“in Colin Matthews reports that only ~20 of 51 teams importing design systems into AI prototyping tools use Figma as their source of truth, with the remainder on GitHub, Storybook or MCP.”

#9 in Colin Matthews reports that only ~20 of 51 teams importing design systems into AI prototyping tools use Figma as their source of truth, with the remainder on GitHub, Storybook or MCP. #10 𝕏 LlamaIndex 🦙 introduces Extract v2 with simplified tiers, pre-saved extraction configurations, and fully configurable document parsing for more powerful, streamlined data extraction.

“#8 𝕏 Thariq is excited about Figma’s new MCP, starting with a rough Figma sketch that Claude Code fleshes out into a polished design which he then iterates on before final review.”

#4 𝕏 Thariq sketched a new grocery-list feature in Figma and then prompted an AI to convert the mockup into his app’s style while adding extra components. #5 𝕏 Peter Yang suggests that any account replying to over a dozen posts within five seconds is likely AI-generated. #6 in Thomas Hendrickx recommends Claire Vo’s How I AI YouTube series for its hands-on, real-world AI workflows—product builds, system setups like Teresa Torres’ Obsidian setup—rather than generic demos. #7 𝕏 Lenny Rachitsky : Claire Vo built 9 OpenClaw agents across 3 Mac Minis to automate sales outreach (replacing a 10 hr/week rep), family scheduling, podcast prep, homework help, and course project management. #8 𝕏 Thariq is excited about Figma’s new MCP, starting with a rough Figma sketch that Claude Code fleshes out into a polished design which he then iterates on before final review. #9 𝕏 There's An AI For That unveiled upgraded autonomous bots that carry up to 25 kg (55 lb), clear 30 cm (12 in) obstacles, mount heavier payloads like micro-missiles and grenade launchers, and use a “collective brain” for real-time data sharing and coordinated action.

“Anthropic releases Claude Code channels - We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord.”

#1 𝕏 Anthropic releases Claude Code channels - We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone. #2 📝 OpenAI News OpenAI to acquire Astral - OpenAI announces its intent to acquire Astral to enhance its capabilities, bringing together teams and technology to accelerate product development and research.

“MCP (Model-Context-Protocol) connectors by Anthropic enable agents to use Gmail, Google Calendar, Granola, Notion, and Stripe; custom skills stored in .claude/skills (e.g., ads analyst skill scraped 220 ads and landing pages to generate a competitor report that once required 3–4 hours manually).”

#10 ▶️ Building AI Agents that actually work (Full Course) Greg Isenberg Building an AI executive assistant agent using markdown context and memory files (agents.mmd, memory.mmd), MCP connectors for Gmail, Google Calendar, Granola, Notion, and Stripe, and custom skills within harnesses Claude Code, Codeex, and Anti-Gravity. Agent loop (observe, think, act) runs on LLMs such as Claude Opus 4.6, GPT 5.4, and Gemini 3 within harnesses Claude Code, Codeex, and Anti-Gravity, demonstrated by building a minimalist portfolio site for Greg Eisenberg via Perplexity research, code generation, localhost preview, and screenshot validation. Context is preloaded from agents.mmd (called claude.mmd or gemini.md per platform) and preferences are persisted in memory.mmd via “update memory.mmd” instructions to retain user settings across sessions. MCP (Model-Context-Protocol) connectors by Anthropic enable agents to use Gmail, Google Calendar, Granola, Notion, and Stripe; custom skills stored in .claude/skills (e.g., ads analyst skill scraped 220 ads and landing pages to generate a competitor report that once required 3–4 hours manually).

“#21 in Marily Nika, Ph.D warns that a rogue Chipotle burrito-bot demo exposed how AI products fail without steering guardrails.”

#21 in Marily Nika, Ph.D warns that a rogue Chipotle burrito-bot demo exposed how AI products fail without steering guardrails. She’s teaming with Aman Khan and Tal Raviv for live OpenClaw & MCP builds to teach true AI Product Sense.

“LlamaIndex 🦙 explains that MCP tools’ fixed-schema API calls give precise, always up-to-date context for fast-evolving domains, while local natural-language Skills offer quick setup at the cost of potential hallucinations; in practice, documentation MCPs beat custom Skills fo...”

LlamaIndex 🦙 explains that MCP tools’ fixed-schema API calls give precise, always up-to-date context for fast-evolving domains, while local natural-language Skills offer quick setup at the cost of potential hallucinations; in practice, documentation MCPs beat custom Skills fo...

“𝕏 v0 now supports custom MCP servers in its API—simply add an mcpServerIds array (e.g. ['vercel-mcp'] ) to your v0.chats.create call to route chat requests through your own MCP endpoints.”

𝕏 v0 now supports custom MCP servers in its API—simply add an mcpServerIds array (e.g. ['vercel-mcp'] ) to your v0.chats.create call to route chat requests through your own MCP endpoints.

“Santiago warns that the MCP-driven agent explosion has outpaced server security—static API keys are a disaster and wrestling with OAuth 2.1/PKCE is far too complex, yet you need dynamic, short-lived, tightly-scoped credentials for autonomous, multi-system agents.”

The newsletter frames MCP as part of the broader security and authorization problem for autonomous agents.

“in Dharmesh Shah argues that the composability and rich documentation of CLIs make them a perfect fit for agentic coding, and suggests platforms like HubSpot should offer a CLI interface alongside APIs and MCP to unlock more powerful agentic workflows.”

#13 in Dharmesh Shah argues that the composability and rich documentation of CLIs make them a perfect fit for agentic coding, and suggests platforms like HubSpot should offer a CLI interface alongside APIs and MCP to unlock more powerful agentic workflows. #16 𝕏 Peter Yang argues that building an MCP server should be the final step—first expose each capability as single-purpose, well-documented APIs with agent-readable docs and ensure your product works outside a human UI so AI agents can seamlessly chain tasks.

“#11 ▶️ Anthropic killed Tool calling AI Jason Entropic’s Advanced Tool Calling release introduces programmatic tool calling via a code execution sandbox, dynamic filtering for Web Fetch v2026209, deferred loading through Tool Search, and input examples for tool usage, boosting agent efficiency and reducing token consumption.”

#11 ▶️ Anthropic killed Tool calling AI Jason Entropic’s Advanced Tool Calling release introduces programmatic tool calling via a code execution sandbox, dynamic filtering for Web Fetch v2026209, deferred loading through Tool Search, and input examples for tool usage, boosting agent efficiency and reducing token consumption. Programmatic tool calling uses a code_execution sandbox and allowed_caller parameter to let models generate code that invokes multiple MCP functions, cutting token usage by 30–50%.