Real Alpha
Watch modeSubscribed

AI & I · 4 min · Aug 12, 2026

Agents need an open web of tools to become useful

Kevin Scott says model capabilities are outpacing products, while limited memory and access to tools hold agents back. Open protocols could connect agents to the internet’s existing sources and services.

Kevin Scott

Kevin Scott is CTO of Microsoft.

Chief technology officer at Microsoft, previously SVP of engineering and operations at LinkedIn and VP at AdMob.

  • Dan Shipper, Host · Co-founder & CEO, Every

    Sold his first startup, Firefly, to Pegasystems; writes Every's Chain of Thought.

About this segment

Kevin Scott says model capabilities are outpacing products, while limited memory and access to tools hold agents back. Open protocols could connect agents to the internet’s existing sources and services.

From “Microsoft’s Vision for an Internet Made for Agents With CTO Kevin Scott (Best of the Pod)”, Aug 12, 2026. Watch the full episode

Answers “Are AI agents ready for real work?” See all 44 answers

“You need like an ecosystem that looks a lot like the internet where if you have a source of information, you already have a website, you already have an API”
Kevin Scottat 4:48 · AI & I4:48

Takeaways

  1. Model capabilities are ahead of what products currently deliver.
  2. Limited memory makes it hard to delegate complex tasks.
  3. Open protocols can connect agents to existing websites and APIs.

In this episode

Full episode

  1. 2:10Agents need an open web of tools to become useful4:24

  2. 9:38Open agent ecosystems and strong security can coexist6:04Up next
  3. 15:36Stay open to new tools without giving up your craft5:21
  4. 3 more moments in the full episode

Transcript

From the transcript AI & I publishes with the episode.

  1. 2:14

    So what has changed? What have we learned from last year to this year? Yeah, I think there's a bunch of things that have changed. Like one of the things is that I think last year. people were like really in this state of mind that they were doubting that the scaling laws were going to continue to work really well. Whereas like I think, you know, we've demonstrated year after year after year that they are intact and working quite well.

  2. 2:41

    Like that's not a... thing that people need to be reminded of anymore. And I think the other thing, too, that's happened, honestly, is that the reasoning capabilities of the models has actually gotten a little bit ahead of what we're using the models to do in products. So I've been talking a lot lately about this thing called the capability overhang. And, you know, I think we actually have some work to do collectively across the whole industry to...

  3. 3:11

    close the gap between what the models are actually capable of and like what we're delivering to users of that capability. So that's one of the one of the like big thematic things why, you know, scaling laws might not be as interesting to talk about it this year's build as last. And then the other thing, too, is that we just discovered is all of these agents have emerged over the past year. And so like both the number of agents and like the amount of time that people are spending doing stuff inside of these agents or with these agents is that there's a bunch of other stuff other than reasoning that has to get sorted out in order to make them as useful as they should be.

  4. 3:47

    So, you know, the things that I was talking about earlier. at the keynote today at Build, we're, you know, we need better agentic memory like our agents right now because memory is constrained in a bunch of interesting ways. They're a little bit transactional. So like you use them for like one thing and like, you know, memory is coherent across the course of that task. But, you know, then it may or may not completely go away.

  5. 4:19

    And like you're starting from scratch the next time, which really is. inhibits your ability to delegate increasingly complicated tasks to these things. And then, like, there's just this real issue that, like, if agents are going to be useful, they have to take action on your behalf. Like, they have to be able to use tools and, like, make changes in systems and consult information sources that are, you know, diverse and rich.

  6. 4:47

    And in order for that to, like, really... be great. You need like an ecosystem that looks a lot like the internet where if you have a source of information, you already have a website, you already have an API that's doing something for people out there. Like you've got to figure out how to plumb things through where agents can like talk to those things and where, you know, all of the incentives are aligned for everyone to like go, have all of this stuff participating in, you know, ways that make sense to them in this agentic web.

  7. 5:25

    And so I think that is the big story this year. It's like you've seen the first glimmers of like real progress with like super awesome, simple open protocols like MCP that are, you know, serving the same purpose in this agentic web as HTTP does on the internet and where you have things like NL web that are like serving, you know, the same moral equivalent purpose as HTML does on the internet. And so I think you're going to see these things like simple things that are composable and layering and like just lots of activity in the open community and like a bunch of things hopefully getting to ubiquity so that, agents can actually do stuff right so i think to play that back like one of the things i hear is like we have agents agents are starting to work and in order to make them powerful agents need access they need access to like what whatever is out on the internet whatever is on your computer all that kind of stuff yep and you need um basically protocols um and processes for agents to be able to access that stuff and so you're looking at different parts of the stack so like absolutely the runtime layer where where you're you know you're building like