AI forced us off Scrum after years. Not because Scrum was broken.
3 weeks task-to-production felt wrong when AI makes 3 days possible.
Everyone debates vibe coding. The real shift is redesigning the entire loop from customer to prod. #EngineeringLeadership
Introducing Claude Design by Anthropic Labs: make prototypes, slides, and one-pagers by talking to Claude.
Powered by Claude Opus 4.7, our most capable vision model. Available in research preview on the Pro, Max, Team, and Enterprise plans, rolling out throughout the day.
Three ways to do browser automation with AI agents: Chrome extension (zero setup, breaks in prod), dev-browser CLI (sweet spot for agent work), full Playwright (max control, max overhead). Match the tool to the scope. #AIAgents #ClaudeCode
Replaced most MCP with local scripts. Faster, cheaper, easier to debug. MCP overhead adds up fast when you have 10+ tools, hundreds of tokens per request before anything useful happens. Right tool for the right job. #ClaudeCode #AIAgents
Running 15 agents in parallel to review tasks. Code diff + ClickUp spec + UI screenshots, all at once. Results go back into ClickUp automatically. The gap between what was asked and what was built is where most bugs live. #AIAgents #ClaudeCode
Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.
It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.
Now in public beta on the Claude Platform.
Claude Code agent teams daily, the leak explains a lot. The tool-calling architecture is more elegant than I expected. The gap between "we could build this" and "this runs reliably at scale" is huge. #ClaudeCode
The goal:
Cut down hours (or days) spent wrangling schemas ➡️ into minutes of automated model generation.
Perfect for analysts, data engineers, or anyone maintaining reporting pipelines.
Why we built this: #LLMs and #BItools are great, but only as good as your #datamodel. Poor modeling = poor answers. This tool bridges that gap by making your data both structured and explainable, for humans and machines.
vasekd retweeted
Claude Sonnet 4 is back via first party support from @AnthropicAI!
Available at 2x credits (limited time discount) per request for Pro and Teams users. That’s 250 requests a month!
vasekd retweeted
🎉 Hendersonville & WNC, you’re invited!
7/18/25, we’re celebrating the reopening of the Ecusta Trail—after months of rebuilding from Helene’s flooding.
toashevilleandbeyond.com/a-n…
#AskHendo #EcustaTrail #HendersonvilleEvents #WNCCommunity #FoodieAdventure #TrailCelebration – at Hendersonville, NC
Did you know? @SnowflakeDB has partnered with @AnthropicAI to integrate #Claude 3.5 models into its #AIDataCloud. This collaboration enables enterprises to leverage advanced #LLM capabilities for enhanced #DataAnalytics and #Visualization.
vasekd retweeted
Check out Inzata's new AI module🤖. It serves as an assistant across InBoard, InModeler, and InFlow modules. It can answer questions❓, describe metrics💭, reports📈, and more. Learn more👇 inzatastg.wpengine.com/inzat…
#AI #DataAnalytics
vasekd retweeted
🚀 Agile Data Warehouse: Swift changes, streamlined modeling, follows #Kimball methodology.
🔍 SOLUTION: Modernize data analysis with our tech—crafted tools and methodology. No more outdated procedures, thanks to Inzata's all-in-one. #agiledatawarehouse @myagiledata







