Fragments: May 5

2026-05-05 · Source: Martin Fowler · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, medium

Summary

The "Fragments: May 5" brief highlights several AI and software development trends. Rahul Garg launched Lattice, an open-source framework operationalizing engineering patterns like Clean Architecture for AI-assisted programming, available as a Claude Code plugin or for any AI tool. An update added a Q&A to the popular Structured-Prompt-Driven Development (SPDD) article. Jessica Kerr identified a "double feedback loop" in AI tooling, where developers refine both the product and the AI tools used. Legally, Ashley MacIsaac is suing Google for defamation after its AI falsely linked him to criminal convictions. Financially, major tech firms are investing over 50-75% of revenues in AI infrastructure, a "staggering" amount, while Apple invests around 10%. This divergence resonates with arguments for local AI models being "Good Enough" for agentic programming, potentially mirroring Apple's historical strategy. Kent Beck also introduced the "Genie Tarpit," questioning if AI tools can produce software with the internal quality needed to avoid future complexity.

Key takeaway

For AI Engineers evaluating development workflows, you should consider integrating frameworks like Lattice to embed engineering standards directly into AI-assisted programming, mitigating the "Genie Tarpit" risk of low internal quality. Explore local AI models for agentic programming to reduce costs and data exposure, especially if "Good Enough" performance suffices. Be mindful of the "double feedback loop" to continuously refine your AI tools, and ensure robust guardrails are in place for any AI-generated content to prevent reputational and legal risks.

Key insights

AI's rapid evolution demands adaptable development practices, responsible deployment, and strategic infrastructure choices.

Principles

• AI tooling involves a "double feedback loop."
• AI systems require robust guardrails and accountability.
• Internal quality remains critical for AI-generated code.

Method

Lattice operationalizes AI-assisted programming patterns using composable skills (atoms, molecules, refiners) and a living context layer (.lattice/ folder) to embed engineering disciplines and project standards.

In practice

• Implement sandboxing for AI agent development.
• Integrate battle-tested engineering disciplines into AI tools.
• Consider local models for cost and data privacy.

Topics

• AI-assisted Programming
• Agentic Programming
• AI Ethics
• AI Infrastructure Investment
• Local AI Models
• Software Quality

Best for: CTO, VP of Engineering/Data, AI Architect, AI Engineer, Software Engineer, Director of AI/ML

Related on AIssential

• Trump’s AI Order Won’t Stymie U.S. Competition with China — A future Trump AI order is predicted to not hinder U.S. AI competition with China.
• EU Unveils Sweeping Tech Sovereignty Push, Balancing Autonomy with Openness — Europe's tech sovereignty strategy balances reducing foreign dependency with fostering domestic capacity and open markets.
• Personalization is the #1 Driver of Meaningful Employee Recognition, Snappy Workforce Study Finds — Personalized recognition, particularly through gifting, is the top driver for meaningful employee appreciation and engagement.
• Micro-Dyn, a leader in healthcare claims pricing software, announces its acquisition of CMSPricer. — Micro-Dyn's acquisition of CMSPricer expands its healthcare claims pricing and contract management platform with new technology and executive expertise.
• ThroughPut.AI Now Available on SBIR Aisle of CDAO’s Tradewinds Solutions Marketplace — AI-driven materiel flow optimization significantly improves military equipment readiness by preempting shortages and streamlining maintenance.
• Asset Panda Introduces “Build with Excel” to Streamline AI-Powered Account Setup in Asset Panda Pro — Asset Panda's "Build with Excel" uses AI to convert existing spreadsheet data into a functional asset tracking system, simplifying setup.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Martin Fowler.