1. Built with
  2. /
  3. Claude
Sign in
Claude
Built with

Claude

  • JA
    Jordan Ayala@jordan7448
    Post·2w ago

    The most useful thing AI helped me do this month was accelerate debugging on a tricky real-time streaming pipeline. We were building live event processing for video interactions at Saywise, and there was a latency spike we couldn't immediately trace. I fed the logs and architecture into Claude, walked through the reasoning together, and within minutes had three hypotheses I hadn't considered—one of them turned out to be the culprit: a subtle ordering issue in our Kafka consumer group.

    What struck me wasn't that Claude solved it alone. It didn't. But it compressed the time between "something's wrong" and "here's what to check" from hours of rubber-ducking to maybe twenty minutes of focused conversation. I also ran some quick exploratory queries with ChatGPT for syntax validation and used Cursor for inline code suggestions as we tested fixes. For someone who's spent a decade building systems, that's the real win—not replacement, but thinking partners that are always available and never tired of the same problem.

  • SS
    Shaun Seo@shaun
    Article·2w ago
    Automating Code and Doc Reviews with Claude Routines

    At Saywise, we ship fast. That's a feature, not a bug—but it comes with a real cost: documentation drifts, edge cases slip through, and by the time you realize a README is stale, three more things have changed. We were running into two specific problems. First, our core docs—CLAUDE.md, AGENTS.md, README.md—were constantly out of sync with what we'd actually built. With the pace of iteration we were moving at, keeping them current felt like a losing game. Second, even with solid PR review practices, we wanted an extra safety net: a systematic way to catch issues in code that had already merged, especially patterns we might miss in the moment. We decided to automate both with Claude Routines. The setup was straightforward in concept but required real iteration on the prompt itself. We configured a routine to run every 24 hours, early in the morning, that would: Pull all PRs merged in the last day. Run a fresh code review on them, looking for logic issues, edge cases, and potential bugs we might have missed in the moment. Audit our key documentation files against the current codebase and flag anything that looked stale or inaccurate. Create PRs for any fixes or updates it found. Post a summary to our engineering Slack channel so the team could see what it caught and what it changed. The prompt tuning was the real work. We had to be specific about what "stale" meant, what kinds of issues we actually cared about flagging, and how aggressive we wanted the routine to be. Too strict and it became noise; too loose and it missed the point. After a few iterations, we landed on something that felt right. The impact has been real. Our docs stay current without anyone having to manually track them. We catch subtle bugs and inconsistencies that slip past human review in the moment. And the Slack summaries give the team visibility into what's happening—it's become a useful daily checkpoint, not just a bot running in the background. It's not a replacement for careful code review or thoughtful documentation. But as a daily layer of protection and maintenance, it's been exactly what we needed at our pace.

  • KL
    Ken Lee@ken
    Post·2w ago

    My wife's wine collection—150 to 200 bottles spread across four fridges—had outgrown Trello. It was buggy, clunky, not designed for this kind of inventory. So I sat down with Claude Code and built Vinlo, a wine stock management app tailored to exactly what she needed.

    No bloat. No guessing. Just a clean interface to track bottles, locations, notes, and what's ready to drink. The speed was remarkable—Claude Code let me move fast without wrestling infrastructure or boilerplate. I could think about the problem and build the solution. No friction between idea and working software.

    That's what excites me about AI tooling now. It collapses the distance between "I have a problem" and "here's a working app." The best part? She's actually using it. No more Trello frustration, no spreadsheet chaos. Just a tool that fits.