The retrieval layer that helps AI systems navigate, read, and verify information inside even the most complex documents
Agentic Search is a retrieval system that enables AI models to search through and navigate complex documents and data sources more effectively by using a multi-step process to find, inspect, and verify information. The system improves search accuracy significantly, with performance gains up to 3x on financial document questions and 45.6 points on multi-document questions, while also reducing latency by up to 39.6 percent and token consumption by up to one-third. It works with existing search indexes through five tools called search, open, navigate, read, and grep, and is available through Mistral Search Toolkit and built into related platforms. The technology matters because it allows organizations to extract value from their proprietary and sensitive data, including financial filings, legal contracts, and internal records, without moving that data outside their secure boundaries.

Slack is introducing dedicated channels where teams can vibe-code together with AI agents instead of jumping between different tools and conversations. The Slack Code launch includes open, project-specific code channels with dedicated user tabs, alongside features that compare coding changes and preview HTML output before the project is shipped. "With Slack Code, when you have an idea or need to build a new feature, update a web page, or fix a bug, you simply tag in a coding a

Meta said its Muse Spark model is powering the dictation feature.

Binance's Agent OS works with tools including ChatGPT, Claude Code, and Cursor.
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven