Run an autonomous loop that builds SEO pages and tools
An agent loop reading a revenue dashboard ran 365 cycles, generating 394 interlinked SEO pages and a webhook inspection tool with landing page, docs and drafted outreach.
Done with a custom-built or unnamed agent
- What they did
- The agent was told to make real money and ran every 20 minutes. Each cycle it read a dashboard of revenue, products and decisions, and it read a tenet file of rules it could not edit. It then picked an action, built or shipped something, and appended its reasoning to a decision log. Over 365 cycles it produced the SEO pages and the webhook tool.
- How it went
- Revenue was $3, from one coffee purchase prompted by a story about the project rather than by the tools. The 394 pages earned nothing, and distribution stayed unsolved. The agent then pivoted on its own to build-in-public writing.
- Worth knowing
- The tenets, including never spending money without approval and preferring one thing done well, kept the agent in check, and it had no budget or audience to draw users.
Try it yourself with Claude Code
Help me build a small [type of tool, e.g. webhook inspector] with a landing page and docs, plus a set of [number] interlinked SEO pages around [topic] in [folder or repo]. Work in short cycles: generate pages, check links and quality, then improve. Stop after [number] pages and a summary of what you made, and show me any outreach drafts instead of sending them, and ask before deploying anything.
Source: dev.to · Undated
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- Custom agent
Sell services through an agent that takes payment and delivers
An agent runs a transaction flow, creates Stripe checkout links, verifies payment before delivering a service, and asks the owner on Telegram to approve refunds or disputes.
Answer sales reps' questions with a Slackbot agent
A RevOps practitioner built a Zapier Agent Slackbot to answer reps' questions; it took an afternoon to work and he concluded agents are imperfect.
Resolve customer calls proactively with AI agents
TELUS uses Gemini Enterprise for CX agents to proactively resolve customer calls; Google's case study reports 30% of calls resolved and issues resolved 87% faster.
Flag churn and expansion signals and draft support replies
Healthie's Zapier agent checks CRM and support tools weekly for churn or expansion signals and posts a summary in Slack; Erewhon drafts personalized support replies.
- Custom agent
Answer tenant and rental prospect questions with AI
A commenter says AI tools handle most tenant questions, prospect inquiries and document preparation, handing harder cases to a human.
Find stale commercial listings and email brokers
A Hermes bot scrapes lease listings, filters by days on market and zoning, calculates commissions and emails brokers.