Knowledge management and documentation for code
Live Last read · last published · next check
The foundation problem most engineering organizations are ignoring. Every company wants to become AI-native. The ambition is everywhere — in board decks, engineering all-hands, and hiring briefs. And the response is usually the same: deploy Copilot, roll out Cursor, give everyone Claude Code, stand up some agents. These are real investments. But they’re not the […] The post You Can’t Become…
A month into Anthropic’s Project Glasswing, the numbers are in, and they settle an argument the security industry has been having for years. Claude Mythos Preview, working with about 50 partner organizations, found more than 10,000 high or critical vulnerabilities. Cloudflare alone surfaced 2,000 bugs, 400 of them high or critical, with a false-positive rate […] The post AI just found 10,000 bugs…
Swimm is becoming a service company. From Software as a Service to Service as Software. Here’s why. The pace of AI has turned long-term tool decisions into a moving target. The model that looks right today might be middle of the pack in six months. The framework that wins this quarter might be deprecated next […] The post We’ve stopped asking customers to bet on the right tool appeared first on…
Enterprise IT leaders want to build an AI modernization capability that works like a factory – standardized processes with best-in-class tools for each stage that enable predictable ROI across the portfolio. Yet, using agentic AI on real-world applications is falling short of expectations. The barrier isn’t AI code and test capability but rather the ability […] The post Swimm 2.0: the…
The progression is visible and accelerating. Three years ago, autocomplete suggested a line of code and you decided whether to accept it. Two years ago, an AI assistant drafted a function and you reviewed the output. Today, AI agents handle entire features, refactor codebases, and migrate legacy applications – and humans review the result, not […] The post Tests are the final gate: why…
Using Swimm for context saves cost and time. Our new benchmarking tests show just how much. The post 75% faster. 61% cheaper. What Swimm does for Claude Code. appeared first on Swimm .
Claude Code is a genuinely impressive tool. We’ve used Claude Code extensively ourselves. However, Anthropic’s recent blog post about using Claude Code for COBOL understanding – that wiped $40 billion off IBM’s stock price – is not new information. There is no new COBOL product, no answer to the vast limitations of LLMs in understanding […] The post A blog article is not a product. No, Claude Code…
After working with enterprise teams on modernization initiatives throughout 2025, we’re seeing a clear shift in how organizations approach legacy transformation. The hype cycles have matured. The budgets have tightened. And the focus has moved from technology experimentation to practical execution. Here are seven application modernization trends defining enterprise IT strategy in 2026, based on…
Our validator needs an LLM to be honest. This is how we did it. The post To trust an LLM, make lying harder than telling the truth appeared first on Swimm .
Introduction In this post, we will discuss how to extract business logic from COBOL applications. What are business rules? Business rules are the rules that govern the operation of a business. There have been many attempts to define “business rules” formally (for example, by the Business Rules Group), which stated that a business rule is […] The post Blackbox to blueprint: Extracting business…
