Netlify

You can now start a Netlify project with a prompt. Type what you want to build, pick your agent, get a live URL on production infrastructure in minutes. This is netlify.new. Here's what that actually means: ntl.fyi/46TbFce

What stalls your AI-assisted builds? Not the prompting. The part AFTER. Auth? Storage? Team access? The "now what?" moment? What's yours? netlify.com/platform/start…

Dana Lawson is joining us at AI Native DevCon London 2026. As CTO of Netlify ( @Netlify ), Dana leads engineering, product, and design, shaping how modern teams build and ship on the web. With leadership experience across GitHub, Heptio, and New Relic, she brings a deep understanding of how systems evolve as the way we build software changes. Her session, Built for Humans. Now Agents Are Here., explores a shift many teams are only starting to notice. Our tools, workflows, and platforms were designed assuming a human is always in the loop. But when agents take over parts of that loop, the cracks start to show. What you’ll take away • Where existing developer workflows break when agents become the primary users • Why logs, previews, and CLI outputs often fail in agent-driven environments • What Agent Experience (AX) looks like in practice • How to design systems with clearer signals, structured feedback, and better collaboration between humans and agents • Why judgment and system design are becoming more critical than ever This session goes beyond surface-level ideas and gets into how platforms actually need to change to support this new way of building. If you're thinking about how your tools, pipelines, or platforms will hold up in an agent-driven world, this is a perspective you don’t want to miss. Join us in London or online: tessl.io/devcon/ (use AIND-X-BB-20 for 20% discount)

Now your team can generate new pages without thinking about layouts or code. Prompt templates help preserve engineering decisions, Agent Runners makes them available for the rest of your team to apply. netlify.com/blog/how-to-en…

Then create a prompt template that exposes only the content variables: Campaign name: {{campaign_name}} Headline: {{headline}} Description: {{description}} CTA text: {{cta_text}} Slug: {{slug}} The structure stays consistent across every page.

Prompt templates work great for the work you do on repeat. Marketing pages are a good example: - event pages - beta signups - product pages Here’s how you can help your team reuse existing patterns ↓

What's next for Mattel? Leaning into AI to eliminate repetitive setup work, scaffolding, and common React patterns. Already aligning with Netlify AI Gateway, Agent Runners, and Observability. The infrastructure is stable. Now they build. Read the full story: netlify.com/customers/matt…

74 Netlify sites supporting global presence. ~70 active projects across brands and internal services. Zero emergency calls. That last one is the one Mark actually cares about.

500+ digital properties. Issues day and night. Every fix pulling in sysadmin, cloud admin, network admin, and DevOps. Mattel called it "death by a thousand cuts." Here's how they got out. 🧵

Hot take: most AI app builders are demo tools pretending to be platforms. Amazing start. Then you need auth, a database, an API proxy. And you're migrating. The migration IS the product decision. It's just disguised as a starting experience. netlify.com/blog/start-a-n…

You can also create your own prompt templates. Keep them private for your team's recurring workflows, or submit them to the Netlify community for everyone to use.

Skills tell agents how to use Netlify correctly. Prompt Templates combine them into ready-to-use patterns. Less time on setup. More time on what makes your app different. netlify.com/blog/better-ag…

Raise your hand if you've fought CORS errors at 2am trying to connect a frontend to an AI API. ✋ On Netlify: AI Gateway is already there. One endpoint. OpenAI, Anthropic, Gemini. Agent wires it up. The best feature is a problem that doesn't exist. ntl.fyi/46TbFce

SREs have been dreaming about self-healing systems for 20 years. The Google SRE book promised them. Scripting got us partway there. And now AI is getting there. So why does it feel like a threat? Dana Lawson, CTO at @Netlify, has a hypothesis: your career was built around being the one who holds reliability together. That identity is real. The fear that comes with letting go of it is real too. But here's what she doesn't let people off the hook on: LLMs are modeled off human brains. The pattern matching, the intuition, the ability to spot something wrong before you can explain why. That's yours. AI is trying to replicate it. Not replace it. "Look at coding agents as an extension of yourself. That's how you're going to have job security. But you've got to fight for it." Dana Lawson and @SylvainKalache , Head of Rootly AI Labs, get into why the pushback against AI in reliability is really about identity, and what it takes to come out ahead.