift traffic. Best suited for technically capable people who want to build a side portfolio without leaving their primary job.
Frequently Asked Questions
The practical questions a builder or operator is likely to ask before trying a strategy like this.
What does this saas AI coding workflow actually do?
This saas AI coding workflow is a real workflow where the agent takes on an operational job, not just a brainstorming task. A $7K per Month AI App Portfolio Run Nights and Weekends With Claude Code shows what that looks like in practice. A full-time data scientist ships features solo with Claude Code across a three-app portfolio that peaked at $100K annual run rate and 2.5 million registered users, all built after work The practical value comes from the agent handling repeatable business work with enough autonomy that a human only steps in after context has already been gathered.
Who should use a saas AI coding workflow like this?
This example is most relevant for saas operators. It is especially relevant for businesses where speed to lead, after-hours coverage, or consistent intake quality directly affects revenue. The category here is Dev Tools, which means the best fit is a team looking to turn a manual bottleneck into a repeatable system with a saas AI coding workflow.
Which tools are used in this saas AI coding workflow setup?
The source names Claude Code, OpenAI. That matters because one of the strongest signals in this directory is whether the operator shared the actual stack. Named tools make a saas AI coding workflow strategy far more useful than vague claims about “an AI system” doing the work.
How hard is it to implement a saas AI coding workflow like this?
Intermediate difficulty is the current read. The listing suggests a launch window of months. Startup cost is listed as under $50/mo. We were able to extract 7 concrete workflow steps from the source. We would treat a saas AI coding workflow like this as a workflow that needs real business context, testing, and exception handling rather than something you should copy blindly from one prompt.
What results can a saas AI coding workflow produce?
Ramsri Goutham Golla reports current combined monthly revenue of roughly $6,500 to $7,000 across the three products, with a peak of around $100,000 in annualized run rate reached in 2025, over 2.5 million registered users across the portfolio, and more than $150,000 in lifetime revenue from Questgen alone. These are self-reported figures published on Indie Hackers and have not been independently verified.
How credible is this saas AI coding workflow case study?
Right now the evidence comes from an Indie Hackers post. That is enough for us to study and curate the workflow, but not enough on its own to treat this saas AI coding workflow like an audited case study. We look for named tools, concrete results, and enough workflow detail to understand what was actually deployed, then we add our own editorial judgment on top.
Related Strategies
More AI agent strategies you might find useful
Learning to Code With AI and Building a $28K Per Month SaaS Portfolio
A non developer learned to code using AI tools and built a portfolio of SaaS pro…
How a $40K MRR SaaS Growth Playbook Uses Claude Code and Google Search
A SaaS playbook combining Claude Code for development and Google Search for dist…
Running a Company Entirely With AI Agents: What Worked and What Broke
Seven AI agents ran a company on a single VPS for a week. They pivoted the busin…
Pieter Levels Vibe-Coded a Flight Sim to $1M ARR in 17 Days Selling In-Game Ads
Pieter Levels built a browser multiplayer flying game almost entirely with AI co…
A $15K MRR SaaS Built in 12 Hours Using AI Coding Tools
A solo founder built a SaaS that hit $15K MRR with the entire MVP coded in a sin…
A Log Analysis SaaS Built in 30 Days That Hit $1,287 MRR With 41 Paying Customers
A developer tool that turns cluttered production logs into concise incident summ…
Want more strategies like this?
Get weekly AI agent case studies in your inbox.