JP Dillingham

Most vibe coders are optimizing the wrong layer. There’s a post going around showing how a “non-technical” prompt and a “senior engineer” prompt produce wildly different results for the same task. The takeaway people grabbed: write longer, more detailed prompts. That’s not the lesson. Here’s what usually happens. A deal team needs to review 6,000 documents in a virtual data room for a mid-market acquisition. Someone asks an AI to flag every contract with a change-of-control provision. They get a script that searches for the phrase, pulls matches, and dumps them into a spreadsheet. Half the results are boilerplate. Key risks in assignment clauses and consent requirements get missed entirely. Nobody knows what the AI skipped or why. An experienced builder doesn’t write a better search query. They ask different questions first. What document types are actually in this data room? Are we looking for explicit change-of-control language, or any provision that could block or complicate closing? Do amendments override the base agreement? Are side letters in the set? What’s the priority: speed to first-pass flags, or completeness for the disclosure schedule? What happens when a clause is ambiguous and needs deal-team judgment? That reframes the problem before a single line of code gets written. The gap between a weak AI output and strong output isn’t verbosity or technical vocabulary. It’s the quality of the constraints. Success criteria. Tradeoff decisions. Knowing what not to build. Vibe coding gets dramatically better when you stop describing the task and start defining the boundaries around it. I Try this: next time you prompt an AI to work through a diligence set, write three sentences before the request. What’s a real risk versus noise? What should get escalated instead of auto-flagged? What’s the consequence of a false negative? That alone will change the output more than any prompt template. Subscribe to PossibLaw. Substack. Podcast. Tools to become a builder. We run custom training for legal teams who are done watching from the sidelines. Let’s talk.

2

2 Comments

Funding didn’t speed up your Rails team. It exposed everything you duct-taped to ship fast. They slow down because execution changes. You shipped the product fast. Now enterprise customers want SSO, audit logs, compliance. 
Your engineers are still firefighting onboarding. But now: • Releases feel heavier • Senior engineers are overloaded • Leadership is back in the weeds • Velocity feels… fragile The instinct? “Should we rewrite?” “Is Rails the problem?” “Do we need more engineers?” In most cases, the bottleneck isn’t headcount or the monolith. It’s ownership. It’s decision flow. It’s execution structure. Before rewriting your app, map where work actually gets stuck. If execution feels heavier post-growth, our playbook walks through how to create clarity, ownership, and decision flow inside Rails teams. 👉 teloslabs.co/playbook #tech #rails

3

👨‍💻 We don’t micromanage at Optavyn. Every dev here knows they’re not “just writing code”, they’re building products that matter. Every feature we ship solves a real-world problem. Every API we build connects with a user’s workflow. Every screen we design has intent behind it. Our team works remote, but we’re aligned, focused, and committed to the end goal: Delivering results not just tasks. If you're a founder or agency who values clear ownership, clean code, and reliable delivery, we might be the team you’ve been looking for. #TeamCulture #RemoteTeam #SoftwareProduct #OptavynCulture #ExecutionMatters #TechThatWorks

4

Any best guesses on how long until Claude Code can: 1. Fire up the browser (without needing the MCP configuration) to evaluate changes 2. Fully leverage the Chrome Dev Tools 3. Use the Ruby debugger I’m finding Claude Code is creating fixes that would have been too tedious or painful. The gap right now is testing and debugging.

10

4 Comments

🏗️ How HOT2000 Makes Understanding Code Pathways Simple Navigating SB12, Step Code, and Net Zero pathways can be confusing—especially with multiple compliance options. HOT2000 helps builders and designers visualize the best route for each project, reducing errors and saving time. 💡 The Challenge  ❌ Multiple code pathways can be overwhelming  ❌ Manual calculations risk compliance mistakes  ❌ Early design decisions may lock builders into suboptimal paths  ❌ Misunderstood pathways can cause redesigns or permit delays  🔧 The Solution: HOT2000  HOT2000, Canada’s official residential energy modeling software, provides clear guidance on code compliance by simulating performance under all relevant pathways.  Here’s how it helps:  ✅ Compares prescriptive, performance, and Net Zero pathways side by side  ✅ Shows energy and cost impacts for each compliance option  ✅ Highlights where early design choices affect code eligibility  ✅ Reduces the risk of costly redesigns or non-compliance  ✅ Produces clear reports for stakeholders and municipalities  🎯 The Result  A builder in Mississauga used HOT2000 to evaluate three compliance pathways for a 2-storey home. The software revealed the most cost-effective route met Step Code Tier 2 with minimal changes, avoiding a $7,500 mechanical redesign.  💬 Bottom line: HOT2000 makes code compliance straightforward, helping builders confidently select the best pathway for every project. 📥 Download your free guide:  👉 https://lnkd.in/g_wtUD2T  💼 Want clarity on code pathways for your next build?  Book a call: https://lnkd.in/g3QtQUMK 

1