Ashley Colletti

When a dev leads with “clean architecture,” I pause. If they push for the perfect setup before writing a single feature, I ask why? It’s not that quality doesn’t matter. It’s that context does. Perfect code doesn’t help if no one needs what you built.

7

4 Comments

I've been quiet on LinkedIn while we reimagined how Squidler works. Here's what we realized: Your coding agent knows what you wanted to build. It has the full code and context for every feature you prompted and every user story you described. But it not great att verifying, especially not at runtime. It's not design to run your app, or reason around it, as a user would. Cursor, Lovable, Claude Code, Replit and the rest, have made the Build phase magical. The amazing teams behind these products have pushed Building further and faster than I ever expected. But Building and Verifying are different jobs. This is why we redesign the navigation and interface of Squidler to close the loop between the two. Now, your coding agent can use our MCP integration to describe user goals, based on what it implemented, in the same language your agent already thinks in. Squidler then executes them, as a user in a browser, and answers three core questions: * Does it work? i.e. can users actually achieve their goals? * Is it broken? i.e. does it pass our rule based runtime validation? * Is it easy? i.e. was is intuitive or hard to achieve the goals? Goal-driven. Runtime-verified. Your agent knows what you wanted, and with Squidler you can now check that you got it. Check the comments for demo and a link to try it.

63

18 Comments

I’ve worked with enough developer teams to see a clear pattern. The best developers aren’t just great at writing code. They’re great at solving problems. Now, with AI copilots, problem-solving is accelerating. Bugs don’t sit in backlogs for days, they get flagged and fixed in minutes Smart suggestions make code tighter, cleaner, and more secure Delivery timelines shrink, without lowering quality This doesn’t diminish the role of the developer. It elevates it. The companies that embrace AI copilots won’t just ship faster. They’ll set a higher standard for what “good” looks like in software. The baseline of productivity in development is being rewritten, and it’s rising. #AI #CEOThought

1

1 Comment

You don't need to hire a software farm for anything anymore. You need one developer who sits next to you for 6 weeks and learns how your business runs. Not how it looks in a deck. How it actually runs. The messy inbox system. The Notion doc nobody follows. The 4-step process your EA does manually every morning. A good AI developer, someone who works in n8n, Claude, and modern automation tools, turns that into systems that run without you. We placed one with a 12-person e-commerce brand. In 8 weeks he'd automated their order exception workflow, their influencer outreach follow-up, and their weekly reporting. The admin team is being trained in AI. Those that don’t adopt are gone. 3 tasks. Each one was eating 6-8 hours a week from someone on the team. That’s money in your pocket. 416h per year. That’s almost a full quarter's worth of work. A dev shop's savings don't matter if they can't ship. Ours do. I wrote more on this on more detail in the blog linked below: https://lnkd.in/gVpWJGZw DM me if you have been seeing AI happening in front of you and want to know how you can avoid missing out.

32

10 Comments

pro tip: teach your coding agent to make small commits. add pre-commit hooks in the same way you used conventional commits. pretty rad.

1