
Wabi is repositioning its prompt-based app builder as a personal AI agent that can create interfaces on demand, combining chat, apps and ongoing tasks.
Wabi, an AI startup that previously let users build apps through prompts, is shifting its focus to become a messaging platform that combines conversation with app creation and task completion. The pivot responds to growing demand for AI agents that integrate chat and productivity features. According to the company's founder, the new version aims to solve problems with chat-only agents by creating custom interfaces on demand within conversation threads, allowing users to organize apps and tasks around specific topics like health or family rather than having everything buried in a single message stream.

DeepSeek has released an official desktop app for DeepSeek Harness (dsh), its open-source agent harness. The app ships with the v0.2 preview. Installers cover macOS (Apple silicon) and Windows (64-bit). Is it deployable? Yes, today, as a preview. Download it from deepseek.com/harness or run npx @deepseek-ai/dsh web. DeepSeek warns that compatibility-breaking changes will follow. What Shipped in v0.2 A harness is the runtime that turns a model into an agent. It reads files, runs command

When AI systems claim task completion without verification, downstream errors can cascade through dependent processes, exposing gaps in reliability for critical workflows.

Capcom's Pragmata might be all about the horrors of AI, but in practice the studio doesn't seem so down on the tech. During the Capcom Open Conference RE: 2026 programmer Satoshi Ishida gave a presentation with the mouthful of a title: "The Outlook and Future of the REX Project, Further Evolving the RE Engine for the Next Generation." During the talk he laid out the challenges facing studios producing games at the scale of Resident Evil, which can make even simple tasks extreme
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven