Loading…
Topic
Collaboration
3 posts about Collaboration. Every summary links to the original.
- 3 posts
- 3 companies
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
Newest first
Posts
How Block powers collaborative AI agents with Buzz and Unity Gateway
Block developed Buzz, an open source collaboration workspace where employees and AI agents work together in channels, threads, and direct messages. Users create agents, choose a model or coding harness per agent, and collaborate with multiple agents and colleagues in one environment. Databricks Unity Gateway provides centralized access to frontier and open-weight models from OpenAI, Anthropic, and Google through a single integration. Block experiments with multi-agent workflows, using a more capable model to coordinate agents powered by smaller, more efficient models, and has an internal benchmarking approach for different configurations. Buzz is model-agnostic, self-hostable, and supports multiple agent harnesses including a lightweight version of Goose.
Preview, edit, and collaborate on markdown (.md) files natively in Google Docs and Drive
Google Workspace now allows native viewing, editing, and real-time collaboration on Markdown (.md) files directly in Google Docs, eliminating manual conversion between formats. Markdown, which preserves structured content such as tables and headers without bulky formats, has seen surging usage in Google Drive as a common language for humans and AI agents. When opening an .md file, a visible badge confirms native editing mode, and users can co-edit in real time with teammates or AI agents, leave comments, and track suggestions while preserving underlying file fidelity. Google Drive provides rich rendered previews with full table and hyperlink support, as well as an option to toggle to raw text, and version history maintains a transparent audit trail. This unified workspace combines Markdown’s simplicity with Google Docs’ collaboration features to help teams draft, review, and ship technical content faster across developer tools and git repositories.
Collaborate with Claude on Projects
Anthropic announced Projects for Claude.ai Pro and Team users, a feature that organizes chats around curated knowledge and custom instructions to avoid the cold start problem, powered by Claude 3.5 Sonnet. Each project includes a 200K context window, equivalent to a 500-page book, allowing users to add documents, code, and insights to ground Claude’s outputs. Users can define custom instructions per project to tailor responses, such as adopting a formal tone or role-specific perspective, and Artifacts provide a dedicated window for code, documents, and diagrams with live previews that streamline reviews. Team users can share conversation snapshots into a shared activity feed to inspire collaboration, and early adopters like North Highland reported completing content creation and analysis tasks up to 5x faster. Anthropic confirmed that data shared within Projects will not train generative models without explicit consent, and future native integrations with popular applications and tools are planned.
Related topics
All topics →Weekly digest
The best engineering reads, once a week.