
Maintaining working memory in AI agents
🕓 7 MINTL;DR An LLM has no memory between calls. Its working memory for a single request is one thing: the tokens in the context window. Attention

🕓 7 MINTL;DR An LLM has no memory between calls. Its working memory for a single request is one thing: the tokens in the context window. Attention

🕓 6 MINAI-native productivity platform for enterprise .NET applications, launching at Microsoft Build

🕓 5 MINSix markdown files that turn an AI agent from a Stack Overflow query into a teammate joining on day one

🕓 7 MINWhat actually happened when we ported a real 15-window WPF OCR app to Uno Platform: 57% less code, 52% less memory, ~92% feature parity, and the patterns that didn’t survive

🕓 9 MINSeven ThemeResource keys, one blank afternoon, and the name-vs-size trap every AI-assisted XAML migration hits.

🕓 5 MINBetter prompts help, but they only go so far. The real skill is giving coding agents the product, UX, and architectural context they can’t infer on their own

🕓 2 MINMigrating from desktop-based applications to the Web with Uno Platform is reasonably straight forward. The important thing is to first perform your research, think about
Uno Platform 5.2 LIVE Webinar – Today at 3 PM EST – Watch