Is Agentforce the future of enterprise vibe coding? | Salesforce’s Dan Fernandez

25:39if you're reinventing it over and over, that's a luxury only like an AI native startup that's still trying to find product market fit has. And so it's a whole different set of problems. And ultimately, it really orients everybody around this idea of reuse and understanding this like what's already at hand. And we're going to talk about that a bit because that's the great thing about Salesforce and building inside Salesforce is where your data lives. it's where your systems already live and so there's a lot of reusability that you can play with and kind of at the top too you know because of that there's a lot of guardrails that you get to be able to set up because salesforce is you know it's it's the home to their data but it's also where a lot of people in the enterprise a lot of people at scale are going to look to get the source of truth and to understand like where the company is going pull reports build new products So what are the kinds of guardrails that can exist when you take that vibe coding idea, but you supplant it within this firmly rigid structure of Salesforce?

26:43Yeah, it's a pretty multifaceted question. So I'll try and give some of the highlighted things to go through that really resounds with everyone. One of the key areas that Salesforce does is makes a great set of tools for pre-production environments. Those are called sandboxes. So instead, a lot of times developers have to like, oh man, I have to build a new environment and it's going to take me all day to build this from scratch. I have to read this code and then write the script. Sandboxes basically say, start with production and make a copy of it. And you can choose, do you want just the metadata, the structures of the data, or do you want all the data itself?

27:22If it's all the data, it's called a full sandbox versus just the metadata, which is sort of like the developer sandbox. Like on a day-to-day perspective, we'd have our own developer sandboxes. And really making that a first-class citizen means that I have a safe environment to test my AI on. As opposed to, you know, you see some of these examples where the agentic tool literally deleted a production database, right? Oh, yeah. We've all read that story. We covered that here on the podcast, too. You probably don't want that, right? So that's sort of like step one. And there's just a number of other things, too.

27:57the Agent Force for Developers tools. One of the key things we did was partnered with our friends at Client Open Source Tool that brought a number of capabilities. And we built on top of that our Salesforce capabilities. So that does include one of my favorite features, which is checkpoints. This is like the, hey, the AI did something and oh, I just replaced all the CSS that I spent the hour building. What is going on? And you have that checkpoint that you can revert quickly, right? That's sort of like, okay, great. I didn't mess up. We talked about like not messing up the production org. Now we haven't messed up our code, if you will.

28:32So Hagrid at Checkpoint is a great area. And I think some of the other things are model context protocol tools that we do. So we're going to ship our own set of MCP tools that make it really easy to work with Salesforce and make it that much safer. So it doesn't randomly guess. It's using our pre-built tools. And then the last thing is obviously a set of agentic rules. And this is really what I think everybody's discovering is sort of the secret sauce. how you can tell and really do the governance. So if I'm a team lead, I am telling you everything I wanna do, whether it's those style rules or we must use this framework or you know what, don't AI, ignore this folder.

29:07This is our legacy folder. We don't wanna change this. I don't wanna rebuild 30 unit tests for this legacy thing. And you have those sort of granular controls that are cascading as well that you can use there. And then lastly, all the stuff that are in the platform fundamentals, field level permissions, audit history, access control. There's just a ton of stuff that you can do within there. And then specifically for, we have a product called DevOps Center that allows us to do a DevOps pipeline. It uses GitHub as the backend. And within these builds, we want to make sure that we have quality by default, right?

29:44So when we ask you to build something, it's building unit tests for it. It's suggesting code analysis runs for it. And it's making sure that when the output is built, it's built. We're not just building the artifact. We're building the way to validate the artifact is correct. And using agendic reasoning like, OK, yes, we know it's built. And then the last mile, what we call quality gates, which is you can define you. It's the bouncer, if you will. You want to get in. You must be this tall. You must pass this percent of quality tests. There is no SEV0 on the code analysis tool. and our code analyzer tool, for example, is actually an aggregation of five different engines, right?

30:24Everything from PMD to ESLint, some of the best open source tools for Salesforce and web tools that it runs and you can set like, hey, no SEV zeros or you know what? We'll take a SEV2 on this one because we really want to make sure that, or a SEV3 that all docs must have triple slash comments, right? So you want to make sure that something is blocking and you can control those at a really granular level with our quality gates. And sort of those guardrails from, we're going from an individual, which is building things, their environment, they can make sure their code is okay and their org is okay.

30:59Then what we're doing is making sure, hey, how do we set this across a team? And these are some of the things that we're still thinking about how the best way to do this. And AI rules are a great example of where we are codifying what we want to do for a team perspective. And then across all team members, this is the bar that all code need to get in, whether it's manually built or AI built. Those are some really great points that kind of frame what makes it strong. I want to like walk through some of them because there was some great stuff in there. So one of them being meeting the developers at the experience that they not only like expect, but they need in order to build these tools.

31:34And that means, you know, providing things like these, you know, many would almost call these sandboxes like ephemeral environments, right? Being able to create clones of production and pull in certain things and scope them out And we all know that AI is really great at scaffolding out those kinds of things, making the blank page upon which you write. And so that's like a first class citizen, I think, in building in the AI world. You have to have that. that another thing that's like really important is bringing in all of the actual like experience actually using like the primitives of manipulating the ai like people have like agents.md right you have all your best practices for what people for how the agents should do it oh we use this linter or oh we have to have this kind of style or everything it has this preamble in front of it and those details are small but in the enterprise when you're building these tiny little building blocks that build up to be these huge structures, those are huge force multipliers and you have to have them in a repeatable way.

32:34They need to be scoped, you know. So those are two really big important things is having that those ephemeral workstations so that you can spin stuff up. And when you mess it up, you can roll back to a checkpoint. I can't even tell you how many times I've clicked the restore checkpoint button in cursor. And if it wasn't there, I would not still be using it because it's really important to be able to experiment with these tools and to try out new stuff and when you're working on enterprise-grade software that's really scary when you start going down this one road you know it can be really easy to over rotate on something or oh we'll try to fix this problem and in doing so you introduce five more oh wait let me just go back to when i introduced this problem in the first place and see if i can even prevent it from happening so these are all the kinds of things that people are already doing.

33:21But this last one that you said was really interesting because I haven't heard a lot talk about it because a lot of organizations don't have this need of almost having this like bouncer. Like we're all talking about the AI code review tools or the AI agents that work asynchronously and they review your work and they tell you it sucks or doesn't follow the guidelines of what you expect. But like actually having the rigid checklist and then a system in place to enforce it, it helps keep all of those first two parts like all in line. So now you have a system that the engineer can work reliably through and it likely saves them a lot of time being at the iterate in that way.

33:58Have you all been able to kind of experience a rapid flow of development once everyone's locked in on all three of those kinds of controls? Yeah, I think so. And remember, this is a granular set of controls for, imagine we're in an enterprise, the finance team is going to have some of the most rigid rules, right? everything must be an audit history everything must have a unit test you know we need to do these things every you know we need to sign off and yada yada but there's other categories where there's departmental apps and hey that's more like just what we're doing for uh internal planning and it is our uh we're going to build a set of tools for sharing specs and it's going to be doing and you're going to allow for upvoting downloading discovery and all these wonderful things maybe that doesn't need that level of rigidity that that you have then there's other ones where it's more like it's really is a new sort of category that personalized productivity that i call personal apps which is yes building for me right i'm just like almost testing just in local host so you can choose how much of a quality that you want on a per app basis and it gives you know i call it sometimes the federal state local everything you check in must follow and some companies do very high federal set of rules.

35:15Some do, hey, this is going to be the set of federal rules. Like the good examples would be like state, like finance is going to have state rules, right? Like you must do this for finance. The personal app is more like local. Hey, we're going to do whatever we want and we're going to use this framework. And it's sort of just get the job done. So you at a granular level can choose how many of these gates that you want. Is your organization one where everybody decides things to sort of top down on a federal level? Or is it more like, hey, it's actually on the team business. The HR team, finance team, they're going to have the most biggest rules.

35:50They're going to be more like state driven, if you will. Or it's just, hey, anybody can do anything. And there sort of are no rules. But you need those levels of granularity, which is where are you stopping? Is it all code or is it code for specific applications or specific business processes that you want to say? And what you need to do is just have tools that are flexible to have different DevOps pipelines and different rules within there as well. Yeah, recognizing the impact level of the software you're building is critical in this world that you're talking about. We've talked quite a bit about personal software in the rise of AI coding here on Devontrap that we recently had.

36:30Lee Robinson of Vercel talk about V0 and that exact way, how you can submit up that personal software on demand, right? That's like that local level that you described, right? And then going up one level, you kind of have the lovables if you're trying to build a business and trying to get a larger thing on top of it. But up until this conversation, there's not a lot of talking about this up in the clouds layer that we're talking about. This federal, top-down, very rigid. And that is ultimately the core of our conversation and the opportunity that Salesforce is going after. and something i want to ask is because you know build building with these tools as an engineer it's fun to experiment building a company on top of them it's fun to spark up something new but how does a company as like rigid and high impact as salesforce and you know with a high need for security and compliance and control and safety how do they not how do you not only recognize that there's a market opportunity, but how do you get over that whole, oh, you know, we're just going to, we're going to wait and see a little bit more how it plays out.

37:38It's so tempting at that scale, I think, to do so, to wait and see what the smaller players do. You know, you have all the resources and time. So how did that conversation really begin at Salesforce that, you know, y 'all said, okay, we really need to bring this to market for our users? Yeah, that's actually a great question. So it jumps back to some of our team members, Wade Wagner, that brought me to Salesforce about five years ago. And they were building Salesforce developer experience. They really wanted to have a first class experience for building on Salesforce platform. And out of that came a number of things, which is certainly well positioned us for this, which was we built a browser based version of VS Code.

38:22So much like Cursor builds a fork of VS Code, it's only available on the desktop. We have our own fork of VS Code called CodeBuilder. We are one of the companies that started, that helped found the Eclipse Foundation for OpenVSX, which allowed for a VS Code marketplace, along with like Google and a number of others, so that you could share extensions. Why? Because Microsoft closed down that marketplace. So, and everything is a VS Code extension. We ship everything we do for our developers within our Salesforce extensions for VS Code. So we had a number of the capabilities there that we were really doing.

39:05And we're really just trying to make developers more productive. And we had the first versions of our code analysis tools. So it became a really logical thing, which is, hey, what are the things that we can do to increase developer productivity and quality? And that's sort of where it started. it and it was really sort of started with uh inline autocomplete which is hey can we just help people build and complete things which is you know start with a method definition and and complete it if you will and now it's gone from sort of like single file to multi-file multi-app and everything within and even then we're starting to see different trends where it's going from sort of uh dev centric to op centric which more like individuals uh to teams short running to long running.

39:48We're really just sort of in the process of evolution of this and where you have tools for all of those things. We're releasing a preview version of an ALM agent that allows you to have these sort of natural language questions and do long running tasks as well and do so in a collaborative. So it's not an individual talking, it's in a Slack channel. And some of these are going to be user initiated. Some of them are going to be event driven. So something happened to our site, you know, based on some criteria, it thinks it can automatically fix that. So we're talking about like self-healing. It really is sort of the future on what we can enable, even if it's just sort of like agent to agent or as simple as, hey, there's when I set the label to do this, the ALM agent knows to fix this.

40:35And what it's going to do, that unit of collaboration is still the pull request. And when we got the pull request, it summarized what it did. and then it tells me, did I pass the code analysis tests? Did I do all those other things that I'm doing? And it's just kind of one example that we do is also scale tests. We're probably one of the only companies that give you a version and actually take your pre-production environment and basically supercharge it so that you can do geo-scaling tests, right? My app works great when I have 100 users, but Cyber Monday is coming. What's gonna happen when I have 100 ,000?

41:09Can it actually scale? We will give you not the production environment, but a pre-production environment and a set of tools to do the measurement and instrumentation on what are the hard things that will happen within your application. So really trying to think through all the developer scenarios. And it very much started from a single file to, wow, what are the use cases? We're thinking about the health of the application and making sure that we have the right things for observability and that it can scale with our scale test service. And then it discovers, you know what, that code, while it's functional and it works it's actually not a good idea to do under under when your user load gets over 500 and we build those and then shift them left so it's directly in the id it's going to be able to track and tell you this is the line of code that you need to do and we will again using ai suggest a fix for it right so instead of instead of doing things like queries in a loop, we're going to tell you to do a batch query, things like that.

42:08Chunky versus chatty. Yeah, no, I love that. I love the idea of the stress testing tools being built into that same world. I think that's often something so overlooked. And even when it comes to like shipping AI generated code or AI software, you know, we still have to rely on kind of like older or traditional DevOps and CICD pipelines and practices to like actually put it to the test. But being able to roll all of that in very smartly, by the way, as like VS Code extensions play off of this framework and this experience that developers are already used to, that's already really well thought out and well developed.

42:44And it's interesting to me because I think, like going back to the beginning, we talked about like the, you know, if you just throw 10 Vibe Coders at one problem, you'll get 10 different solutions to it. And they're all probably around the same level of verbosity and, you know, whatever the case. And so, you know, recognizing, I think, that, like, one-off code problem is easy. Anyone who's done agentic coding has experienced this, where it will reinvent the wheel when the wheel is a very popular NPM package. But what principles really guide your engineers in creating this experience so that it actually does extend instead of recreate?

43:23Because I think that is an interesting, you know, problem to crack into, and it's largely also a language problem. So, you know, how did y 'all think about that problem once you had recognized it? Yeah, so there's a number of things, which is like, one, how do you get an understanding of what exists today? So we have a number of tools within there. So another service we're building is sort of what we call our metadata intelligence service. This is actually something that we are talking about at Dreamforce at a really high level. It gives you all the information and context. So you can do things like ask it natural language questions.

43:56How is this designed? if I remove this field, what is the impact? Ooh, there's three things and a workflow that is guided on this, or you know what? You can delete it and you do things like you couldn't do before, which ask natural language impact analysis questions, right? So a deep sort of introspective knowledge of everything that they've built for. And that includes an API catalog, which are the right APIs to do this? And those can be annotated both by customers or by AI. So you can make sure that you're picking the right thing. Then so all of that stuff is within our metadata and our schema.

44:31And then also we even do like a vector DB, both for our standard objects, custom objects, and even code, right? And the code vector DBs are relatively common, just to be fair, so that people can know, here's what's possible. Here's the code that exists. So which is like, hey, cancel order already exists. And it's within the order management class, right? We don't have to reinvent that. We can suggest that and then somebody can say, actually, no, I want to rebuild this or rebuild an overload for that method and so on and so forth. But you really get the opportunity to start with what you have, get the smarts of it.

45:09And really what we're doing is the smarts for you to be able to query, but really the smarts for the AI to do the better understanding. So it's giving you the best possible responses and then setting a set of MCP tools that help there as well. And that's a great way of framing it. And ultimately it was down to context engineering, about being able to take that world that exists, you know, use RAG, look at what's already preexistent, and then smartly and on the fly as it's needed, bring it into the AI's world, make it equipped with that knowledge, turn it into an expert on what it needs to be, and be an expert on at any given time.

45:46And then context engineering, as we know, is it's a balancing act. It can be really easy to overwhelm versus to underwhelm. And so actually like tapping into that, it's, you know, a magic layer for sure. I think that requires a lot of tweaking. And it's really great to hear that that's like the same kind of like lever that y 'all are messing with. When we've talked about VibeCode and we've talked about how do people get the most out of it, it always boils down to this context engineering. And it really helps people kind of like pull back the curtain and understand that it's all about aligning the information that matters most when you need it in that moment.

46:20And I think that's like a great way of framing it. And I kind of want to use that as like a jumping point into how some of the things in Vibe Coding transform when you have that contextual engineering, when you have that stuff baked in. So like one of them that you pointed out to me, for example, is like you have schemas and understanding like databases of what is the customer cares about, what they track, and all the little details and fields of the things that make Salesforce what it is. And so you take that, you pair it with RAG, and you make it contextually aware of their actual organizational shape.

47:00And then once you do that, you know, what changes out of the box in your experiences playing with this kind of tool? Yeah, so like, let's just say you were using a standard schema for an employee. There is sort of like a starting point. This is one of the things that Salesforce builds a set of pre-built schemas called our standard schema, but you can still customize those. Maybe you're adding custom on bridge, or maybe you're adding or removing fields within there. So the challenge is if you're using tools like cursor copilot, they don't know, they know your code. They don't know the exact structure of the, the exact Salesforce org that you're connected to, right?

47:38If you're a consultant, you're like connecting to 40. So these things may change literally depending on what hour or which project you're working. So really having that deep understanding of that. And you can do things like even walk on and say, plus for this response, what I want you to do is change this. I'm going to tell you, I'm going to manually add the three standard schema object that I want you to do. So what I want you to do is build a way to search for cases. And here's my specific case object, if you will. and you're going to get the results. So instead of randomly choosing fields or choosing fields that are generic out of the box, but not specific, it is the exact fields that are within that schema because you have the schema.

48:21And of course the LLM is going to do its best job to guess, but if you have the schema, it's going to do exactly what you tell it to do from a schema perspective. And that's like really cool because I think, so something I always think about whenever people build stuff is, you know, you start in that world like cursor or on your local computer and you put together little tiny bits and you're like, okay, you know, it's standing up. Now I have to go pull in all this information, right? I need to hit my Salesforce API. I need to grab all that and pull it in. I need to go to this other service and pull in all this information.

48:51And it becomes like actually bringing the context and the data from those different houses into the little prototype that you're building, because that's what you have to do to make it safe and local and to try it out. But in this world, you're describing, you know, your prototype, it lives in the house of your data. It's a first-class citizen alongside of the data. And so is that like an aha moment for developers and your experiences when they can pick it up and use it? How does that kind of change the rapidity in which people that you see can prototype? Yeah, I think it's probably more the other way, which is people, like, again, if we think about the adoption maturity curve, there's a set of folks that have been using ai tools since the absolute beginner right uh we talked about some of our friends martin woodward is one example right super cutting edge but then there's sort of the late majority in laggards they try something and if it doesn't have that context they're like this is terrible i'm going to spend all this time removing fields that don't exist like why am i spending my time cleaning up so the more it can you can just sort of have that trust by default are really just taking the uh the onus or work or the manual changes out of that layer the more they start to trust and more to have that that experience where they love where they're not spending time doing what is effectively simple uh scaffolding of crud apps right they're not spending time worrying about the infrastructure because salesforce take care of all that they just prescribe what it is and that that makes it fun where they're spending time on the more important parts versus, oh, geez, I need to copy and paste and remove these HTML components for fields that don't exist.

50:36And now the validation thing is now broken because it was the third field. And geez, now like, you know, you're just like almost want to just give up and all right, let me just delete it. Exactly. First of all, I love the Martin Woodward shout out. You know, if you're listening to this and you haven't listened to our episode with Martin Woodward, he drops a lot of really great advice. And it's a great pair for this episode, because we're talking about using agentic coding, where your code lives. And this is the same idea here, building agentic enterprise applications, where your enterprise data lives.

51:09So these are a natural pair. And I think that, you know, tapping into that same stuff, what he taught us is the same lines of what you're teaching us now. And that is ultimately about providing that safe environment, but also bringing in all of that rich context that makes the platform what it is. But I want to take a second there to pause and also, you know, talk about the, there's a lot of velocity in this adoption. There's a lot of excitement about picking it up, but we're talking about the enterprise and their skeptics. And so when you talk with a customer and maybe they are trying to wrap their head around how they would use this, or maybe even they say it's flat out unworkable for them until a certain thing changes.

51:53How does Salesforce attack those problems and what are the kinds of frameworks you all have used to make sure that this is meeting your customers where they need it? Yeah, so this is the great story that we had or just ran into. when we originally started, Agent Force for Developers, you know, VS Code extension, we want to make, because you're buying Salesforce, we're going to make the AI credits included and we really want this to be a productive experience and you're going to do, and obviously we're over the hump now. We have, you know, millions of lines of code. People that use Agent Force for Developers, it's like 20 to 25 % of our users is actually agentically built, which is awesome and that we can track this.

52:33But that's basically where we stopped. When we originally started, I was like, we need all of this data. We need, because we need to train our model. This was the Salesforce CodeGen model. And the enterprise was like, you want to use RIP that we're paying people for to train so that somebody else, our competitors can copy our features? Like, why would we ever do that? Why? And it really was the, that aha moment. Like, that's not going to realistically fly with our customers. and what also happened is because they couldn't trust it they would just use it for like hello world lorem ipsum so if you do train totally imagine you spent all this time training it and everybody's just building hello world apps now now the training set in data that you have has its own sort of uh implicit bias so it really was one of our biggest changes was and our adoption certainly grew in major ways by removing the we will not use your IP to train our model.

53:34And again, this is also just using lessons learned, but we also use the Agent Force Trust Layer. That has like data masking to make sure, prompt defense, the toxicity stuff, zero retention, which is really what we're talking about here. If we send it to an LLM, it's not sending, you know, that the LLM can't retain that data and things like an audit trail. So there's just a ton of things that customers were like, okay, this isn't just me calling chat GPT from an API. This is, you know, we had that enterprise level of governance for this data with the agent force trust layer that I can now enable.

54:09But as with all customers, this is what we expect. They're going to do a pilot. They're going to see, are they actually successful? Where does it work and not work? And based on that, those things are what really start the snowball effect of, yeah, it works great for this. but it was terrible at that. You know, really, we're spending a ton of time building UX screens. And this is one feedback that we got from one of our ISVs. They really wanted Figma. Show us how you can take Figma so we can reduce our time to market because that's the designer to developer workflow has always been a challenge.

54:42So the ability to be able to, now with MCPs, to be able to go from a Figma comp into a working version in Salesforce in just minutes is a huge, huge benefit to them. I love the idea you have being able to learn something like that from changing like a contract or an agreement or just like the terms of service. I think, you know, in this world you're describing, trust is the fuel. You can build this amazing rocket ship that can take them all the way to the moon, right? But like, no one's going to get in it if they don't believe in you and they don't think that they're ultimately going to be there for the whole ride, right?

55:16And so I think that's a really great acknowledgement. I think that's something that a lot of engineering leaders listening to this can really take away from it is that making sure that the AI products that you're building and the way that they're serving your customers is really serving them and bringing them along for the ride, protecting their best interests and recognizing that it's a big, scary world and we're all kind of like reaching and feeling in the dark in front of us and trying to figure out where it's all going to go and that you have the most resources and the biggest viewpoint on where it could go.

55:46And so being in that guiding light instead of allowing any kind and mistrust is, first and foremost, I think that that is like the absolute base foundation of building anything great in partnership with the customers. I really love that. There's another thing I really want to dig into with you because when we talked originally, got a glimpse at like a really amazing and layered feedback loop between Salesforce and how y 'all have learned to build and how you meet your customers where they are. So there are a few things that you've called out, Like there's stuff like internal dog fooding or, you know, drinking your own champagne if you want to be really bougie about it.

56:23Yeah, there's all the customer previews that exist. There's all the developer surveys that you send out. And also a really cool thing called Devlog Diaries that I really love to learn more about. So, you know, as like a software leader, you're inventing a new category, Dan. How do you roll all of those signals into a concrete roadmap decision? Yeah, you know, that's always the challenge, right? because you want to have that quantitative view. What's happening in the market? How big is this? What is everybody doing? And certainly there are a number of studies that do like the Stack Overflow Developer Survey.

56:56JetBrains does their own version as well. We can start understanding what people are doing. And even within those, about three out of four customers are already using AI. So it's like, what are they using them for? What works? What doesn't? And again, you sort of start moving from the quant to the qual. When we're releasing this new version of our enterprise vibe coding tools for Age of Force for developers, we started, you know, dogfooding, doing, you know, customer surveys. But that's good when people like try it out and just give us feedback. And it's really the people that started using and continue using it, that's great.

57:32The people that stopped, we want to know, well, why? And it turns out like some of the use cases, and this is for customers as well, it's like, well, I only code a couple of times a month. And it's really like, you know, this app is sort of in support mode. and you don't realize not all developers are nine to five developers right i support 10 applications so i wait until somebody files a bug and then i'm going to use your agentic app tools so really think about what are the things they need well what does that person need they actually need the ability to explain what's happening so uh we do slash explain explain what does this do geez i wrote this a year ago or somebody that left the company wrote this three years ago I now need to add the ability to validate, you know, don't let them submit without this required field.

58:16I don't even remember how the validation thing works. So you can ask and have that conversation within code and really just start to get to know developers and really ISVs as well. This is one of the most powerful things that Salesforce does is we have big and, you know, they call them unicorn ISVs that are built on Salesforce. And those are ones that are valued at more than a billion dollars. and really think about the platform for ISVs. And we, you know, we'll go on site and do events where we ask them, what are the most important things? How can we make you successful? And really think about the customer first.

58:51For the Dev Diary, man, there's just so many great examples where you think your feedback is going to be about the product or feature or, yeah, I like that, they like that. You don't realize just how many things that they have to do. So it's like, we always start like our tutorial in our docs, like, well, you've got everything configured. Let's get started. Then you see somebody try and do it. Developer wants to go through. It's like, okay, so NPM install this package. They hit NPM in a command line. And you're just like watching these screenshots and listening to them. NPM isn't installed. And I don't know why.

59:28It's like, okay. So they go check and they have installed it, but they installed it from brew, which didn't install it on the command line. and then it's like oh well i'll go change it and just like copy at it into zish but they don't have zish on this machine they have they have bash and then they're like okay fine i got this installed and i just you know decided to install it it's the wrong version of node and so the library they have doesn't work with that one and wow what you're describing is so triggering for all all javascript high script developers that exist myself and myself included and it's it's you don't realize it's like hey what we want is the feedback on the person it's like no No, setup, setup, setup.

1:00:06It is such a pain to get started with software. I'm certainly not picking on Node.js. Python and Python virtual environments are... They all have their quirks. Quirks is not their... A nice way of putting it. Yes, a nice way of putting it. So as just kind of one example, how did that feed into some of our feedback? We wanted to build CodeBuilder, browser-based tool, zero install. You're not installing Node. You're not installing Python. You're not installing VS Code. You're not installing our Salesforce extensions. You're not installing your CLI. You're not installing Salesforce MCPs. It's all just there.

1:00:39Then there's no other vibe coding experience that I can think of right now that even compares to that. They all have some level of like, oh, copy this command or oh, get something local. So that's really the cool part about it being in this contained world. Yeah. And look, the best and how does that start? It starts with talking to customers and getting real world examples, which is getting started with stuff and configuring software is just a real pain. how can we make the lives easier and that absolutely drives adoption and access which is like is one button to get this thing you know instantly ready just to make your lives that much easier when you talk about your customer segments and you have folks obviously that don't have a lot of experience using code they're the more traditional drag and drop or low code users and you also have folks that are somewhere between that and an engineer like they're more aspirational They're technical, comfortable in a command line.

1:01:32And then you have these full-fledged unicorn ISVs, you know, billion-dollar companies that have built themselves on top of you and are creating value for customers. And those are three very distinct segments. But something that's happening right now is that I think a lot of those lines are starting to blur. And what has surprised you about how those groups are adopting these tools? Yeah. So to give you an example of one of the ISVs we work with, Encino, they call themselves the bank operating system. So if you work with like Wells Fargo and US Bank, these are really big banks that use Encino for things like your home loan and your mortgage, right?

1:02:13great software all built on the Salesforce platform. So you would think, and they are absolutely hardcore, amazing developers, but one of the things they wanted to do was, how do we just get feedback on new products, features, or capabilities? So they partnered with their product folks with a UX designer. The UX designer would basically, that was their dream. It's like, look, we're just doing this to get feedback. It just needs to be a prototype. And that's really where some of these Vibe coding tools would do, which is start with the Figma, get a click through, you know, they set up a meeting and just ask the person, the loan officer, is this the right tool?

1:02:49Is this the right sort of feedback? And those are just examples of how when you would traditionally think, oh, they must be completely engineering, even within their organization, they're experimenting for ways that they can expedite getting to that product market fit and getting that feedback for customers to make their software that much better. So when it is ready to hand off, we're not handing off something that no customer wants. They're like a great example of where they're just so customer focused to get that right feedback in as quickly as possible. I love that of using it as a way to really tighten the feedback loop.

1:03:25I think that's critical in building software safely, especially for customers and really sensitive industries. Like you just use banking as a really great example Being able to actually vibe code it into this little shared experience and bring it right to the customer is, it's like, that's like the first class experience going to the top of our talk of like what this is all about. And as this continues to evolve, do you think that those worlds will continue to blur and those lines will continue to go away? Because that's the trend I think everyone is seeing. But, you know, what do you think the future might hold?

1:04:02Yeah, I think absolutely. You are going to see the sort of democratization of app building. And I think some of the other areas that are, for lack of a better word, sometimes neglected too, is just feedback and iteration, which is, hey, did I start this to build an app or did I start this to have an outcome? What is the outcome we're trying to drive? And maybe there's an easier way to do that. And then how do I measure success with things like product analytics? so that I know and can, you know, vibe the next changes based on that. Like, ooh, geez, our shopping carts are being abandoned. What are the ways that we can reduce the mean time to learn within there?

1:04:43So really, it's sort of like democratizing all those things. You know, sometimes you ask, it's like, well, geez, if you want to look at analytics, you got to be a data scientist. Well, maybe you don't. You can start asking natural language questions of your analytics platform. So both the developer and an end user or a product manager or a business line manager can ask questions about their business. What would you recommend? What would you do? Here's what our app is doing. And really better understand things that we haven't thought of before as possible as like, well, you can export all the data into a CSV file and load it in Google Sheets.

1:05:17There's got to be a better way. There's got to be a better way, right? Exactly. Dan, this has been an amazing conversation, like a really great view into how Salesforce is approaching this new category of coding, you know, enterprise vibe coding. It takes two very opposite worlds and it brings them together. And ultimately, it makes that wild, wild west experience of agentic coding a little less wild. And I'm really excited to see what people are going to build on top of Salesforce and the tools you're making available. And before we wrap up, where can our listeners, if they've been following along and they're kind of curious, where can they go to learn more about your work and what Salesforce is building?

1:05:56So our Agent Force for Developer Tools is now in a preview mode. That means anybody watching this, like today, can do this. By the time you launch, this will be actually GA'd. So you go into VS Code Marketplace, install the Salesforce extensions for VS Code, connect to an org. You don't need a credit card. You don't need anything. Again, we include all that stuff to really get you started. Or just developer.salesforce.com. Cool. Well, we're going to include some links so people can go check it out. And this is, like I said, I've been a really amazing tour through some of the problems y 'all are tackling.

1:06:26So thank you so much, Dan, for joining us on Dev Interrupted. It's been so fun. And to you listening, thank you for joining us for the conversation and for tuning in. That's it for this week's Dev Interrupted. But the conversation doesn't stop here. Be sure to find Dan and I on LinkedIn. Continue the conversation. Ask any questions you might have because we're really curious to know how you've been building and how you might use a tool like this. So we'll see you next time.