Private drinks with the private network. Join the @Speakeasydev and @Tailscale teams at a real life speakeasy. It's on the last day of @aiDotEngineer, we'll be chatting about privacy and security in the age of agents. Space is limited: luma.com/po85yuqq

Skills are a powerful primitive, but organizations have struggled to get a handle on them. Extending MCP to cover Skills is going to encourage more companies to manage skills as a 1st class artifact, and that's going to explode usage. With MCP there was enough friction in creating them that most employees wouldn't create their own. Not the case with skills, anyone can create a markdown file, so management has been highly dispersed. Not a single company we've worked with knew how many skills were in active use across their org (before implementing @speakeasydev ofc). That's not inherently a problem, but there's usually a lot of duplicate work being done. Once companies start bundling skills in their MCP servers they'll start spending more time curating them. Usage will go up without users even needing to be aware. Kudos to the committee for continuing to be great stewards of the protocol.

This is an exciting update for claw devotees who want to pitch this upwards to their IT and Security leaders. There's still a major gap though. Claws are long lived and proactive entities that will work and take action like employees. For humans you can go into @okta and authorise access to apps. How do you do this for long lived agents like openclaw? We've been cooking on an easy to use Agent Identity feature on the @speakeasydev control plane. I use the word "easy" because the Agent Identity space is filled with dozens of acronyms: Workloads, SPIFFE, WHIMSE, CXA, ID-JAG and more. We've made built on the state of the art protocols here to give users a simple workflow to register an agent (or discover it automatically) and grant it scoped and revocable permissions to various mcp servers and other tools. Every agent has its own identity and short live tokens rather than less secure shared access models like service accounts. For an IT admin though its just a few clicks or running a skill. I'm excited to see how many enterprises we can accelerate agent adoption in by solving the foundational building block of identity. A little more on how we've done that for Claude Tag. Open Claw next! 🦞speakeasy.com/blog/agent-ide…

SaaS as a category was always silly. It bundled systems of record like Slack or Jira with productivity apps like Miro or Canva. Agents have made this division clear... Systems of record are more important than ever, just look at MCP usage on the @speakeasydev gateway Productivity apps, not so much...

Nvidia pushes agent containment below the model, dv01 and Cognizant put agents into finance and claims workflows, and Google tests buying from Flipkart inside Gemini. Speakeasy adds tighter identity and policy controls for MCP.

I understand the rush for companies to adopt token-based pricing, but I can't help thinking that for most it will turn out to be a mistake in the long run for the simple reason that, 1 Claude token ≠ 1 DeepSeek token Different models use tokens in completely different ways. That doesn't matter if you build your product on a single model, but what happens when you change the underlying model? Are you going to switch all your billing? What if your product becomes multi-model? What if you allow users to BYOM? It gets complicated quickly. For most products, token-based pricing doesn't make sense because tokens are not tied to the economic value of the outcome the product is driving. I saw recently that @PostHog's self-driving feature charges $15/PR opened i.e. patches submitted. I think this is much more appropriate for the majority of AI-based products. Focus on the outcomes you are driving and price-in what it costs for you to accomplish it. The one place where token-based pricing does make sense is companies where the stream of tokens is the basis of the value. For example a model router company, or a company like @Speakeasydev where the greater % of the companies AI usage flowing through the platform, the more value the customer gets.

@MoonPay distributed AI to every employee without turning security into the bottleneck. Now they run 200+ MCP servers and 60,000+ agent sessions through one control plane. Great writeup from @AgenticAIFdn:

I am going to The @AIConference in SF next week. We may or may not be bringing drinks to the booth 🍸️ See you there!

Most of the @speakeasydev has been together for multiple years now through cycles of growth and PMF iteration. Longevity >> team size.

MoonPay moves funds between fiat and digital assets for 30M+ customers and 900+ partners. When employees started connecting AI assistants to internal systems through MCP, browser-level governance stopped being enough. Their security team went to market with clear requirements: full visibility into MCP usage, coverage across Claude, Codex, Cursor, and Gemini, and the ability to block unsanctioned MCP servers at the point of use. Everything had to work in production immediately. They evaluated Speakeasy, an AAIF member, on a 30-day POC with success criteria written up front, then rolled it out company-wide in a single deployment. Today: 200+ MCP servers under governance, 60,000+ agent sessions, 5,000+ brokered MCP connections. Full writeup: bit.ly/4AAkrcy

The cooking has not stopped

Have agents made it easier or harder to build software products? If I had to boil down the sentiment, I would say that MVP is easier than ever, PMF is harder than ever... There's no question that agents make it possible to go from idea to usable in a day, which was previously unheard of. The problem I'm seeing though is when it comes to PMF. Product creation is becoming infinite, but market is still finite. There's only so much buyer attention in the world. As the volume of product increases the competition for that finite market attention is becoming much higher. What are the implications? I think we'll see a correction to the spray and pray product development that is happening. Teams will need to build conviction over what is the most impactful thing they can build, build it to a high degree of polish and then really hammer their messaging with the market.

Don't want Harvey's +50% --> -50% margins drop!

To be clear this is our costs curve not our revenue curve 😅

All the @speakeasydev engineers are in SF this week for our engineering onsite. Humbling to be reminded how cracked this team is.