The PyTorch Korea User Group will host its inaugural offline conference on Saturday, November 21, 2026, hosted at AWS Korea in Centerfield East, Seoul. Designed around the end-to-end AI lifecycle, the event features three primary tracks: Build, Serve, and Run. Community members, developers, and researchers are invited to submit session proposals highlighting real-world project wins, takeaways from failed experiments, or core performance optimizations. The deadline to submit proposals is Sunday, September 13, 2026, at 23:59 KST. Submit your talk today:

2 months ago, we launched a Gemini power user group to test early features in the app. 20+ features tested later, your feedback has been incredible. Thank you! A new cohort is now getting early access to what’s next for Daily Brief & Personal Intelligence, and we’ll keep onboarding people. ​Join our community:

Infrastructure challenges are rarely unique to one team. At this HashiCorp User Group meetup in Singapore, practitioners share real-world lessons, implementation strategies, and experiences building and operating cloud infrastructure at scale. If you're working with Terraform, platform engineering, or cloud automation, this discussion offers practical insights from peers in the field. See talks like: 🛠️ Engineering "Invisible" platforms with Crossplane and Score 🤖 Terraform at scale: Architecture, automation, and AI-assisted @awscloud delivery 🫆 Enable zero trust for service connectivity across hybrid cloud with Consul 🎥 Watch the meetup recap:

There's only one month until HashiConf at IBM TechXchange! Don't miss your opportunity for... 900+ Total sessions including pre-conference activities 450+ Technology breakouts 180+ Hands-on labs 150+Tech talks 50+ Certifications 70+ User group meetups 100+ HashiCorp product sessions Register today.

Grok Bot desktop 0.68.1 is out Bots can build slide decks with you now, 1:1 chats take on your Bot's color, and the Bot's computer got bigger and faster. New • Your messages in a 1:1 Bot chat take that Bot's color; set Accent to Black in Settings → General to turn it off. Requires Grok Bot 0.64.0 or later. • Bots can build slide decks with you, showing sample slides to choose from, and deliver them as PowerPoint files or Google Slides. • Bots can send formatted emails from a draft card, so recipients see headings, bold text, and lists. • Bots can search your Gmail Spam folder and move a message back to your inbox. • Team Bots can mention a Slack user group so its members get notified, while @​here and @​channel still don't ping anyone. (Teams) Improved • Typing / in the composer no longer opens a menu of skills and actions. • Bots work faster on their computer: actions settle sooner, screenshots come back quicker, and new windows skip a five-second wait. • The Bot's computer has a 1920 × 1200 screen, up from 1280 × 800, giving more room when you watch it or take over. • In Slack threads it follows, a Team Bot stays quiet on untagged replies that don't need it, such as emoji-only replies. (Teams) Fixed • Gmail actions fail less often: send and reply no longer report a missing tool, and Bots wait out Google's rate limits. • Email drafts show up as a card in the chat, a Send cut off by Stop still goes out, and attachments keep their file names. • The Bot's browser recovers from a crashed tab, handles large uploads, and gives up on a stuck page after 25 seconds. • Stop or a new message ends a Bot that's stuck on an unresponsive step within about 30 seconds. • Secure Forms fill into the page the Bot has open, and checkout card fields get a Secure Form instead of a screen handoff. • When X or Vercel needs you to sign in again, the Bot shows a reconnect card instead of retrying or giving up. • If the app's window crashes, Grok Bot reloads it instead of leaving it blank. On Linux and Mac (Apple silicon) now. Notes:

I am so grateful to have had the opportunity to chat with Sadie St Lawrence about Community, Slack, Al and the impact it all has on myself and so many others. I love people, and its an honor to help bring as many people as I can on this journey so that no one gets left behind. I am also grateful to be in a position where I can experiment with technology to help those who cannot always advocate for themselves. If you are wondering how to get started in the community - find a local or remote user group and join today! If you are wondering how to get started with Slack, Al or anything else - stay curious, join Trailhead and spin up some sandboxes to get hands on. And if you need help with implementation, brainstorming or anything else Slack, message me and let's chat! @salesforce @SalesforceAdmns @SlackHQ @sadiestlawrence @slack_community @Benioff @gilliankbruce

# Useful but Little-Known Features of Claude Agent SDK 🌍 Watch, block, or modify agent behavior -- all through hooks. Rich hook events let you intercept everything from tool calls to subagent completion at any point. 📌 Title: Rich Hook Events 🔗 URL: 🧩 Overview The Claude Agent SDK hook system lets you register callback functions at key points in agent execution. Events available in both Python and TypeScript include: PreToolUse (before tool call), PostToolUse (after tool execution), PostToolUseFailure (on tool failure), UserPromptSubmit (prompt submission), Stop (execution stop), SubagentStart/Stop (subagent lifecycle), PreCompact (before conversation compaction), PermissionRequest (permission dialog), and Notification (status messages). Callbacks run in the app process, not in the context window. 🛠 How to Use ```python import asyncio from claude_agent_sdk import ( ClaudeSDKClient, ClaudeAgentOptions, HookMatcher, AssistantMessage, ResultMessage, ) # Hook to block writes to .env files async def protect_env_files(input_data, tool_use_id, context): file_path = input_data["tool_input"].get("file_path", "") file_name = file_path.split("/")[-1] if file_name == ".env": return { "hookSpecificOutput": { "hookEventName": input_data["hook_event_name"], "permissionDecision": "deny", "permissionDecisionReason": "Cannot modify .env files", } } return {} # Hook to log all tool calls async def audit_logger(input_data, tool_use_id, context): print(f"[AUDIT] Tool: {input_data['tool_name']}, ID: {tool_use_id}") return {} async def main(): options = ClaudeAgentOptions( hooks={ "PreToolUse": [ HookMatcher(matcher="Write|Edit", hooks=[protect_env_files]), HookMatcher(hooks=[audit_logger]), ], } ) async with ClaudeSDKClient(options=options) as client: await client.query("Update the configuration files") async for message in client.receive_response(): if isinstance(message, (AssistantMessage, ResultMessage)): print(message) ``` 🏗 Integration into Production Systems - Return permissionDecision in hookSpecificOutput to allow/deny/ask/defer tool calls - Multiple hooks on the same event run in parallel; the most restrictive decision wins (deny > defer > ask > allow) - Use additionalContext in PostToolUse hooks to append info to tool results - Return async_=True for fire-and-forget side effects (logging, metrics) without blocking the agent 💡 Use Cases 🛡 Security: block access to sensitive files/directories with PreToolUse 📊 Audit logging: record every tool call with PostToolUse 🔔 Notification integration: forward status updates to external services (Slack, etc.) via Notification hooks 🔄 Input transformation: redirect file paths to sandbox using updatedInput in PreToolUse ⚠️ Caveats - Hooks run in the app process; implement error handling to prevent unhandled exceptions from interrupting the agent - Returning "allow" from a PreToolUse hook does NOT skip subsequent deny rules or permission mode evaluation - Matchers only match tool names, not file paths. Check tool_input inside the callback for path filtering - Default hook timeout is 60 seconds ✨ Hold the reins of your agent for safe and transparent automation! #ClaudeAgentSDK# #AIAgent#