I’ve built a couple of AI systems like AI customer service agents and AI document processors, but now I’m at the “how do we get this in front of the right clients?” stage 😅 For those of you selling AI builds, what’s actually worked after you finished a build? Do you make content about your builds to get inbound leads? If so, does making content also play a huge role in getting you inbound leads? I’m curious whether that brings real enquiries or mostly views from other builders. Would love to hear what worked for you and what you’d skip if you were starting again.🙏

When a workflow with reads, drafts, sends, payments, and deletions enters a real workflow, who owns the stop button? The human owner checks the evidence before the consequential step; an uncertain result stops the run. The deliverable is an authority matrix separating reads, drafts, sends, payments, and deletion. I would make human ownership visible beside it. For a workflow with reads, drafts, sends, payments, and deletions, I would assign authority by action class instead of using one broad approved flag. In a small Muse pilot, I would test personal-agent preparation with explicit approval before consequential actions and ask a second operator to check human ownership. Which part of human ownership would you verify first?

Hey everyone! 👋 I’m building an AI startup called Pip, an AI accountability buddy that lives in your text messages. It helps you stay consistent with your goals, follow through on commitments, and actually get things done. You can tell Pip what you want to accomplish, set your own accountability rules, and choose what happens if you don’t follow through — whether that means notifying a friend or putting money on the line. Think of it as a friend who keeps you accountable and makes sure you follow through on what you said you’d do. We’re offering a free trial, and I’d love for you to try it out, explore the product, and share your feedback! It would mean a lot as we continue building and improving Pip. Try it here: https://www.textpip.com/go/ashrit Would love to hear what you think! 🙏🚀

A startup just deleted more than 800,000 lines of unit tests. On purpose. The founder of an AI observability startup argues that now that coding agents write so much of the code, unit tests can do more harm than good: → They lock in bad AI-generated code → They create "busy work" for agents → They slow down CI pipelines → They drive up token bills A Coinbase engineer agreed: lean on full end-to-end, integration, and golden tests instead. Not everyone is convinced. Veteran engineer Bob Martin ("Uncle Bob") says he still relies on unit tests to keep his agents honest. Here's how I see it: Unit tests written by agents, for code written by agents, can turn into the AI grading its own homework. But tests that capture real business rules are the guardrails that stop an agent from "fixing" your code into the wrong shape. So maybe the question isn't "delete or keep?" It's "which tests protect behavior, and which only protect implementation details?" Where do you stand? A) Delete most of them and test behavior end-to-end B) Keep them, because they're the agent's guardrails

How would you define the frontend/backend development principles when using Claude/Claude Code? The goal is to establish a reliable foundation for a purely AI-based web development project. The key distinction is that Claude should not act as a "freestyle coding programmer," but rather as a developer operating strictly within a predefined architecture. To achieve this, the project must be built around a framework of rules from day one. What would you include in this rule system?