Huge TypeScript AI day today! Live from London 09.30-16.30: 9:40 - 9:55 AM: Opening Keynote → Sam Bhagwat, Shane Thomas, Abhi Aiyer, Co-Founders @ Mastra 10:00 - 10:15 AM: Evals Are the New TDD → RL Nabors, Developer Experience @ Arize 10:20 - 10:35 AM: Deploying AI Agents Where Your Customers Actually Want Them → Raphaël Titsworth-Morin, Senior Developer & Evangelist @ Defang 10:40 - 10:55 AM: What I Learned Shipping FGA to Production → Tiffany Lozenski, Founding Product Engineer @ Palette 11:30 - 11:50 AM: The CLI Is Dead, Long Live The CLI → Jan Peer Stöcklmair, Senior Software Engineer @ Sentry 11:55 - 12:15 PM: Agentic UX: How The AG-UI Protocol Is Redefining AI-Driven User Experience → Tyler Slaton, Founding Engineer & Head of Open Source @ CopilotKit 12:20 - 12:35 PM: Building an OpenSearch Research Agent at Scale → Alfonso Graziano, AI Tech Lead @ Nearform 1:45 - 2:00 PM: Why Monetizing Agents Needs Different Infrastructure → John Yeo, CTO @ Autumn → Charlie Lamb, Founding Engineer @ Autumn 2:05 - 2:25 PM: Even TS Agents Need Retrieval → Carly Richmond, Developer Advocate Lead @ Elastic 2:30 - 2:55 PM: From Magic to Harness: Building an AI Agent for a 25-Product SaaS Company → Ilyà Zayats, CTO @ Factorial 3:00 - 3:15 PM: Designing Zero Trust Harnesses → Ohans Emmanuel, Co-Founder @ Coldtea 3:20 - 3:35 PM: Building Cloud Coding Agents on Prisma Compute → Tyler Hogarth, Head of Engineering @ Prisma 3:40 - 3:55 PM: What We Learned Building Our Own Agent Harness → Danilo Delizia, AI Architect @ commercetools 4:00 - 4:20 PM: The Agentic Repository Automation Revolution → Don Syme, Principal Researcher @ GitHub Next 4:25 - 4:30 PM: Closing Remarks → Sam Bhagwat, Shane Thomas, Abhi Aiyer, Co-Founders @ Mastra

$2,500 prize pool Up to 35,000 Prisma Points 15 days left. 33.22K have joined the @Galxe Quest. The First 100 seats are won by scoring real robot data, and they're still open. Are you in?

AI coding agents like Claude Code, Codex, Copilot, and Cursor can access repos, invoke tools, and connect through MCP. Prisma AIRS AI Gateway and AI Runtime Security inspect these interactions inline to stop threats, protect code and secrets, and enforce policy before risk becomes impact. Secure AI from prompt to action.

fx v0.0.8 Embedding fx just got much faster. • NAPI initialization is over 40× faster • Smaller, more accurate shell tool with 75% fewer actions • TUI up to 19.6× faster, with first paint 74.6× faster • Common CLI commands 18–25% faster • 2.8% smaller binary (6.01mib vs 6.19mib) • Active turns can now be steered with Enter We've also documented MCP integrations with @calcom , @clerk, @knocklabs, @plainsupport, @prisma, @sentry, @Stagehanddev, @upstash

fx v0.0.6 • Better Auto mode (cheaper & faster) • Approval workflows up to 23% faster • Smaller macOS binary: 6.12mb (-0.26%) • Remote HTTP MCP support • More reliable Codex, Grok & MCP sign-ins • Many bug fixes We've also documented MCP integrations with @neondatabase, @supabase, @prisma, @usekernel & @browserbase. Thanks to @sachinadlakhaa, ackingyou & @mjlbach Full:

Last week, Verify Quality opened to the public. Start scoring real robot data now, the top 100 scorers become Founding Data Quality Validators 🦾 This week, The First 100 Validators campaign will go live, powered by @Galxe. $2,500 prize pool + up to 35,000 Prisma Points

Some have asked questions on $now which i'd say are more saas/ai rabbit hole. That's not the point i'm making here. This stock on par w $twlo and now below $okta on ev/sales. Yes, its deceled but its also $16 bl biz. $panw grew organic rev 14% last q and has blown out to like 30x sales. $crwd at 25% is in the stratosphere now. These wild multiple expansion moves have largely been driven by surface area/substrate bets ahead of agentic world and security concerns. This is where i take issue as some of names being rewarded have either made dubious strategic moves or pretty much telling a meh story. Like okta moves at the speed of human hr department and is totally the wrong architecutre for agentic. It's very hard to listen them talk about going into a client and being surprised that instead of 200 nhi they have 2000. You really think a sub-agent will be governed same way as a human; i don't? And have you done cyberark customer calls lately? I can tell you that if you have you are not going to be bouncing of the walls that PAM+ prisma solves everything let alone screaming the P word all the way to 40x rev. Now I definitely am not saying servicenow figured this shit out but today it looks like they spent the critical window crafting the actual substrate to transform the platform for an agentic world with real-time asset intelligence (Armis), the permission graph (Veza), and agent telemetry standard (Traceloop). Add in operational db to make this all work in real-time and you would think they would get some sort of surface area benefit of the doubt on the security/identity/goverance/risk side agentic. And they blew up the catalogue and went all in on packaging going forward so they are not selling u AI in so much as they are just saying they are evolving for u and this is how it will be consumed going fwd which btw is where everyone is gonna end up anyway. My 2c is so many of the names bid up recently gonna get so nuked and i think $now actually comes out far cleaner on the other side. That said this is a discounting exercise and all i'm arguing is right now this seems way off. They deserve way more of surface area/subtrate multiple then they are getting.