Tool desk · Updated daily
Many coding agents execute generated code with full access to secrets, creating a significant data exfiltration risk. Developers should explicitly define and enforce security boundaries in agentic architectures to limit access and reduce exposure. Read more: https://lnkd.in/ee-SEQgD
How we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.
Go deeper on Vercel
The briefing
19 May 2026Step-by-step guide to migrating your Lovable app to Claude Code. Learn how to move from Lovable's managed platform to a stack you own and control.
Read →The briefing
10 Feb 2026Honest 2-week review of OpenClaw — an autonomous AI agent powered by Claude. We test setup, safety, autonomy, and real value to see if it's worth using.
Read →
34 minPodcast
James and Kieran discuss practical AI-powered development through real-world examples, including a seven-year-old building a website business with Claude Code voice mode, Anthropic's new Claude Design tool, API security challenges in the AI agent era, and Cloudflare's expanding AI infrastructure offerings. The episode covers hands-on experiences with vibe coding, emerging design tools, and the evolving landscape of AI-assisted development.
Watch now ↗
Podcast
James and Kieran discuss the practical realities of building AI-powered software, emphasizing the importance of testing in vibe-coded applications, exploring alternatives to traditional SaaS tools, and implementing autonomous AI agents for business operations. The episode covers technical topics like Convex databases, app store bottlenecks from AI-generated submissions, and using OpenClaw as a marketing automation agent.
Watch now ↗
38 minPodcast
In this Create With podcast episode, James and Kieran are joined by Matt Roberts from Happy Operators for an in-depth discussion on using autonomous AI agents in production. The conversation covers practical experiences with OpenClaw, security considerations, comparison with emerging tools like Manus, and the broader shift toward AI-assisted development. They also discuss the VibeCoding Olympics results, Bubble's new AI capabilities, and research on Claude.MD file effectiveness.
Watch now ↗Latest tool news
VercelDigestVercel shipped dashboard controls, faster builds, alert filtering and more ways to work with AI models and connected services. The updates cover feature flag sharing, project…
Scoped Personal Access Tokens now let Supabase users restrict a credential to specific organisations, projects and permissions. New tokens created in the Dashboard use scoping by…
Vercel custom monitors can now turn Observability query results into alerts. Builders can track AI Gateway costs, Core Web Vitals, performance metrics, Workflow failures, external…
VercelDigestVercel shipped quicker static deployments, four AI Gateway models, more free domain choices and new CLI controls in late October. The changes cover developers testing sites…
submitfeedback is a new Vercel MCP tool that lets agents and harnesses send bug reports, friction reports and feature requests directly to the Vercel team. Feedback can include…
Managed API Key is now a connection option for Stripe connectors in Vercel Connect. It creates a separate restricted Stripe API key for each agent or task, removing the need to…
The Create With Briefing
Every Tuesday: the tool changes worth knowing, real business use cases, and what's on near you. Free, unsubscribe any time.
Supabase
