Project Management

Practitioners documented Cowork and Claude Code setups that use shared CLAUDE.md files, progressive skill loading, and agent memory instead of blank-session prompting. That matters for vibe-coders because PM, design, and implementation workflows can compound across sessions, though some stronger performance claims came from third-party posts.

Holaboss launched holaOS Beta 0.1 with permanent workspaces, sub-agents, and a dashboard for recurring tasks and review loops. Use it if you want persistent project memory instead of reset-every-run agent chats, though the evidence is mostly launch-thread documentation.

At Code with Claude San Francisco, builders showed Claude Code running 21-agent app pipelines across Figma, Jira, Confluence, and TestFlight. Users should watch for reliability strain as posts and conference recaps tie recent slowdowns to Anthropic's reported 80x growth.

Rezonant showed a browser extension that records screen walkthroughs and narration, then turns them into structured briefs, tickets, and agent-ready tasks using live product context. It plugs into GitHub, Figma, Linear, Jira, Notion, Granola, and Confluence, so teams can skip a standalone spec doc.

Figma added voice-to-text prompts, version history, question cards and clearer context in Make, while Weave gained node unpacking, iterators and flow-preserving delete. The updates make it easier to capture prompts and manage asset-heavy AI flows inside Figma; try the new controls if your team needs traceable edits.

Figma added new FigJam MCP tools for generating architecture diagrams, placing notes and code blocks, and reading a board back into next steps. The release matters because system maps can now be created and queried from the same MCP workflow instead of being rebuilt manually in FigJam.

Posts from PM candidates say Google is using a live Cursor build instead of a standalone technical screen. Figma, Codex, and Claude Code users are also shipping prototypes and PRs inside coding tools.