This week on Dev Interrupted, Slack’s Chief Product Officer, Jaime DeLanghe, joins the show to explain why enterprise AI value depends on embedding custom bots directly into your existing team communication loops rather than deploying them inside isolated, single-player chat silos. She breaks down the platform's shift toward open ecosystem standards like the Model Context Protocol (MCP) and how dynamic UI frameworks are transforming standard channels into active execution environments. Jaime details the operational realities of managing autonomous software fleets, including a striking look at how leading companies are placing hundreds of custom agents directly onto their corporate org charts.
Show Notes
- Slackbot MCP Client:Learn more about connecting your tools to Slackbot via the Model Context Protocol at theSlack Blog.
- Slack Developer Hub:Start building your own agentic workflows and explore the latest tools atslack.dev
- Connect withJaime onLinkedIn
Transcript
(Disclaimer: may contain unintentionally confusing, inaccurate and/or amusing transcription errors)
[00:00:00] Andrew Zigler: Today's guest is Jamie DeLanghe, Executive Vice President and Chief Product Officer at Slack. And as our listeners know, I'm a total Slack nerd.
[00:00:13] Andrew Zigler: I spend a lot of my time in Slack building agents for my teammates, and I've formed a lot of opinions, especially over the last year, about what my workspace needs and what kind of
[00:00:24] Andrew Zigler: spice it needs to bring to the mix to make AI powerful. And in the last year, I, I've really had the privilege of being part, I guess, of the Salesforce cinematic universe and going to places like Dreamforce and TDX and getting really keyed in on how Slack and Salesforce are betting on the transformations they're making with their technology, their bets on where the work is actually happening, and Slack is center stage on that. Um, I've heard a lot of great panels and discussions at both of those events about the directions that Slack is going. So I too was like, you know, "Let's bet on this. Let's build on [00:01:00] this." And, uh, as part of learning more, you know, we had Kurtis Kemple from Slack on
[00:01:05] Andrew Zigler: our show, who even walked me through how he created some of his Slack agents, which was really exciting to dive into, and that was around the end of last year.
[00:01:14] Andrew Zigler: And since then, you know, I've launched a whole fleet of Slack a- agents for my teammates. I found a lot of success building on the things that Kurtis taught me. Uh, and I've also been so excited about how Slack is deepening its partnership with protocols and technology that are powering AI for everyone and helping all of us enact gains and find the best standards moving forward, so it's exciting to be part of that story. Uh, but center to all of this is how the Slack, the product, is evolving and changing and meeting the needs of knowledge workers now, and that's what I'm so excited to dig into, is some of that high level thinking, because here on Dev Interrupted, we love to get aligned about where all of the ships are going, because it's pretty stormy seas right now.
[00:01:58] Andrew Zigler: So Jamie, [00:02:00] welcome to Dev Interrupted. We're so excited to have you here.
[00:02:02] Jaime DeLanghe: Thank you. I'm so excited to be here. I feel like, uh, your intro just spiritually connected us in, like, a really deep way. I'm, I'm so excited to talk to you about everything that we're doing
[00:02:13] Andrew Zigler: Amazing. Well, now that we're best friends, we're gonna dive into a whole chat today, um, about how Slack is transforming. But, uh, obviously the opportunities that you've been exploring as a product leader,
[00:02:25] Jaime DeLanghe: Yeah
[00:02:26] Andrew Zigler: and what you see the, the AI, the powered world, the Slack world that we're operating in changing into.
[00:02:33] Andrew Zigler: Uh,
[00:02:34] Jaime DeLanghe: Yeah
[00:02:34] Andrew Zigler: to start with like what your vision is and the opportunities you see?
[00:02:38] Jaime DeLanghe: Yeah. So, uh, I feel like, you know, I'm, I'm Slack CPO now. I've been here, uh, for about eight and a half years. Um, I haven't been the CPO the whole time. I'm more recently the CPO. But when I think about the future of Slack, as somebody who's just been here for so long, it's impossible for me to not think about Slack's past and the things that [00:03:00] have always made Slack Slack.
[00:03:02] Jaime DeLanghe: Uh, made it the place where people love to work, made it the, you know, only piece of SaaS that, you know, people, like, really, like, fanboy over. And I want that to continue to be true as we all evolve how we're working. And so the things that come to my mind in terms of, like, what has Slack always been that it needs to keep being and maybe even get better at is, one, it's, it's the place that people want to work in.
[00:03:25] Jaime DeLanghe: It is human, it's friendly, it's fun, it, it works the way that people work. It's not trying to, like, put some rigid structure on top of how you get stuff done in your day, but it's gonna be helpful. It's gonna be there just in time to, like, help you get a little bit organized, um, maybe help you prioritize your work, help you and your team stay on task.
[00:03:46] Jaime DeLanghe: Um, Slack has also always been a platform, or for almost the whole time Slack has been around, it's been a platform. And, uh, we've had this strong belief that the more work you bring into Slack, the [00:04:00] better your workers' lives are gonna be. They're not gonna have to go into every single SaaS application to get stuff done.
[00:04:06] Jaime DeLanghe: Um, and the more people can look at information together in a channel or look at content together in a channel, um, the more aligned they're gonna be, the more they'll be able to move. And then finally, all this needs to be open by default. It all needs to be searchable. It all needs to be findable, so when a new hire starts on day one, they don't have an empty inbox.
[00:04:25] Jaime DeLanghe: They have, like, a whole bevy of channels to, like, dig back into, and they can basically get up to speed super fast 'cause they're just jumping into the conversation. But they're not missing the whole rest of the history. They have everything. So all these things have always been what Slack is, but now we got agents, right?
[00:04:42] Jaime DeLanghe: Like, we have LLMs that can come into the mix. And, A thing, a thing about me is that when I started at Slack, I worked in search and machine learning. So I had all of these, like, highfalutin ideas about how we were gonna turn all of that information in Slack and turn it into knowledge, and we were gonna make, like, Slack the smartest [00:05:00] application.
[00:05:00] Jaime DeLanghe: It was gonna be, like, super assistive. Um, and we can actually do that now. Like, we can do that. Slack can do that itself with Slackbot. But more than that, we can be an engine that kind of helps every developer, um, no matter who they are, do that for themselves, for their companies. And so when I think about the future of Slack, it's really extending that original vision of being the place where all of your people, your applications, um, your information come together in channels to keep everybody aligned and moving forward in the right direction.
[00:05:29] Jaime DeLanghe: And extending that to agents and making sure that Slack is the best place for humans and agents to collaborate. And making sure that that human and agent collaboration stays human at its core, and that we have the same kind of flexibility to work in the ways that make sense to us. That we're not being pulled into, like, uh, isolated AI chambers where we can only work with robots, and then we have human spaces where we can work with human spaces.
[00:05:54] Jaime DeLanghe: I think these, these spaces need to blend a lot. And with agents, it also means we can pull [00:06:00] in a lot more work. Like, we used to say that Slack is like, you can pull in the thin work that's just really fast. Like web forms, web hooks. Turns out those were super powerful, right? But now you can do so much more.
[00:06:11] Jaime DeLanghe: Like, you can paint graphs inside of Slack. You could maybe even like, you know, review code inside of Slack. You could completely build your whole website from inside of Slack, and that's what agents allow for. And I think as I think about what are we gonna build toward, it's continuing to build that environment and that ecosystem that really makes the interaction patterns powerful and delightful.
[00:06:36] Jaime DeLanghe: And thinking always about the team and how the team gets work done, not just about, uh, an individual person. So I think, you know, Slack needs to evolve to make humans and agents work together super well, make it the best place to develop your agents, deploy your agents. Slackbot can be sort of a super orchestrator over all of that in so many ways.
[00:06:57] Jaime DeLanghe: And then we just need to keep making the experience dead [00:07:00] simple and delightful, um, so that people wanna stay there.
[00:07:03] Andrew Zigler: Exactly. Dead simple and delightful, and the way that it has to transform to meet the individual needs of the, of the worker and what's important to them in the organization in general. What's really exciting is, you know, this vision that you see for Slack is this, like, context world, this, this equal plane operator where agents and humans can work together and have the views and the outputs that they need to get their work done.
[00:07:29] Andrew Zigler: Really what it exposes is that, um, much like engineering and the, and the ways that we solve code generation and delivery at
[00:07:37] Andrew Zigler: scale with AI agents, almost that same thing's happening with our knowledge work. And the sooner and, more clearly that we have understandings about where are those loops within our org, what are the windows we need to have into these loops, and these become channels.
[00:07:53] Andrew Zigler: You're, like, punching holes into your organization to see where these agents are working, and Slack becomes where you're [00:08:00] peering in to, to do that work. And then, you know, there's some stuff in there that we're gonna touch on a little later when we talk about MCP and protocols and,
[00:08:07] Andrew Zigler: and stuff because then obviously you can bring the whole world into Slack now because everything can get bridged into AI conversations.
[00:08:16] Andrew Zigler: AI conversations can take advantage of MCP, which can have apps embedded in them. Now
[00:08:20] Jaime DeLanghe: Totally
[00:08:21] Andrew Zigler: natural language and conversations that are happening into live rendered things. Like you said, you can drive any kind of process that you need from there. So then we arrive at a responsibility for a lot of leaders, uh, both non-technical and technical leaders, product leaders, engineering leaders, everyone alike, to think about how are we gonna engineer the harness of our context world, of our Slack world, of our communication world, because now that we've acknowledged that, oh, this too is a bunch of loops and a bunch of checks and gates and guards and context that goes in and out, how are we going to build it?
[00:08:58] Andrew Zigler: And what I've found is [00:09:00] that Slack becomes the building block to ex- not
[00:09:02] Andrew Zigler: only start building it, but express it really quickly, uh,
[00:09:05] Jaime DeLanghe: Yeah
[00:09:05] Andrew Zigler: its superpower, I think. And that's like it's in a, in a lane of its own in terms of where you can take it
[00:09:12] Jaime DeLanghe: Totally. I mean, I think like, um, Stewart Butterfield used to call channels, uh, they were digital containers for arbitrary objects. Uh, which sounds like, you know, that's kinda nonsense. Uh, but exactly that, right? Like, you can... Y- the-- one of the toughest things when you're building an agent is how do you figure out the context layer?
[00:09:32] Jaime DeLanghe: How do you, like, build up your knowledge graph that's gonna power this thing? How do you keep it up to date? And one of the coolest things about Slack is it has just enough structure for you to be able to like, point at, like, a project or point at a topic, but not so much structure that you're having to stitch together a bunch of different things.
[00:09:52] Jaime DeLanghe: And the conversation itself actually ends up being, like, the richest context for you to be [00:10:00] able to action off of any of, like, I don't know, the meatier things like a slide deck or even, like, a PR. Like, y- you-- the more you know about what happened around it, the, the smarter your agents can be
[00:10:13] Andrew Zigler: Yeah, you're like scattering all these artifacts, and they
[00:10:15] Jaime DeLanghe: Yeah
[00:10:16] Andrew Zigler: the roads, something needs to lead back to Slack. It all comes down to good, healthy reporting, information going into Slack, co- communications happening in Slack, and correctly labeled semantic channels that are open and not siloed. You know, good communication practices we should all be having as organizations in general, because it turns out
[00:10:32] Jaime DeLanghe: It
[00:10:32] Andrew Zigler: AI
[00:10:33] Jaime DeLanghe: out that works for agents too.
[00:10:34] Andrew Zigler: the bad.
[00:10:35] Andrew Zigler: Yeah, exactly. And so, and, uh, you know, before we dive into some of the more exciting, like, technology and product changes that are powering the ability to do all of that, I do wanna ask 'cause I'm curious from a practitioner standpoint.
[00:10:47] Jaime DeLanghe: Mm-hmm.
[00:10:47] Andrew Zigler: know, the, the barrier that gets crossed from when you're, like, doing the single player AI experience to the multiplayer one experience, it becomes profoundly more complex in terms of how you deal with the interactions.
[00:10:58] Andrew Zigler: That's something that I've learned [00:11:00] just building with them. Uh, but also too, just as like, uh, someone interested in the space. Uh, uh, two years ago, I gave a talk at BSides Barcelona about multiplayer AI and how you could use AI chat conversations to basically hack your coworkers' context. Like, this is an understanding that we need to have as folks that are operating in this space together. So like, how, how do you think about a, as a product leader about securing that kind of space and making sure too that it's like, uh, going to scale for the needs of all of your users that have a huge range of sensitivities for their topics?
[00:11:34] Jaime DeLanghe: Yeah, I think it's really, it's really interesting. We're-- It's, it's a topic that we're continuously grappling with. I think one of the, one of the benefits we have here is channels. And so, um, channels are, not only a digital container for arbitrary objects, but they're also an, uh, ACL, basically. And so you can kind of make a pretty good assumption that whatever is pushed into the [00:12:00] channel, if an agent has access to that and the people have access to that, that's a fine...
[00:12:04] Jaime DeLanghe: We're all happy. That's a happy universe. It gets a little bit more challenging when then that agent gets access to tools, and it's not just looking at the content that you put inside of Slack, but it's looking into some third-party system. And where we are at right now with that is really allowing for configurability for whatever use case makes sense.
[00:12:26] Jaime DeLanghe: So in some cases, it might make sense to have an agent have fully its own identity and have that identity-- like it has its own account in whatever tools it's having access to. It may also make sense for it to be an OAuth, where it's passing through your identity and whoever's talking to the agent, now the agent's acting on that person's behalf.
[00:12:47] Jaime DeLanghe: It may make sense to throw up a modal or a, modal, but like a, a radio buttons or something to be like, "Do you wanna do this as yourself, or do you want me to do it as me?" Like, to just like explicitly ask the user. I think [00:13:00] what it's become imminently clear to me as we dig into this more is it's really difficult to make a rule that fits everything.
[00:13:09] Jaime DeLanghe: Like, everybody's going to have, like you said, a different level of sensitivity. Everyone is gonna have a different use case and configurability. Um, and even just con-- even that idea of like on-the-fly configurability, I think could be really powerful so that we're fitting the, the configuration to the use case and letting the people who are closest to the work actually make that decision.
[00:13:33] Jaime DeLanghe: A-and I think then it's just about helping people understand the implications of those decisions, whether it's on the developer side or the admin side or the end user side, um, 'cause there's trade-offs. There's no perfect answer for what that looks like, um, until, you know, the agents get so smart that they know what's secret and what's not, but I don't trust them yet.
[00:13:53] Andrew Zigler: I don't trust them quite yet. No, you're,
[00:13:55] Jaime DeLanghe: I don't trust them yet.
[00:13:56] Andrew Zigler: you're hit- you're hitting on an ex- exactly kind of how I... [00:14:00] When we've talked with other leaders about how they think about the security planes, the world within their space, how they, uh, think about it too, it has to be deeply configurable just as much as it has the, the, you know, the needs of your, of your end users are on a wide range of sensitivity.
[00:14:13] Andrew Zigler: Your configs need to expose to that and meet to that level. Uh, but another thing too that we, you know, learned recently, we had Tanya Janca, who was OWASP Ha- Hacker of the Year last year, and she helped put together the OWASP top 10, vulnerabilities for 2026, and the top one was, like, vibe coding and developers themselves.
[00:14:32] Andrew Zigler: Like, people, people have become the biggest vulnerability, which is why, like, I think it's important for people to double down on using places like Slack and using, like, user management and control plane surfaces, like what's offered in like the supporting Salesforce universe, to really understand and identify all of the movers within your system and what they have
[00:14:53] Andrew Zigler: access to, and being able to scale it up and down with the levels of, like, sensitivity that you need.
[00:14:58] Andrew Zigler: And, you know, I [00:15:00] think it's really easy to like, you know, roll your eyes. Oh, for some people, like, just to not necessarily want to double down on that, but it's like ultimately if, like, your workflows are just logs on a machine somewhere, they're like so sensitive in
[00:15:12] Jaime DeLanghe: Totally
[00:15:13] Andrew Zigler: of work going in and the outputs.
[00:15:14] Andrew Zigler: Whereas if it's like siloed away in a specific kind of like channel, a chamber for that particular purpose, you can understand and audit its usage. You can
[00:15:24] Jaime DeLanghe: Totally.
[00:15:25] Andrew Zigler: little bit better and,
[00:15:26] Jaime DeLanghe: Yeah
[00:15:27] Andrew Zigler: that's like the kind of control plane that I
[00:15:29] Andrew Zigler: think knowledge
[00:15:30] Jaime DeLanghe: I think we've also been, I, we, think about it at like a administrator level. So like, you know, more fine grain provisioning for agents, being able to say like, these agents can only be operated by these people. Potentially getting to a place where we say, these agents can only operate in these channels.
[00:15:46] Jaime DeLanghe: This is an allow list for the, the channels that this agent can be in. That's something that an admin could set. But the thing that I think we haven't yet quite figured out is like a lot of the people are not gonna be [00:16:00] admins. The builder also needs some visibility into this, and as the bar, like the barrier to entry on building is so much lower, like we need-- the, the builder should be able to do that.
[00:16:11] Jaime DeLanghe: And we should make the builder as close to the business owner as possible so that the business owner could also know that. And ideally, maybe they can't build the agent themselves, but they could troubleshoot it. Like they could push it in the right direction and see where it's going wrong. And I think this is, it's something we've gotta figure out for any-- bo-both agents and, and things like skills.
[00:16:33] Jaime DeLanghe: Any-anything that you can pass around and is getting leveraged multiple, in multiple places. Like having that kind of observability so that you can inflect on what you've built is, it, it's really important. And, also figuring out how to make that understandable because, you know, this isn't, it's not just software.
[00:16:53] Jaime DeLanghe: It's not like there's a bug. I wrote the if statement inverted or something, and now the whole thing [00:17:00] went kerflooey. It's like much more nuanced and helping people, maybe even with other agents, figure out how to inflect on their agent to make it better. I think... I don't know what it is yet, but I feel like there's definitely a role Slack can play in, in making that world work better.
[00:17:17] Andrew Zigler: Yeah, I'm even thinking now about how Slack can help organization leaders identify and highlight and elevate these AI unlocks that do
[00:17:27] Jaime DeLanghe: Exactly
[00:17:28] Andrew Zigler: really siloed basis on, like, a team per team le- base level. And then, like what you said as well, you get a level of skill sharing that becomes really important.
[00:17:36] Andrew Zigler: Slack becomes a really great almost, like, skills ecosystem with
[00:17:39] Jaime DeLanghe: Yeah.
[00:17:40] Andrew Zigler: that it can plug in. So,
[00:17:42] Jaime DeLanghe: Absolutely
[00:17:42] Andrew Zigler: skill, Skills themselves, an open standard, one that AI users around the world are just, like, really strongly embracing. A- another one as well is MCP. And
[00:17:52] Jaime DeLanghe: Absolutely
[00:17:52] Andrew Zigler: course, like, a, a, been a little bit of, like, a news hype darling child.
[00:17:57] Andrew Zigler: It has been the coolest thing ever. It has been dead. It [00:18:00] has been brought back to life. It
[00:18:01] Jaime DeLanghe: Yeah
[00:18:02] Andrew Zigler: really, uh, mislabeled, relabeled. Bets have been taken on and off the table. And along the way, I think MCPs totally had an identity crisis, but the one thing along the way that it did better than anything else was distribution.
[00:18:15] Andrew Zigler: It could get a lot of really good stuff really cleanly in a lot of people's hands in a really scalable way, which, hey, guess what? Is perfect for AI rollouts, AI enablements. Now folks are embracing Skills over MCP, has a new working group with the Linux Foundation. I'm like, "Can that spec please just hit the, uh, MCP protocol already?"
[00:18:33] Jaime DeLanghe: Yeah.
[00:18:34] Andrew Zigler: locked in, right, on how these protocols are
[00:18:36] Jaime DeLanghe: Yeah
[00:18:36] Andrew Zigler: the future. So, you know, how is Slack also playing in that space? And you're bringing things like MCP into Slack. What is it, what has it been like to watch those technologies unfold, but then also to participate as, like, a, a builder, a contributor?
[00:18:48] Jaime DeLanghe: Well, I think one of the things that's very, um... We have the great fortune at Slack of having such a strong developer community and such a strong partner community. [00:19:00] So I, I think like for pretty much anybody who's really building agents in the ecosystem is thinking about building them in Slack. Like, our partners are incredible.
[00:19:13] Jaime DeLanghe: Uh, the individual developers at our companies are incredible, and they're all telling us what they need from us. And the move to MCP was pushed in a lot of ways by the community telling us that it's what they needed. That's when the MC- like the MCP server came out because we saw the community trying to do a lot of things with our APIs that they weren't designed for, that felt, to us, unsecure and uncomfortable, and we were like, "We gotta figure out how to meet this demand, but we've gotta do it safely."
[00:19:41] Jaime DeLanghe: And that was our first move to MCP on the server side. On the client side, um, we really started to play with things internally. You know, we built Slackbot ourselves. Uh, we started connecting our own MCP to it. I think originally we had this [00:20:00] idea that we would only have a limited set of partners for MCP because we weren't totally sure on what the level of adoption was gonna be, and we weren't totally sure on what the level of sophistication of that adoption was gonna be.
[00:20:13] Jaime DeLanghe: Like, are people gonna just publish junk to this and degrade the experience of the agent to such a degree that like it's not, it's not really usable anymore? Um, and we, we kinda solved for that by allowing our own MCP ecosystem to grow internally and like we're, we're not, you know, we're not Luddites. We understand how to build technology.
[00:20:34] Jaime DeLanghe: But we did have MCPs of varying quality, and that allowed us to understand that like this is-- we're, we're gonna be okay with this. We can do it. We can have good tool selection. We can have good logic around the tool selection. Um, and leveraging MCP is gonna give us a lot more power than trying to roll our own tools for every single thing that we might want it to do or trying to figure out, a more robust like agent-to-agent protocol.
[00:20:58] Jaime DeLanghe: I think this will get us a lo- [00:21:00] there a lot faster and provide a lot more flexibility. I'd also say like highest level I want anybody who is thinking about building for agents to be able to build for Slack. And I also wanna thank anybody, anybody who's thinking about building agents to be able to easily put those things into Slack.
[00:21:19] Jaime DeLanghe: And that means that we have to have open standards, not Slack specific standards. So, you know, I don't think, I don't think MCP is gonna solve everything for everybody, and I am, like you, very interested in skills over MCP. I think we should get that as soon as humanly possible. Uh, 'cause they'd actually just make skills and, skills and MCP go together like peanut butter and jelly.
[00:21:39] Jaime DeLanghe: Like you
[00:21:39] Andrew Zigler: Okay,
[00:21:40] Jaime DeLanghe: need, both of them.
[00:21:40] Andrew Zigler: we're all literally the same page. Yeah, okay, great
[00:21:43] Jaime DeLanghe: Yeah. Uh, so I, I agree with that. I also think like, you know, there are places inside of Slack where we're playing around with, uh, A2A. Salesforce is betting on A2A. We're, we're, we're, we're testing a bunch of different things 'cause we don't know, we don't know where this whole [00:22:00] thing is gonna go.
[00:22:00] Jaime DeLanghe: So, um, I think it's-- being tinkerers is really helpful here, and then having the, you know, having our ear to the thousands of other tinkerers out there who are trying to get their stuff inside of Slack, I think our, our ecosystem pulls us in the right direction a lot of the time.
[00:22:18] Andrew Zigler: Yeah. So here's, here's this, the playbook that I'm hearing then, is that, you know, you're s- standardizing early because it's less expensive to standardize early, but obviously keeping a very open ear and open conversation with all of the tinkerers abound internal and externally to, like, really go through, like, what works and what doesn't work.
[00:22:38] Andrew Zigler: And that requires obviously, like, a, a good engineering practice, a good reflection practice, a good ability to, like, uh, highlight things that are working or figure out, like, why is this not working. Uh, but also too, uh, when you, you know, bring everyone together to work on that unified problem and you give it a, a label, then it gives you an opportunity, too, to be such an early [00:23:00] influence on where
[00:23:01] Jaime DeLanghe: Totally.
[00:23:02] Andrew Zigler: can go.
[00:23:02] Andrew Zigler: And
[00:23:03] Jaime DeLanghe: Yeah
[00:23:03] Andrew Zigler: one that I think anybody who's building in the spaces that, like, we are, where we're building things that are connectors and highways of information for other tools, MCP is absolutely going to be critical for business success, for product success, just for the technology to be, like, safe and scalable. So acknowledging that and knowing that MCP has to be, like, center stage, you know, it's important to partner up with those protocols early. And this is something that, uh, like, I learned and got, like, a really good deep dive from when we had, we had Tyson Singer. He's
[00:23:33] Andrew Zigler: from Spotify Pack- Backstage, and really the kind of person behind, like, the IDP portal.
[00:23:38] Andrew Zigler: And what's always been, uh, so fascinating to me about that product is that, like, that's not what Spotify set out to do. Like, why do they have this, like, first in class IDP, and they set the standard, and everyone just uses Backstage 'cause it's awesome, right? But it's like, one way I really dug into his, this story and he told me how, you know, when they were early in figuring out what their IDP was gonna look like, it was more [00:24:00] strategically and financially and long-term s- smart for them to just, like, set the standard, make the standard, go with the standard because it was so early in the play, because switching, switching later would be so expensive.
[00:24:13] Andrew Zigler: But he was saying, too, in that same conversation that he was like, "But if there would have been something really great to latch onto that solved that problem, like, that's what we would have built around because that's what we're optimizing for." And so that's why MCP is now. I see that for a lot of big orgs and enterprises.
[00:24:27] Andrew Zigler: They're building MCP-like things into their product and their bets about where things might go. But ultimately, we're all still just, like, one prompt away from doing, like, the full changeover when everyone else gets on board with, uh... Because, I mean, that's how we engineer these days, when everyone gets
[00:24:42] Jaime DeLanghe: Absolutely
[00:24:42] Andrew Zigler: um, with where things have gotta go.
[00:24:45] Andrew Zigler: And, uh, I'm just curious, like, from, like, a practitioner standpoint, um, I, I've recently been appointed as, like, an, uh, a- agentic AI foundation ambassador, and MCP protocol is, like, one of the library of projects within it that, you know, I've been kinda tasked [00:25:00] with learning more and evangelizing, and so I've been going deep in the MCP world.
[00:25:04] Andrew Zigler: Like, have you, uh, in Slack engineers and product, like, partnered with the development of MCP as a protocol, or do you have plans to do that? And, like, what's that look like as an ecosystem participant for you?
[00:25:15] Jaime DeLanghe: That's, that is a really good question. Um, I think MCP, uh, is one of the areas where we're trying to figure out, um, exactly how far we can, uh, go with MCP. And, you know, I honestly am not... I should, I should know the answer to whether or not we're contributing to MCP. Um, but I don't know off the top of my head.
[00:25:41] Jaime DeLanghe: I know we're...
[00:25:41] Andrew Zigler: are in some capacity.
[00:25:42] Jaime DeLanghe: Exactly. I
[00:25:44] Andrew Zigler: if no, of course, I'm not saying like, you know,
[00:25:46] Jaime DeLanghe: No, I
[00:25:46] Andrew Zigler: in the, is
[00:25:47] Andrew Zigler: Slack in the minutes
[00:25:48] Jaime DeLanghe: was,
[00:25:49] Andrew Zigler: channel working group or whatever the case may be. But the
[00:25:52] Jaime DeLanghe: Yeah
[00:25:52] Andrew Zigler: that the answer is yes because of the ecosystem participation that you bring forward.
[00:25:57] Andrew Zigler: I think that's the most vital thing. That's what I'm
[00:25:59] Andrew Zigler: always
[00:25:59] Jaime DeLanghe: and then [00:26:00] it's also figuring out how MCP fits into the existing ecosystem that we've built and how MCP really can be a complement to the Slack platform and not like-- So, so developers who are already invested in our platform don't totally have to pivot. They can invest in MCP and have that be a part of their story and not the whole story.
[00:26:23] Jaime DeLanghe: Um, we've also thought about that from our own, um, sort of how are we going to allow for... I'll give you the example, like how are we gonna allow for UI to be built inside of Slack? Um, there was a moment, I would say like six months ago, where we were having a debate about whether or not we should k-keep investing in Block Kit at all.
[00:26:40] Jaime DeLanghe: Um, and we had a group of people get together,
[00:26:44] Andrew Zigler: But I
[00:26:45] Jaime DeLanghe: and
[00:26:45] Andrew Zigler: getting, I'm getting kind of invested in this conversation already
[00:26:48] Jaime DeLanghe: we, we had a group of people get together from the platform team, from the user experience team, from the front end engineering team, and they came up with a solution set that was basically, you see this out, [00:27:00] it's out live now. But like see-- you can see that Block Kit supports many more dynamic kinds of blocks.
[00:27:05] Jaime DeLanghe: We also have the ability for Block Kit-- We're working on making Block Kit a great translation layer for MCP UI as well. And so Block Kit is not... Block Kit still exists. Block Kit is still a really import-important, robust part of the developer story inside of Slack. But we have changed what Block Kit means in a lot of ways by allowing for much more flexibility inside of Block Kit.
[00:27:30] Jaime DeLanghe: And I think, you know, similarly, the message, message, uh, stream inside of Slack is gonna continue to be the main carrier of information in and out of Slack. But we're gonna have to really change what can go in those messages, and Block Kit is a really important part of that story. Um, but we may also find that we need to have other kinds of things inside of Slack.
[00:27:54] Jaime DeLanghe: We may need to start building more just-in-time UI affordances. We may, you know, we, we just [00:28:00] recently launched like a better markdown viewer. I know that's very simple, but like having more ways of being able to do the kinds of things that people need to do at work now that are fully supported by the platform and don't feel kind of hacked on, um, but extend the platform in a natural way instead of saying like, "You know what?
[00:28:18] Jaime DeLanghe: Forget the Slack platform. Everything is all MCP all day." So we're, we're, we're, we're sort of like, I, I think constantly thinking about how can we get the best out of each kind of technology.
[00:28:28] Andrew Zigler: Exactly. It's acknowledging that MCP's, you know, one piece of the
[00:28:32] Jaime DeLanghe: Yeah
[00:28:33] Andrew Zigler: of things and things to explore. There's actually so much, like, fog of war, so much greenfield, so much stuff that we haven't seen or figured
[00:28:41] Jaime DeLanghe: Yeah
[00:28:41] Andrew Zigler: like, all it takes is a curious spirit to play around with some of these primitives and the new things that are available to start finding new ways of working.
[00:28:48] Andrew Zigler: Like, that story you just told about Block Kit's, like, new identity, its transformation as almost like an agentic expression layer
[00:28:55] Andrew Zigler: is critical because MCP is only as good as the presentation [00:29:00] in which it can then serve it up to all of its users, which in the Slack universe is gonna be, like, largely non-technical in a lot of cases.
[00:29:07] Andrew Zigler: And so how do you make that really fluent? Of course, use the UX that they already know and are familiar with. Don't try to pigeonhole them into
[00:29:15] Jaime DeLanghe: Troubling
[00:29:17] Andrew Zigler: You know, anybody who's tried to drag anybody into the terminal in the last six months has found that not to be enjoyable, and XTools takes way too long to install.
[00:29:26] Andrew Zigler: But all of that aside, it's like it really, uh, like, calls out that things that we are taking for granted and we already have are gonna transform, and maybe it's just something you're s- you... It's sitting over here, and it needs a, a working group, like in your case, to, like, reevaluate. Uh, in other cases, it's gonna evolve on its own, but we all have to just keep our eyes open to that. And the most important thing I'll say there, this is m- what excites me as, like, a practitioner, even, like, a researcher in the space, is that all of this is stuff that you can be experimenting with, and building new workflows for, and taking [00:30:00] notes about, and really just, like, understanding what, how do I operate and orchestrate this context?
[00:30:04] Andrew Zigler: And there's actually just so much to write about and share and study and discover. So it's never been more exciting to be a knowledge worker because, like, the way that we're reinventing work exists. And what happens is Slack becomes your workbench. Like,
[00:30:19] Andrew Zigler: as, as much as it is, like, your communication place, it's the place where you go to, to drive, uh, your impact at scale, uh, which is, like, what becomes really exciting about where it all goes.
[00:30:29] Jaime DeLanghe: Yeah, I mean, I feel like even, even like the folks who you would think like, I mean, they've got the best audience, they've got the biggest, most dedicated users. I feel like we f- hear from our partners, they put it inside of Slack, and then it just goes. I mean, I think like I don't, I don't wanna get too grandiose, but in some ways, for the companies that use Slack, like Slack is basically acting like it's doing what Google did [00:31:00] for the internet for their agents.
[00:31:02] Jaime DeLanghe: Like it's making their agents discoverable. It's ma- giving their au- agents an audience. It gives their agents backlinks.
[00:31:09] Andrew Zigler: own
[00:31:09] Jaime DeLanghe: They can get...
[00:31:10] Andrew Zigler: It's their
[00:31:11] Jaime DeLanghe: Exactly.
[00:31:12] Andrew Zigler: Everyone was freaking out earlier this year about the moltbook thing, and now no one talks about moltbook because it was
[00:31:16] Jaime DeLanghe: Yeah.
[00:31:17] Andrew Zigler: But no, really, that's like the reality of like what you're describing is like, yeah, it becomes the stage, it becomes the marketplace, it becomes like the, the public exchange of those agents
[00:31:26] Jaime DeLanghe: Exactly
[00:31:27] Andrew Zigler: It's al- that messy context is always gonna live in Slack, and you can try as you may to come in there with a crowbar and get it all
[00:31:34] Jaime DeLanghe: Crank it up
[00:31:35] Andrew Zigler: containers and transform it and do an ETL thing. And then like what are you even doing at that point? Bring the agent into that world with you. That's the whole power of it being a natural language, you know, thing.
[00:31:47] Jaime DeLanghe: Yeah. And I mean, I think if you do that too, the thing that you get is you don't risk sort of cutting off your data source to feed your thing. I think like, the thing I [00:32:00] think about a lot is if we move too much of that, like rich, messy interaction, like if, if too many people start to try to like neatify it and congest it and be like, "Okay, I've got this little Slack nugget.
[00:32:12] Jaime DeLanghe: I'm only gonna interact with Slack in nugget form over here in my terminal," nobody is-- Who's gonna make the, the, the, the messy stuff? Like, and, and I think like, you know, as good as agents are, they are also not gonna do the kind of, you know, human collaboration, the kind of like, you know, butting heads productively when you need to.
[00:32:37] Jaime DeLanghe: Like, they're not gonna tell you you're wrong and fight with you. if they do, it's because you told them to, you know? Like I, I think like our-- the agents will only be as good as we are as humans 'cause they need, they need our exhaust to kind of learn and get better, at least at this point.
[00:32:55] Jaime DeLanghe: Um, and Slack is a really good way to ensure that that loop keeps [00:33:00] happening for you.
[00:33:01] Andrew Zigler: So, uh, you know, as we've talked a little bit about, like, the vision, about the product, and how we've partnered, uh, with, like, this, these kinds of technologies and then brought them closer into the Slack world because that's the kind of tooling that we need to work with this context. You know, a lot of this is, like, prototyping and, and experimenting, and even I was mentioning a second ago about, like, there's just so much to learn and do. And, uh, something that we really focus on here on Dev Interrupted, too, is focusing on, like, that day two reality of, like, stepping into production, of taking it to the finish line, of otherwise delivering it in, like, a durable and secure and safe state. And so with Slack, that's a tall order. For all of the r- things that we've talked about before, just because any type of context could be living inside of it.
[00:33:43] Andrew Zigler: And before it was just people talking to each other, but now it's people and their agents talking to each other,
[00:33:47] Jaime DeLanghe: Yeah
[00:33:48] Andrew Zigler: giving humans dashboards and interfaces, humans giving agents commands. Maybe somewhere in a channel somewhere, two agents talking to each other, and they just need to get
[00:33:56] Jaime DeLanghe: Absolutely
[00:33:57] Andrew Zigler: knows? It can be just completely [00:34:00] chaos. And so, like, I, I'm curious to think about how, like, you as a product leader, how do you p- prevent the already very complex world of Slack from just becoming this, like, uh, uncontrollable mental monster for your admins?
[00:34:14] Jaime DeLanghe: So I, I think I've got, I've got two answers for you here. One is we just really, really need to increase our observability. Um, like I, it just-- we, we just re-launched over 40 new metrics for Slackbot. We need to extend that to the whole ecosystem. Like Slack should be the best place for you to not only deploy agents, but to understand how your agents are doing, how your agents are impacting your team, how your agents are driving business outcomes.
[00:34:42] Jaime DeLanghe: we also really need to continue to invest in our guardrails. Um, so we have like confidential channels that are not AI indexed. We need to continue-- we need to expand that out. But I think we also need to start really thinking about the primitives here. Like you've got people, you've got data, you've [00:35:00] got systems.
[00:35:01] Jaime DeLanghe: And I think we've, for a long time, at Slack kind of gotten away with having guardrails that mush those two things together, or like two of those three things together in different ways. And we don't really allow you to control your data flow as much as I think we, we need to get to. We also don't allow you to control your people and data context together in the same ways I think we need to.
[00:35:22] Jaime DeLanghe: So we're, we're thinking about new channel types. We're thinking about new kinds of provisioning. We're thinking about more auditability. Um, but one of the things that already exists that is really incredible, um, and kind of like a side effect, uh, of all these things being in Slack and working in channels is that, you know, for a lot of companies, there have been a lot of challenges about having a lot of your information inside of Slack for a very long time.
[00:35:48] Jaime DeLanghe: You got a lot of people, humans are messy, and if you're a company like the size of Salesforce with seventy thousand employees, eighty thousand employees, something like that, you know, or an even larger-- we have even larger customers than that, [00:36:00] you're basically running like a social network inside of a company.
[00:36:03] Jaime DeLanghe: There's a ton of stuff happening that, you know, could be good, could be bad. Um, and so we've added a lot of guardrails already. So, um, because agents are talking over the same protocol that humans are talking over, you get a lot of that stuff for free. So you can have DLP inside of Slack. Uh, you could-- so you can set rules and say like, if somebody tries to give, uh, my agent a credit card number and back, like out some data and do some internal hacking, that's gonna be a problem.
[00:36:32] Jaime DeLanghe: Um, we have things like anomaly detection. So if there's some weird behavior inside of your application happening, maybe people are switching channels and scrolling back and switching channels and scrolling back, and maybe that's actually not a person, but you know, uh, somebody has taken over someone's laptop.
[00:36:48] Jaime DeLanghe: You can imagine the same kind of thing for agents where we can say like, this is, this is like malicious agent behavior. We think this is not what you want here. Um, also, you know, being able to have things [00:37:00] like legal holds and like strong auditability and EKM. I think for a lot of people who are rolling their own agent UI, they don't-- they're not thinking about that stuff.
[00:37:12] Jaime DeLanghe: Um, or if they are, uh, it's not their primary, like it's not their primary thing. And so I think we've, we've got through a lot of the At least like the baseline fundamentals of security and compliance and trust in Slack. And trust is our number one value at Salesforce, so we're constantly kind of like, "Okay, what do we need to do next?
[00:37:33] Jaime DeLanghe: What do we need to do next?" Um, but as we evolve it, it's really becoming clear to me that eyes in, like to what's happening is really, really critical, and then the ability to action on that when you see something. So, um, for those really large companies, we've also seen that it's, it's really challenging to manage the amount of content you have inside of Slack, and a lot of them are building their whole, this whole developer ecosystem just to administrate [00:38:00] Slack.
[00:38:00] Jaime DeLanghe: Um, so we wanna, um, think about putting MCP on top of that. Uh, and maybe we have our own out of the box Slack bot can do a lot of the administration for you, and you can talk to it via MCP. You could build your own agent, and you can do your Slack admin via MCP. So we're thinking about how can we leverage the same kinds of tools, uh, to help with, with the problem, basically
[00:38:24] Andrew Zigler: In that world too, um, um, I, I'd really love to know what your thoughts on identity. You talked,
[00:38:29] Jaime DeLanghe: Yeah
[00:38:30] Andrew Zigler: a little bit in that list of things, and also things like ownership. Because,
[00:38:34] Jaime DeLanghe: Mm-hmm.
[00:38:34] Andrew Zigler: I think of somebody and, and this is somebody who's like I, I tinker with and have a lot of these agents who do a lot of different stuff.
[00:38:40] Andrew Zigler: But for me, when I go wrangle them or I find them and then they're in their channels, it feels like for me as the agent wrangler, the agent builder, there's not, like, an intuitive way that it all gets linked back and
[00:38:49] Jaime DeLanghe: Yeah
[00:38:50] Andrew Zigler: can understand the umbrella of the impact. You know, uh, sometimes, uh, something happens in a channel where my agent, you know, provided an insight somewhere, and then I later find out after the fact.
[00:38:59] Andrew Zigler: It would be [00:39:00] cooler if that kind of information could be more surfaced to me. But also too, where people, when they see that cool bot that helped them, there was a more
[00:39:06] Jaime DeLanghe: I know it. It's you
[00:39:07] Andrew Zigler: waved their flag, where it was like, "Hey, it was this guy who built me that made all of these insights possible." And so, like, thinking about the ownership of work,
[00:39:14] Andrew Zigler: also the hierarchies of people because, you know,
[00:39:17] Jaime DeLanghe: Yeah
[00:39:18] Andrew Zigler: almost feel like this become the real -- Like, we, people say now, like, the real prod lives, you know, or the real th- or your real code lives in production.
[00:39:27] Andrew Zigler: You have to observe it in production now rather than, like, look at, like, the, the tests and the CI/CD to know what your code really does. You look downstream. The same thing is here. Like, you sure, you have your org chart in, like, Ripple or something. We've talked about this on the show. But you know what?
[00:39:39] Andrew Zigler: Your, your org charts are really over in Slack. You
[00:39:42] Jaime DeLanghe: Exactly.
[00:39:43] Andrew Zigler: your people, and you see
[00:39:44] Jaime DeLanghe: How they're actually working.
[00:39:46] Andrew Zigler: You
[00:39:46] Jaime DeLanghe: Yeah
[00:39:47] Andrew Zigler: the context, like black holes within your organization where everything is going in and something coming out somewhere. So,
[00:39:53] Jaime DeLanghe: Yeah
[00:39:55] Andrew Zigler: it just becomes like how do you think about those identity problems too?
[00:39:58] Jaime DeLanghe: I mean, so [00:40:00] I've always-- I've heard customers dealing with this in a bunch of different ways, and I will say upfront that this is one of those places where everything's kind of shaking out at the moment. We have, we have a com- customer, uh, Assemble who, who speaks with us a lot, who has like hundreds of agents, and they've put them all on the org chart.
[00:40:20] Jaime DeLanghe: So they all clearly have a manager. Um, that org chart is also reflected inside of Slack. So inside of Slack you can see like who are the people, who are, who are the people who are responsible for the agents. Um, those agents are all, uh, like owned by business owners basically. So they're treated like employees.
[00:40:40] Jaime DeLanghe: Um, they have like performance metrics that they need to hit. I think that's one model on like a, on, on one side. And then on the other side you have, um, agents that are strictly operating off of like an OAuth model where it's more like a tool call for the individual and the agent is o- only working on behalf of the human.
[00:40:59] Jaime DeLanghe: It doesn't take [00:41:00] any independent action. Or if it did take an independent action, that would be logged back to the person. And I think probably different use cases are gonna end up using different, those, those two models, like one of those two models. The thing that I keep coming back to, which goes back to what I was saying before about like builder culture and having, making sure that the agency is close to the business, is having maybe developer and business owner not be exactly the same thing for now, but ideally those become the same.
[00:41:37] Jaime DeLanghe: Um, ideally you can have a person who is the business owner, so your agent that you built is also like on your team and people can give you kudos about like how your per- how your agent did and that comes back to you. Um, or in the same way that I can observe my team when they're operating in public channels, at least I can monitor sort of like what is, you know, [00:42:00] I have like four Katies on my team.
[00:42:02] Jaime DeLanghe: What is that Katie doing this week? Uh, and I can get a, a sense of like
[00:42:06] Andrew Zigler: Ashleys
[00:42:07] Jaime DeLanghe: their role. Yeah, exactly.
[00:42:09] Andrew Zigler: Exactly
[00:42:09] Jaime DeLanghe: ideally you could get, you could set up routines, you could get proactive insights around that. Um, I think my, my kind of like holy grail there is if you could sort of get close to treating agents like, um, employees and saying, you know, this is the performance metric for...
[00:42:27] Jaime DeLanghe: Even if it's just like a, a something like say like Claude Tag that just launched. Uh, it's like one, one identity but across many different surfaces. Like in each of those channels it might have like, it's working toward the objective of the channel, right? And so then you could attribute how much of that, how, how that team interacting with the, the agent in that channel contributed to the objective and that gives you a better sense of real ROI, um, which I think is something we're all kind of like chasing at the [00:43:00] moment.
[00:43:00] Andrew Zigler: It also gives shape to how you work, like what you just
[00:43:02] Jaime DeLanghe: Yeah.
[00:43:03] Andrew Zigler: that, that loop, you know, that we talked about earlier,
[00:43:05] Jaime DeLanghe: Yeah
[00:43:06] Andrew Zigler: like your context world that you're engineering and, you know, in, in this conversation we've covered so much ground in terms of like the technology and how it's getting adopted into what I think is one of the most critical surface planes of, you know, knowledge work, especially right now.
[00:43:20] Andrew Zigler: And, you know, we've covered a lot of stuff, but, you know, just before we wrap things up, Jamie, as well, I was curious, like are there things that are under the radar that you think maybe people are sleeping on or not paying attention to, or directions that this is going that you don't think this conversation touched on?
[00:43:33] Andrew Zigler: You have a profound kind of like bird's eye view on where this kinds of stuff is pointing
[00:43:38] Jaime DeLanghe: I mean, I think one of the, one of the things that I think maybe we're having, we're having the conversation in not exactly the right way yet is, um, I think we keep trying... Like, there's a lot of conversations about where are the agents, like, going to live? Where is the data gonna live? Like, who's gonna own which layer of the stack?
[00:43:58] Jaime DeLanghe: and I'm, I'm just not [00:44:00] totally sure that it's gonna to- it's gonna shake out that way. Like, that, like, there will be one company that, like, only sits at the context layer, and there will be, like, a different application that only sits at the agent layer. I think we're gonna see a lot more bleed. and maybe I think about that because Slack is a little bit all over the place in, in each of these areas, but so are so many different companies.
[00:44:23] Jaime DeLanghe: And I, I, uh, I assume we will see some consolidation, um, in, in certain parts of the, the service architecture. But I also see, uh, such an opportunity for, like, mass diversification. Um, one of the, one of the things Slack has always strived to do is to make everybody a maker, right? To be able to say, like, I can make a low-code, no-code workflow, and I can make my whole team operate super well because I just honestly, like, had a bot do a weekly update in channel, and that's actually enough to get us over the line into, into good.
[00:44:59] Jaime DeLanghe: Um, there are [00:45:00] tons of problems in every company, in every person's life that are just sort of like, "Wouldn't that be nicer if?" And I think we'll see a ton of explosion in different parts of the stack in terms of innovation. we're far from the everything kind of, like, coming together under one player right now.
[00:45:18] Jaime DeLanghe: And I think even as we start to see consolidation in certain areas, I also observe a backlash to that almost immediately. Like, people are like, "We're not ready. We're not there yet." So, you know, I think, again, standardizing on things like MCP that are open, that people can contribute to, like, that feels like that's a moment for the community to get together and figure out where we're going, and I love that.
[00:45:41] Jaime DeLanghe: I think sort of assuming that one player is gonna win somewhere, uh, in terms of, like, the service architecture, the model architecture, like I, I just don't, I just don't think we know enough to know yet.
[00:45:54] Andrew Zigler: Yeah. There's too
[00:45:55] Jaime DeLanghe: there's a long way to go.
[00:45:57] Andrew Zigler: There's too
[00:45:57] Jaime DeLanghe: Yeah, exactly.
[00:45:59] Andrew Zigler: g- there's too many constituents, [00:46:00] there's too many hats in the ring, but also there's too many buyers that each do their own
[00:46:03] Jaime DeLanghe: Exactly.
[00:46:04] Andrew Zigler: and that's
[00:46:04] Andrew Zigler: the whole name of the game is that it can be tailored so specifically.
[00:46:07] Andrew Zigler: So no, it can't just be one monolithic winner in the end. You're gonna get
[00:46:11] Jaime DeLanghe: Yeah
[00:46:12] Andrew Zigler: hyper-specialized niche winners for certain stuff. The spicy take I heard in there in what you were saying is that every application, every SaaS platform is a data lake now, or becoming a data lake. They wanna become the place where all the data gathers
[00:46:27] Jaime DeLanghe: Exactly
[00:46:28] Andrew Zigler: do that next level insights in places.
[00:46:31] Andrew Zigler: So in a world where everyone wants to be a data lake, you should probably be like, you know, way down in the, in the valley. You should be, like, at the b- at the below sea level where stuff is draining, right? Where, where all of the knowledge is going and, and that's the kind of places, like, uh, that we've seen in the engineering world, like, be critical and source and
[00:46:47] Jaime DeLanghe: Absolutely.
[00:46:48] Andrew Zigler: The git forge.
[00:46:50] Andrew Zigler: Like, that
[00:46:50] Jaime DeLanghe: Yeah
[00:46:50] Andrew Zigler: drain where everything in your engineering org is going, and that's not to say a drain is something bad. It's just the direction all the water's going. But then, like, over here in all the knowledge working stuff, [00:47:00] that's what's happening too with all that stuff's going into your communication
[00:47:02] Jaime DeLanghe: Yeah, exactly. Yeah
[00:47:04] Andrew Zigler: and so, um, I think that is exciting. Everyone wants to be the lake. Maybe the water stops there along the way, but it still
[00:47:10] Andrew Zigler: keeps going to
[00:47:11] Jaime DeLanghe: I think, maybe I would say also maybe the better thing is to be like a, uh, both a lake and a river. Uh, I think the thing that Slack gets right is that we have a sense of the current, right? We know what's most recent. We know what people are interacting with. And so-- and this is true, the more data you connect inside of Slack, the more ability you get for like Box files to come inside of Slack, your Canvas stuff to come inside of Slack.
[00:47:39] Jaime DeLanghe: You can see who's touching what. So you have this like constant engagement, good context, and that lets you know, like when you put something in a lake, it just sits there and it all just... You c- you don't know what's most relevant 'cause it's all just in the lake. But we have a sense of, of movement, and I think that that's what gets you velocity
[00:47:58] Andrew Zigler: Amazing. Well, this has [00:48:00] been a fantastic chat. You know, Jamie, thank you so much for joining me on the show, for demystifying all sorts
[00:48:04] Jaime DeLanghe: Yeah
[00:48:05] Andrew Zigler: about Slack and the burning questions that I've been having. Like I said, it's just been a, been a big privilege for Dev Interrupted and myself to be so close to the Slack and the Salesforce world.
[00:48:14] Andrew Zigler: And just before we wrap up, is there anywhere you wanna point folks to, to learn more about you or the
[00:48:19] Jaime DeLanghe: Oh, yeah, for sure. So I, I really just wanted to plug our recent, um, MCP client launch for Slackbot. Um, you can now publish a MCP server with your app. It's really great. Slackbot can use it out of the box. People can build skills off of it. It's, I think, a really incredible way to get more context out of your Slack.
[00:48:41] Jaime DeLanghe: Um, and in terms of places to go, I would check out the Slack dev site. Um, it's amazing. There's tons of cool stuff in there. Um, we're constantly updating it. It got a refresh recently. It's real cute. Um, so go check it out
[00:48:55] Andrew Zigler: Amazing. Well, we'll include links to that in our show notes so people can go build. And, uh, for [00:49:00] those listening, if you've- if you're curious about building on Slack, you know, there's lots of resources, myself included, so don't be a stranger. Both Jamie and I would love to hear from you about what you thought about our conversation today.
[00:49:11] Andrew Zigler: Uh, and if you're listening and you made it all the way this far, then you clearly loved this conversation, so please give Jamie and I a big plus one, thumbs up on whatever platform you're listening or watching this on, and be sure to read the accompanying newsletter that comes out on LinkedIn and Substack for all of the juicy gossip in between.
[00:49:27] Andrew Zigler: So Jamie, thank you again for coming on the show. It was a blast having you here
[00:49:32] Jaime DeLanghe: Thank you. It's been great
