Is Slack just a chat app, or is it becoming the command line for the agentic future? Andrew sits down with Kurtis Kemple, Senior Director of DevRel at Slack, to discuss the platform's evolution into an "agentic work operating system" where humans and bots collaborate in real-time. They explore the concept of "leaky prompts," how to harness unstructured chat data to drive automation, and share practical advice on how engineering leaders can start deploying their own custom agents to reclaim their time.
Watch the Vibe Coding Session: If you enjoyed this conversation, subscribe to the Dev Interrupted YouTube Channel to watch Andrew and Kurtis vibe code together!
Show Notes
- Slack for Developers: api.slack.com
- Salesforce Agentforce: Learn more about Agentforce
- Bolt for JavaScript: Slack's Framework
- Connect with Kurtis Kemple: LinkedIn
Transcript
(Disclaimer: may contain unintentionally confusing, inaccurate and/or amusing transcription errors)
[00:00:00] Andrew Zigler: today, I am thrilled to welcome our guest, Kurtis Kemple, the senior director of Devereux at Slack. Kurtis, welcome to Dev Interrupted.
[00:00:10] Kurtis Kemple: Thank you so much for having me. It is a pleasure to be here.
[00:00:13] Andrew Zigler: We're really excited to have you here. Uh, you and I, we met at Dreamforce last year, and when we met, I knew I had to have you on the show to pick your brain because we chatted for a while about some pretty cool concepts. One of them that really stuck with me, um, around the future. Of work. And I, I really wanna dive into that with you today because when, when we chatted at Dreamforce, you, you shared this idea that really stuck with me about how Slack is evolving from a place where work is discussed to where the work is actually done, as if like those words are starting to move into action.
[00:00:46] Andrew Zigler: And I think that's really interesting to explore. It makes me think of like supporting practices. In the code world, like DevOps, you know, maybe we're entering a world where you get something like ChatOps. And so this is kind of part of the future [00:01:00] of work that Slack is taking us and everyone who uses Slack, which is a lot of folks, uh, in, into the future.
[00:01:06] Andrew Zigler: And I wanna dive into that vision with you and, and talk about how those core problems have evolved. So, you know, what do you think about that premise? Do you wanna dive into that today?
[00:01:16] Kurtis Kemple: I absolutely do. I absolutely do. And you know, before we hop directly into that future, I just wanna take one second to talk about the past and how we got here. Because you know, Salesforce. And, uh, has really created the, the push for agent force and agent interaction into Slack. That was our real first approach, right?
[00:01:35] Kurtis Kemple: Like we dropped it in there, we learned a lot, and through that process we started to understand and develop, like what does it take to support, like that type of experience, getting agents directly in first through there, but now through anywhere, right? Third party directly into the Slack platform, uh, or first party customers building their own agents and integrating.
[00:01:59] Kurtis Kemple: And so [00:02:00] we just hit like kind of that, that, you know, perfect storm or shelling point, if you will. Right. And essentially, uh, you know, it made us really just stop for a second and put on a beginner's mindset and say like, what is a platform that supports like. Any kind of age agentic workflow, but does it in a way that is like structured, consistent, grounded you know, that is a very difficult tension to, to think through.
[00:02:30] Kurtis Kemple: And so I just wanted to preface that. And we've been working with a lot of customers to figure this story out, right? Like Anthropic and Vercel have been at the forefront of this. We've got all kinds of companies really just, uh, helping us Replit another one that stands to mind. Uh, just tons of these, uh.
[00:02:46] Kurtis Kemple: Across different industries, all noticing and saying like, Hey, we can deploy AI here because we've got collaborative environments, we've got context, which is what we're gonna talk [00:03:00] about
[00:03:00] Kurtis Kemple: here. Um, and so, yeah, so sorry, just the, the main intro I just wanted to bring us, 'cause that's how we started thinking about the future, right?
[00:03:07] Kurtis Kemple: Like. Look at where all these things are heading. There are some similarities, some things that are overlapping. And when we think about truly having humans and agents working together and collaborating, like what does that look like in reality, right? Not even just at the code level, but literally handing off,
[00:03:28] Andrew Zigler: the interaction point. I, I love, I love how you framed it. I'm really excited to dive into this because you're right. I mean, slack becomes the place where all of that context lives and that context is messy. It's the real communications between real people getting their work done. It's not this neat, orderly, structured data that can flow in and out of systems, and so it creates this perfect intersection between the systems we're building.
[00:03:51] Andrew Zigler: To be more productive and how and where the work is getting discussed. And it's exciting to think out how all these other companies to see the opportunities with their [00:04:00] conversations and, and, and want to tap into that to make their own work better. And really it comes down to this. Context, right? It's because context has evolved now into being a first class citizen of the AI world.
[00:04:13] Andrew Zigler: Before we were all about prompts and prompt engineering, and then it evolved into context and context engineering and you know, I can't think of a better source of context for a lot of the things that happen at work than maybe some Slack channels. So, you know, can you expand a little bit on this context gap and, and how it really is needed to help models perform and meet companies where they want to use it?
[00:04:36] Kurtis Kemple: Absolutely. So I'm gonna, uh, walk you through super quick something that I refer to as leaky prompts, right? Uh, when you only own half of the experience. Uh, meaning that I can't control what a user prompts, right? And they might start off with a very perfect prompt with what they're trying to accomplish, but.
[00:04:56] Kurtis Kemple: Literally proven through science, like any conversation, [00:05:00] whether that's with something digital, another person, a group of people will actually slip into chaos unless it is actually managed like triaged. Right? And we see this, actually you do this right now when you are interviewing people and you got engaging conversation and we're chatting.
[00:05:19] Kurtis Kemple: Effort from you and energy, you are literally putting in a ton of work to ensure that we have this very good, fruitful conversation that stays on track and has important insights and talking points. So, you know that work is also required when you are engaging with an LLM, surprisingly enough, right? Uh, but the issue is, is we can't control how somebody else is doing.
[00:05:46] Kurtis Kemple: And so it puts us in a place where. The only way that we can have the best chance of ensuring that that intent is in alignment. We're staying on task to their goal is that the context, the [00:06:00] representation of what we give to the LLM on the user's behalf is as best a representation of what we can think they're trying to do.
[00:06:08] Kurtis Kemple: You're almost adding like a second order need of understanding. All right. And it's like. You have to understand how the user is going to interact with the LLM and ensure that you can just provide the right context. I like to think of it more as information architecture at this point, and if you can do it well enough, it makes it a lot harder to have those conversations get off track.
[00:06:32] Kurtis Kemple: And that misalignment on a tent, uh, it makes a difference. And like you said, slack is a wonderful home for that context. We've got threads and channels and messages and that's where the, I see the secret sauce at.
[00:06:47] Andrew Zigler: Totally. And so when you're, you're talking about like basically this triage, this harness to keep the conversational rails. We we're at this point where we all acknowledge that AI is very powerful, but it's a force [00:07:00] multiplier. It multiplies the good and the bad, and it's going to make bad situations worse in terms of not having the right.
[00:07:06] Andrew Zigler: Prompts, you know, leaky prompts as you described it. Also, not doing the, your own kind of like data hygiene on what you provide and what you're asking for. Also having clarity on what you're even trying to achieve when you ask it. All of these things are, are, are powerful things that the user brings to influence the outcomes and the experience of using the tool.
[00:07:25] Andrew Zigler: But context, as you say, becomes this experience that the. The producer of the experience, the provider, the one that's trying to give the end-to-end service can actually use to keep on rails. And I'm kind of curious to know from you, how does Slack turn the messy reality of all of those conversations into that context harness that keeps users from hurting themselves with their own agentic conversations.
[00:07:52] Kurtis Kemple: So we're approaching it in a couple different ways, and I think number one first is like understanding the needs of [00:08:00] app developers, right? And people who want to integrate into the Slack platform because, uh, that's actually going to largely inform what type of context we should be exposing to them and at what degree, right?
[00:08:13] Kurtis Kemple: And, uh, helping them understand how best to use it through SDKs or APIs. And so tactically how that actually manifests is something like, okay. Very common, uh, need is to, uh, do some sort of deep research or deep synthesis of context, right? Uh, and that will be broader than a specific channel or thread or something like that.
[00:08:34] Kurtis Kemple: So how do we accommodate that? We build a, like a real time search, API that is purpose built to interact with LLMs as opposed to end users, right? And so then you can build these, you know, better search integrations, your perplexities or other things. I'm working on an app right now called Trendy that we might talk about a little bit um, that does deep research, right?
[00:08:56] Kurtis Kemple: And so, you know, these things uh, you know, require [00:09:00] one specific type of context. Uh, but then we've got where maybe you are a design team and you're working with your, uh, Mar uh. Marketing team and you've got a design for a new landing page. So you pull up the Vercel v zero agent, and you're working back and forth, and it's able to take the context from that thread level and actually go off and generate something for you based off of that.
[00:09:26] Kurtis Kemple: And that's great. But then also what about the scenario where, uh, you've got, generally most Slack workspaces have some sort of knowledge or answer, you know, or Q&A channels, right, where you go to look things up. So you probably want to be able to have an agent experience at that channel level that's able to tie into related, you know, canvases or lists.
[00:09:46] Kurtis Kemple: And the messages within there and help answer questions faster, I can think of about 15 different, you know, verticals or, or use cases where that becomes immediately applicable. so, you know, last time when [00:10:00] we talked, I'll pause right after this, but it's, you know, I, it's about having the micro, uh, microscopic and macroscopic and just like finding those right integration points at the platform to enable what it is.
[00:10:14] Kurtis Kemple: AI app developers and these AI platforms are wanting to a, you know, bring to their users. And so it's a lot, but yes, it's all context. Everything I said is about like data management or context.
[00:10:28] Andrew Zigler: and in this world where you're managing and creating this context that produces these more deterministic outcomes, you're, you're ultimately rendering a conversation into a tool somewhere and allowing it to apply actions like the, the Vercel the V zero one is a really powerful example. People could be having a conversation or dropping a Figma link or cross linking things in, in Jira, right?
[00:10:50] Andrew Zigler: Because these are also places where context lives. And so when you talk about tools, being able to grab and use and interact with that data, just like we as humans, [00:11:00] can you start talking about a new kind of, uh. It's like an integration layer where human intent and machine ability can meet. And that's an exciting opportunity for, for Slack.
[00:11:14] Andrew Zigler: I think Slack is uniquely positioned to tackle that problem. It sounds like from the way that you frame it, y'all already are, you know, really like headfirst tackling this problem. I I, I'm wondering how y'all think about it too, because Slack is notoriously a multiplayer experience. No one uses Slack by themselves.
[00:11:33] Andrew Zigler: But AI is relatively single player in terms of how we think about it and use it, right? We maintain our own context, windows, our own chats. We have our own silos. We go to chat, GPT, whatnot. But you know, I, I wanna know from your perspective, how does that change and evolve when you start getting multiple people interacting with these bots in a shared communication environment?
[00:11:54] Kurtis Kemple: Yeah. Uh, you know, I really wanted to experience that and so we've been building it right. You know. Um, [00:12:00] And I even built a full on example of just a little chat app for me and my family that integrates AI just to really experience multi-turn, collaborative with AI in the flow of that. And you know, I think the only reason we don't see more of it is because I think it's pretty difficult to really build up that user interface, you know?
[00:12:21] Kurtis Kemple: But we've been doing that for a long time. Uh, and you know, I think the Salesforce, uh, to agent force, the Slack integration. Shows up a lot there, and I bring this up because we see companies who are like saving literally like 4.8 million in annual benefits by offloading stuff that, uh, yeah. Agents that they were able to just click and create to help with deal pipelines.
[00:12:45] Kurtis Kemple: So, so that it's doing the intermediate toil, triaging, not making decisions, bucketing, categorizing, flowing, deciding where it goes. Right. And that is completely different. You know, and like now we're [00:13:00] seeing more and more verticals bringing that, like you can code apps fully through, uh, open AI Codex or GitHub co-pilot or do both.
[00:13:09] Kurtis Kemple: You're an engineering manager. GitHub co-pilot. Go dig through all of my top prs, prioritize them for me. Oh, code Codex. Now please go through those open the top five in a sandbox environment for me so that I can work through them or or check them out, right? And then you close them all up. And you know, the thing for me too is that I think about Slack like as a, a.
[00:13:32] Kurtis Kemple: Uh, saving you is on the productivity tax, right? And so when you're doing AI well in Slack, it's doing the same thing. Any other app does it. It's me. When I. Vibe, whatever, and I spin that off and now I'm off doing something only I can do, only me that I need to spend my time on. And so I've just like got this like web of agents around me now you know that I'm using and they're doing everything, like I said, from deep research projects, pulling in [00:14:00] my calendar and organizing my day, looking at issues and things that I might need to triage and address all the stuff that was just like manual labor.
[00:14:10] Kurtis Kemple: Nobody else was gonna do right, like it falls to me. And then my other favorite place is I love to do it, to apply AI to where I otherwise wouldn't have time.
[00:14:21] Kurtis Kemple: I have 20, 30 minutes for ai. Let me see if I can vibe, code up a, a good enough solution for this. I end up with nothing. It was 30 minutes of my time.
[00:14:31] Kurtis Kemple: I end up with a success. I now have something that I wouldn't have had anyway, because I only had 30 minutes. Couldn't have done it alone in 30. Maybe I'll get a good result if I can sprinkle a little AI in. So I just, you know. When I talk about integrating AI in the flow of work, I think I'm like at a point where people are like, you know, we're talking about like handing off just a Figma here and there.
[00:14:52] Kurtis Kemple: I'm talking about like building the Figma and then handing that off to V zero, who's generating the page and Slack [00:15:00] bots writing up the canvas for me to go share with the marketing team. So we can get ready for the GA and submitting the AI created workflow that lines all of the social media stuff for us.
[00:15:11] Kurtis Kemple: You know, it's
[00:15:12] Andrew Zigler: Wow, that's like pretty embedded. experience. You, you're talking about this world where you're effectively chaining these age agent. Tools together using Slack as the medium. Slack becomes the integration layer because it's the means by which you're communicating with the bots. What do you do when you communicate with any AI tool?
[00:15:29] Andrew Zigler: You're providing words that are context. Slack then just kind of becomes this place where you're conducting an orchestra basically between all of these agents. As the way, as the way that you described it. You're orchestrating because you're basically a, you're basically a pipeline. You, yourself, and you are the.
[00:15:46] Andrew Zigler: The human in the loop deciding what's the next stage of the pipeline, but you're effectively
[00:15:50] Andrew Zigler: handing things between the tools, and I think that's a powerful way of working. I also think that opens up a whole new level of, uh, you know, e even the [00:16:00] examples of like using GitHub copilot to get your top issues and feeding it into Codex, like that's an immediate, powerful atomic example.
[00:16:08] Andrew Zigler: And all of this comes down to how easy it is too. Build and tinker and explore. You talked about companies deploying their own tools that reduce toil and sales pipelines. You know, saving them literally millions of dollars and those are just easy one click wins. So, yeah, I wanna dig into, I think this is a good point to really kind of dig into the how of, how Slack is empowering these teams to build these really cool age agentic experiences to actually unlock those savings and you know, a big vision like that can only work.
[00:16:36] Andrew Zigler: If the platform is easy and delightful to build on, so how does Slack achieve that? How do you educate your devs for all of this complexity?
[00:16:45] Kurtis Kemple: You know, that was the first thing is like, uh, we had to reassess our entire platform. So a couple months ago we were looking at the direction of where things are going, uh, and where we had spent investment over the last two years. And a lot of that was [00:17:00] into our, the automation side of the house, which was
[00:17:02] Kurtis Kemple: good. We needed it. Workflow builder's amazing. It gets you so far. Also just released a bunch more, uh, like conditional, nested, conditional branching to customers So go check that out. If you're not using Workflow Builder, you should be. But it gets you so far. But when we think of building these ai, um. experiences, they're gonna be tying into Slack in all kinds of surfaces, right? Like this, uh, app, I'm vibe coding now, trendy it. You can DM it, you can pull it up through the agent's sunroof, you can at message it in channel and no matter what, it's gonna help you build that deep research report, right? And so, like, you know, we have to think about, and that's still being narrow.
[00:17:41] Kurtis Kemple: We've got slash commands message, actions you know, all kinds of events. There's no reason AI can't sit behind any of those events coming through Slack, you know, and, and as a matter of fact, my next, uh, project app I'm building is called Tidy, and it's gonna go around and help make [00:18:00] sure that your workspace is just all tidied up for you and, and exactly what you want, giving you reports.
[00:18:05] Kurtis Kemple: What's happening now. These channels might need to be archived, uh, you know. It will write up canvases and archive it and clean it up, recommend workflows, and that's just scratching the
[00:18:17] Kurtis Kemple: surface.
[00:18:18] Andrew Zigler: Yeah, because all of that context also will need its own kind of agent janitor to keep it useful.
[00:18:24] Kurtis Kemple: That is it. That is it. And so, you know, we are also hard at work on making that click to create agent experience, just getting them right in there. Super simple. The vibe coding, slack app experience. You'll be able to vibe, code, uh, slack apps like with, uh, Heroku and stuff like that and just deploy them right into your workspace.
[00:18:46] Kurtis Kemple: Very seamless, but it all starts with the developer experience. And we've invested a ton over that. And so we did that by consolidating back onto Bolt Apps, which is our main framework. Uh, we consolidated onto the CLI, so you [00:19:00] CLI, you know Slack, create, pass it a template if you want, or start blank. It's up to you.
[00:19:05] Kurtis Kemple: We've got all the options. You run Slack run and now you can run it in a workspace and tinker with it and run Slack, deploy. And deploy it to your platform of choice. And that's where we are right now in that, that second half um, which I've put under time to value, which is deploying, like I've gotten an agent and it needs to be in Slack and I need to have it production ready.
[00:19:28] Kurtis Kemple: I want that time, like down like a, a week, like two weeks. Like you should be able to databases, observability, fully integrated into surfaces, AI inference happening, uh, in a matter of weeks, and be submitting to the Slack marketplace to get your app there. Uh, last note, and I'll say, I keep telling folks stop building apps and start building conversations.
[00:19:51] Kurtis Kemple: Like we already have Multiterm, multi collaborative UI and AI user experience Purpose built. Why build your whole own [00:20:00] website on an app on top of yours? Find product market fit right in Slack. You know, that's what we're building the infrastructure to support that.
[00:20:10] Andrew Zigler: make conversations the interaction point, reduce the overhead on creating those tools. If it's already something they're gonna concierge serve from a conversation style thing, why not just have that live within Slack? It becomes the, the user experience as
[00:20:24] Kurtis Kemple: it.
[00:20:24] Andrew Zigler: And, and I, I, I wanna know too, in this world we're describing and we're entering into, you know, doing.
[00:20:29] Andrew Zigler: This agentic coding it's relatively approachable. We talked about the developer experience and how the developers can spin up their sandbox environment on Slack Dev and get started, and they can also use bolts, your SDK to quickly get an a, an app on online and connect it. Right. So, you know, how do, how does like also think about enabling people who are not engineers, but who are also using Slack and would benefit from these workflows um, to be able to maybe build and deploy things. Is, is that what the, the [00:21:00] builder, uh, workflow builder aims to solve? Or do you see a world for them where maybe they're using these tools as well?
[00:21:07] Kurtis Kemple: I think. See the world, I think, I think any tool that is built to add guardrails, most people, uh, when they, you know, become familiar with them enough hit the rails. It's almost inevitable and it doesn't matter how far you move that guardrail. Eventually people who are invested enough and have found enough value will hit those rails because they understand the more they integrate.
[00:21:33] Kurtis Kemple: The more value they're receiving, right? And so they'll find new ways that you never thought of to try to do that. So I think my point there is that like, yes, you have to purposefully build, uh, what I like to call, like learning paths that are essentially are persona based and you have to understand that right level of abstraction.
[00:21:54] Kurtis Kemple: And so the kind of, the way I like to think of it is first I teach them about the platform in a bit [00:22:00] of a vacuum, not too much of a vacuum so that there's no external context. But really first let's familiarize ourself with. The platform, its AI offerings, why it might matter to you, what features are available and how you get started.
[00:22:13] Kurtis Kemple: It's like clean, you know what I mean? I can work with that. I can get through that pretty quickly. And then we want to pull out of that vacuum, and now we want ecosystem integration because when I'm building something for production, whether I'm a customer or partner, whoever, I'm never building my app, like completely in isolation, right?
[00:22:31] Kurtis Kemple: We have data management, permissions, security, compliance, you know, the, the, the list goes on and on. And so this is actually where we are now. We've consolidated our developer experience to make this easier, we've updated all the initial enablement material for Slack in a vacuum and where we're pushing with partnerships with Vercel and Replit and Anthropic and open ai and, uh, all these other amazing, you know, AI [00:23:00] companies, uh, more and more on the list too. We're gonna be everywhere. I'm very excited. But long story short is, you know, we're really pushing to, uh, just like enable all of these different types of experiences to be built directly into Slack. And through multiple ways.
[00:23:16] Kurtis Kemple: Like we even have MCP if you're working in Anthropic or you're working in in ChatGPT stay there. Right? But now your Slack context again, is getting to you where you are. And when you jump back over to Slack, you've got the GTP app installed. You're literally picking up almost having the exact same conversation, right?
[00:23:35] Kurtis Kemple: So yeah.
[00:23:36] Andrew Zigler: it it really fulfills that, that that vision of the age agentic operating system, right? It becomes the place where everyone goes to do their work. I I, I wanna peel back the curtain a little bit. I, I selfishly wanna get a glimpse at what that is like inside of the slack world. How much is slack, you know, dog fooding these principles around, you know, making it and just kind of, uh, applying AI for all of these experimental scenarios.
[00:23:59] Andrew Zigler: [00:24:00] You, you've described your your almost a council of tools that you've been building, that you've been advising. I imagine they live, you know, in, in some magical Kurtis sandbox somewhere. So, so what does that look like inside Slack? Like how, has, uh, your engineering team really evolved to also get in the trenches and build these things?
[00:24:19] Kurtis Kemple: Yeah. So first of all, like we bring it in all the time. So we've got another app called Tiny that's already installed to our workspace that, uh. Is used by, uh, first it will be used by everyone within the Slack business unit, and then we open it up to the broader Salesforce company, right? and then I'm working on trendy now, and we'll do the same thing.
[00:24:40] Kurtis Kemple: We'll open that up and let people test it out and build with it, and then we'll open it up to the entire company. And I'm gonna do the same thing with Tidy when I build that. And that one's gonna be deeply embedded into the AI ecosystem, like Lang chain, like creating embeddings and storing that uh, in, uh, interstitial data for [00:25:00] steps for longer jobs when it's doing all these really interesting things, being able to stop and rewind and, uh, redo stuff.
[00:25:08] Kurtis Kemple: And we've got like the thinking steps and all the support, like actual native user experience to support this coming as well. And wisely, we're looking at even building like an agent, SDK, and just saying like, let's make it even faster than using Bolt. Like what if, what can we streamline more? We're looking at adding new APIs to make it easier for partners to have the proper permissions to build and deploy these agents and apps on users' behalfs, but, uh, behalf, but always, of course, as secure as possible.
[00:25:39] Kurtis Kemple: We take that very seriously.
[00:25:41] Andrew Zigler: I wanna know from your perspective, because you have your role in your role at Slack, you are very empowered and you're very technical and you're able to envision and build and deliver these things, which is really exciting because you understand what you're trying to achieve. And as it. As a dere professional.
[00:25:58] Andrew Zigler: I mean, like I, I myself really [00:26:00] resonate with that being one myself is that, you know, our whole roles revolve around building the context for engineers to do their best work and bringing it all together, you know? What would you say to an engineering leader about how your role has evolved and you. Picked up these tools and you are seeing all the success in delivering things.
[00:26:18] Andrew Zigler: And maybe they, they haven't coded in a while. They're an engineering manager, they're kind of like dipping their toes back into this world or they're trying to figure it out. What would you say to them to really get them on the right track and to be building and showing internally? Internally in the same kind of way that you are?
[00:26:33] Kurtis Kemple: I love that. And I'll maybe give all my tips and tricks right now. you know, number one is, I'm just gonna start with this again. I throw AI at what I call toil. And time dependent tasks that I cannot accomplish otherwise. First, I do find places for it in my workflow, but I think the hardest part is getting started, and I think it's when we try to invest too much.
[00:26:59] Kurtis Kemple: Like if [00:27:00] I went into a, okay, here's a, you know, like a seven step program to have you reviewing your PRS today, right? It's gonna overwhelm people and it might not match exactly your workflow. And so I actually say, find the most chaotic, annoying part of your day. Sit. Go through a week, maybe two, and really think about what part of your day is bothering you and invest 30 minutes into researching if there's a way that you can use AI within your system.
[00:27:34] Kurtis Kemple: Right? The tools. What tools are available? Do any of those, uh, tools like features align with my problem space? Yes. Let me actually invest 15 minutes in trying it out and I think that you'll be surprised when you start saving five minutes here. 15 minutes there. 30 minutes here, then you'll start investing a little bit more.
[00:27:57] Kurtis Kemple: I've got a couple fun little scripts and prompts that [00:28:00] I reuse. Like one of my favorites is, it's a strict kind of outline that I give to AI on planning mode when I want to like. Familiarize myself with a new project. What dependencies are in use? What patterns are you recognizing? Where are you seeing like overlap?
[00:28:18] Kurtis Kemple: I'm focused on this area. What part of the project should I dive into first? You know, a lot of these type of things that can just source information for you quick and you can verify I find to be so useful. It's why I'm building trendy. Doing one shot, deep research projects on a topic, and I can just put it to the side and come back to it later.
[00:28:40] Kurtis Kemple: Saves me literal hours. Hours a day. Deep research is probably one of my most used AI features. Uh, in Dev Rel I'm in a role where I need to understand what's happening in the industry, you know, and so that's constantly me out there doing it myself or ai, brave search, [00:29:00] API, uh, a really good system prompt.
[00:29:03] Kurtis Kemple: And now I can just generate reports on the fly. I can just start generating all of them, you know? Uh, I, it is no longer. Me manually opening 40 tabs, synthesizing, writing up the full canvas. I, I guess such a head start. Um, You know, last thing, yeah. Zero to 60 is I love AI for things that will take me zero to 60 in a structured way.
[00:29:27] Andrew Zigler: that's a really useful, like, set of tips. I, I especially like big plus one to like finding the most annoying or like, time consuming toilsome part of your, of your day or your week. Like, go to your Asana board and find that recurring task that always pops back up as soon as you do it and you dread it when it comes back around the next time.
[00:29:46] Andrew Zigler: And create a way to solve that if you don't think it's something that can be solved. I challenge you to, to really change that assumption because we've talked about today how even conversations in Slack can become the workflow through which you solve those things. Even just saving a few minutes of your [00:30:00] time is gonna be a huge unlock.
[00:30:01] Andrew Zigler: And lastly, what I'll end on is, you know, if. if, if you're a, a manager as well, you're an engineering manager, you have a team of people who probably experience these toils as well and you on the aggregate, therefore experience those toils. So really also look to the people that you work with and that report to you and they're busy, right?
[00:30:20] Andrew Zigler: What could you maybe find a way to automate for them to take it off their plate? Start with simple problems and then work. You know, to, to more complex ones. I, I think that that's like a really great way you've laid, uh, laid that out. It's the best way of getting started because once you have that win um, that's the easiest thing to showcase internally, to take and, and talk about with everybody.
[00:30:40] Andrew Zigler: You've saved yourself and other people a whole bunch of time. Uh, and, and that's immediately going to be like fodder, you know, fuel in the tank for your next, uh, idea that you want to go innovate. So one at a time, people. But really great, really great advice.
[00:30:53] Kurtis Kemple: I'll leave you with this. I literally, the last two weeks have been out like sick. Like so sick. I got a stomach bug and [00:31:00] like I deal with like immunity stuff. So like, yeah, I was like out when I came back I had a rush of things I knew, also knew I wanted to be ready for this and like, you know, so many things happening.
[00:31:09] Kurtis Kemple: I went into Slack bot. And I was like, please, here's a couple canvases. Look at these channels, look at my calendar, and I need you to help me plan this week. Like to a tee. Please help me best use my time to squeeze in all these things. And it just did, and I've just been, boop, b boop, boop boop boop. And that's what I mean, like 15 minutes between this meeting, what we did now and another.
[00:31:34] Kurtis Kemple: 45 minute meeting I had between, I literally went and accomplished three little like micro tasks that were already laid out for me.
[00:31:41] Andrew Zigler: See, you're already living the successes of it. And that's what I love so much. I I, I'm really grateful that, that we got to, to grab some time on your calendar, especially, everything is so chaotic around it right now and you're playing catch up. So I definitely also wanna say, you know, uh, as we come to the end of our, of our chat, we've covered a lot of amazing things about how Slack is [00:32:00] becoming the agentic work operating system. And we've showed a little bit about how it's fun to tinker and experiment in. But I really wanted to say, you know, from our conversation, you know, Kurtis, thank you so much for coming on, Dev Interrupted because it's been really great to pick your brain, uh, in this environment that I know myself and many of our listeners use every day to get that work done.
[00:32:18] Andrew Zigler: you've really sold me on these tools um, in fact, I, I, I would love to kind of jump into. Maybe even try to look at some of the things you've been building. Uh, I know we don't typically do this on Dev Interrupted, but I, I'm just so tickled by all of these, uh, product, uh, you know, uh, prototypes that you are building um, that I would love to go and maybe vibe code some of those together with you.
[00:32:38] Andrew Zigler: So, you know, what do you think about doing that together?
[00:32:41] Kurtis Kemple: So excited. Let's do it.
[00:32:43] Andrew Zigler: Amazing. Well, like I said, I'm full of ideas. I've tinkered a little bit with Slack. Um, But I definitely wanna learn from you as we go. And for those of you listening, you know, this is definitely a, a different pivot from how we normally do it in Dev Interrupted. But if you wanna see what Kurtis and I cook up tomorrow, we're gonna be dropping the [00:33:00] vibe, coding demo, uh, within Slack on our Dev Interrupted YouTube channel and on LinkedIn as well.
[00:33:05] Andrew Zigler: So if you're not following us. Either of those places are gonna miss it. Make sure you go and follow us on LinkedIn, uh, or on YouTube. You can also reach out to me there as well. Uh, so you're gonna miss out on the fun otherwise, but it's gonna be a blast and I'm really excited to pull open Slack, uh, and see what this SDK can do.
[00:33:21] Andrew Zigler: So, you know, Kurtis, thank you so much for sitting down with me today. Let's jump into some code.
[00:33:27] Kurtis Kemple: Let's go.
