Beyond Scheduled Tasks: Automate Your Operations with Claude Managed Agents | Episode 110 | Episode 110

WEBVTT
00:00:22.329 --> 00:00:26.250
Today we're going to be talking about building managed agents in Claude.
00:00:26.890 --> 00:00:29.530
This is a pretty cool topic, so stick around.
00:00:31.049 --> 00:00:35.129
Once again, welcome back to the Digital Customer Experience podcast with me, Alex Turkovich.
00:00:35.369 --> 00:00:43.370
So glad you could join me here today and every week as we explore how digital CS and AI can help enhance the customer and employee experience.
00:00:43.530 --> 00:00:50.250
My goal is to share the insights that my guests and I have learned over the years so that you get what you need to evolve your own digital program.
00:00:50.570 --> 00:00:54.409
If you'd like more resources, head over to digitalcustomer success.com.
00:00:54.569 --> 00:01:04.650
There you'll find access to a chatbot that's trained on this content and get information about the Digital CX masterclass where I teach you how to execute and thrive in Digital CX.
00:01:04.890 --> 00:01:06.969
For now, let's get started.
00:01:08.010 --> 00:01:12.170
Hey, Edward Alex jumping in here before we start this episode.
00:01:12.409 --> 00:01:19.049
I wanted to jump in real quick and talk about the fact that what I'm doing today isn't Claude.
00:01:19.290 --> 00:01:25.049
In fact, I think all of it is Claude-based and using managed agents from Anthropic.
00:01:25.209 --> 00:01:32.890
That said, most platforms out there these days have this sort of feature where you can build agents.
00:01:32.969 --> 00:01:35.289
I know you can do that with OpenAI.
00:01:35.530 --> 00:01:40.329
I know you can do that with Perplexity Computer, for instance.
00:01:40.569 --> 00:01:45.849
A lot of different platforms now have this kind of agent-building capability.
00:01:46.009 --> 00:01:56.969
But what I lay out in this episode holds true no matter what platform you're using, because fundamentally agents work in a very similar fashion across the board.
00:01:57.129 --> 00:02:06.810
They all need context, they all need an environment to operate in, they all need to understand when they should be kicking off, what their core instructions are, and those kinds of things.
00:02:06.969 --> 00:02:07.849
That doesn't change.
00:02:07.929 --> 00:02:12.650
The nomenclature changes slightly depending on the platform you're using.
00:02:12.810 --> 00:02:16.009
But fundamentally speaking, it's all the same stuff.
00:02:16.170 --> 00:02:24.090
And so this episode is applicable to you, whether you're a clawed user like I am, or whether you're using codecs or computer.
00:02:24.250 --> 00:02:26.250
So with that said, let's dive right in.
00:02:26.569 --> 00:02:28.170
Hey, my name is Alex Turkovich.
00:02:28.330 --> 00:02:30.010
Welcome back to the Digital CX podcast.
00:02:30.090 --> 00:02:35.290
This is episode 110, and we have a pretty cool episode in store for you today.
00:02:35.450 --> 00:02:46.570
I'm gonna probably spend a few future episodes, including this one, where we're kind of kicking off this project of standing up Claude Managed Agents.
00:02:46.730 --> 00:02:57.290
Now, if you're a regular listener to this show, you'll know that I don't know, several months ago I talked a lot about scheduled tasks in Claude.
00:02:57.770 --> 00:03:17.770
So if you are a heavy Claude user, scheduled tasks was a great way to start getting into agenc work and working with Claude in a way that was agenc because these scheduled tasks would, you know, kick off on a regular basis and do work on your behalf without you having to basically kick off that workflow.
00:03:17.930 --> 00:03:24.650
That is, by in essence, the the definition of what agentic AI really is for the most part.
00:03:24.730 --> 00:03:26.650
There's some more detail there, but we won't get into that.
00:03:26.810 --> 00:03:55.850
I have recently been playing a lot with Claude Managed Agents, which was released a few months ago and takes this to a whole nother level because what we're able to do with managed agents, which is really more on the back end of Claude, is pretty phenomenal because you start thinking, you know, everybody's kind of talking about, okay, I've got this team of AI agents and I've got this group of AI agents working together and all that kind of stuff.
00:03:55.930 --> 00:04:02.810
And so what I figured I'd do is, as I'm building this up for my own business, is kind of take you along for the ride.
00:04:02.969 --> 00:04:09.689
And so today we're going to start at the ground level and talk a little bit about what managed agents is.
00:04:09.930 --> 00:04:18.250
And then we're going to dig into a little bit more about the use cases and how I'm planning on using this.
00:04:18.490 --> 00:04:23.769
And of course, I would love to solicit your feedback on are you using managed agents today?
00:04:23.850 --> 00:04:24.569
Are you not?
00:04:24.730 --> 00:04:26.569
If you are, what are you having them do?
00:04:26.730 --> 00:04:29.449
How are you having them talk to each other and all that kind of stuff?
00:04:29.689 --> 00:04:34.730
So before we get more into this, let's talk a little bit about what the heck I'm talking about.
00:04:34.810 --> 00:04:45.049
Now, if you are listening to this instead of watching it on YouTube, for example, I'm going to try to be as super descriptive as possible so that you can kind of follow along.
00:04:45.289 --> 00:04:53.049
But what we're talking about here is not in cloud.com or your cloud desktop app.
00:04:53.370 --> 00:05:00.409
These are essentially API-based agents that you can set up on the back end of Cloud.
00:05:00.490 --> 00:05:13.609
And specifically, if you haven't even been there, platform.cloud.com is a pretty cool place to poke around because it is where a lot of the backend stuff that you work on every day kind of lives.
00:05:13.689 --> 00:05:22.569
You know, if you are a regular cloud user and you you haven't dug into platform at all, I would highly recommend you take a weekend and go do that.
00:05:23.049 --> 00:05:28.250
Um, but today we're going to talk specifically about managed agents in platform.
00:05:28.329 --> 00:05:31.769
You get there by going to platform.cloud.com.
00:05:32.009 --> 00:05:36.009
You use your login and then go to the managed agents tab.
00:05:36.169 --> 00:05:55.769
Now, one thing that is pretty important when it comes to starting to work with this stuff is let's say, for example, that you are a pro or a max cloud subscriber, the thing that you want to avoid is just going nuts on it because we're not actually using usage towards those subscriptions.
00:05:55.849 --> 00:05:59.689
We're using API based token usage.
00:05:59.769 --> 00:06:06.729
And so you do have to fund the, you know, you do have to fund your account so that you can start using tokens.
00:06:06.889 --> 00:06:19.769
And so that's where once we start building these agents and they start nesting under each other, that's where selecting the model type is going to be very, very important so that you're not chugging through tokens unnecessarily.
00:06:19.849 --> 00:06:28.889
I know it would be great to have everything, you know, running on uh, you know, Opus or Fable or whatever, but that's a quick way to run up a pretty big bill.
00:06:29.049 --> 00:06:30.649
So you want to try to avoid that.
00:06:30.810 --> 00:06:36.409
Now, let's talk a little bit about what the components are of these managed agents.
00:06:36.729 --> 00:06:38.810
First off, you have the agent itself.
00:06:39.049 --> 00:06:42.409
The agent is essentially a set of instructions, right?
00:06:42.729 --> 00:06:50.569
It is a hopefully a pretty narrow task that you want this agent to accomplish on a regular basis.
00:06:50.889 --> 00:06:53.209
Let's uh give you a couple examples.
00:06:53.449 --> 00:07:04.409
One is, I don't know, reading your email, looking through your email, highlighting things that you need to respond to, or maybe flagging certain emails that it wants you to look at.
00:07:04.569 --> 00:07:05.930
So that would be one example.
00:07:06.089 --> 00:07:10.810
You know, another small example would be well, let's take this podcast, for example.
00:07:10.969 --> 00:07:32.490
I'm going to be building an agent that once the, you know, once the audio is ready and the transcript is ready, it's going to take that transcript and turn it into a draft for the show notes, for example, as well as a draft for the YouTube description, as well as chapters, you know, a set of chapters for that.
00:07:32.569 --> 00:07:33.609
And so it's kind of like this.
00:07:33.769 --> 00:07:37.370
I'm going to have one agent that does the package of that essentially.
00:07:37.689 --> 00:07:42.889
I am going to implement a whole series of other agents that are kind of wrapped around this business.
00:07:42.969 --> 00:07:47.370
And I'll actually kind of share with you what that is in a second, but that's essentially what an agent is.
00:07:47.609 --> 00:07:48.490
It's a task.
00:07:48.729 --> 00:07:53.689
You want your agents to be somewhat focused on specific tasks.
00:07:53.769 --> 00:08:01.049
In other words, you don't want one agent to do too many different things because you can create a multitude of agents, right?
00:08:01.289 --> 00:08:16.250
And what I will be doing is creating a multitude of agents that then essentially report to an overall agent or a kind of a chief of staff agent, essentially, that then takes the outputs of all those agents.
00:08:16.329 --> 00:08:19.849
And that's the one that I will be interfacing with on a regular basis.
00:08:20.009 --> 00:08:20.969
So that's the agent.
00:08:21.129 --> 00:08:24.009
The other kind of definition to know here is environment.
00:08:24.169 --> 00:08:30.569
When you go to set up these managed agents, you're going to want to pay attention to the environment in which they run.
00:08:30.729 --> 00:08:38.570
And so you can set these environments up and they allow you to restrict what the agent running on that environment has access to.
00:08:38.730 --> 00:08:47.129
It allows you to restrict, you know, what tools it has access to and and what areas of the internet it has access to.
00:08:47.289 --> 00:08:50.730
So that's essentially, yeah, I mean, it's pretty self-explanatory.
00:08:50.889 --> 00:08:55.129
There is in Managed Agents also the concept of a credentials vault.
00:08:55.289 --> 00:08:59.529
So invariably, these agents are going to want to work with your other tools.
00:08:59.689 --> 00:09:06.009
And so if you if you need it to work with others, other tools, you can create a vault of credentials.
00:09:06.169 --> 00:09:13.129
So let's say maybe your HubSpot API key is in there, or your Stripe API key is in there.
00:09:13.289 --> 00:09:23.289
And of course, just like with any API integration, you can restrict and limit what each one of those API keys gives, eventually gives the agent access to.
00:09:23.449 --> 00:09:25.289
So you have a credentials vault.
00:09:25.529 --> 00:09:32.009
Memory stores within managed agents is the place where your agents are going to be storing their memory.
00:09:32.169 --> 00:09:38.409
And so what you will have over time, the more these agents run, is a memory of what they've done in the past.
00:09:38.730 --> 00:09:47.529
And those agents will then be able to essentially self-improve upon themselves based on what those memory stores contain.
00:09:47.769 --> 00:09:49.289
So that's super, super cool.
00:09:49.610 --> 00:09:54.569
And the last little definition basically that you need to know about is um sessions.
00:09:54.730 --> 00:10:01.529
Sessions is basically like your chat in uh chat GP, you know, chat GPT or cloud or whatever.
00:10:01.689 --> 00:10:09.049
But it's it's you know, one when a session is running, that is one session that an agent is running for you, right?
00:10:09.129 --> 00:10:15.049
So if you have 10 agents, they run, they each run once a day, that means you're gonna have 10 sessions running essentially.
00:10:16.009 --> 00:10:24.250
So that is the kind of definitions element of you know, what all the the components of these agents are.
00:10:24.329 --> 00:10:34.250
And so when you go to build these agents, which is super easy because you can just prompt it out, and I'll I'll kind of share what I've done to do that with you.
00:10:34.409 --> 00:10:43.210
When you build these agents, you're then going to also define what environment they're in and what credentials vault that they use.
00:10:43.370 --> 00:10:50.970
So that gives you then the control essentially of what they have access to and then how they integrate with those things.
00:10:51.210 --> 00:12:30.519
Now, staring at a blank screen about to create agents can be a kind of a daunting thing, right?
00:12:30.680 --> 00:12:42.200
And so uh, you know, I've been steadying up on this for quite a long time because you know, these these are the kinds of things that I like to really dig into and and get into YouTube university on.
00:12:42.360 --> 00:13:06.279
And uh a couple of things that stood out to me when I was researching this is there was a few, there were a few people who suggested that you essentially do an audit of yourself and your use of Claude and your use of AI to understand what would be a good candidate for an agent.
00:13:06.440 --> 00:13:07.879
And so I did exactly that.
00:13:08.040 --> 00:13:12.680
And I'm gonna give you, I'm gonna, I'm gonna read you out the prompt that I gave Claude.
00:13:12.759 --> 00:13:17.080
I'll also put this in the show notes so that you can go copy it if you would like.
00:13:17.480 --> 00:13:26.680
But my goal here was, you know, I'm always trying to automate what I'm doing here with the podcast and the masterclass and you know, the newsletter and all those kinds of things.
00:13:26.920 --> 00:13:37.320
While my authentic voice needs to be there, and I spend a lot of time writing and putting posts together and obviously recording these podcasts.
00:13:37.560 --> 00:13:48.840
The thing that I need efficiency on is like emails and and you know, just the day-to-day stuff, creating drafts for me and and and doing a variety of different things.
00:13:49.000 --> 00:14:08.519
And so what I wanted to do was basically have Claude analyze my usage of Claude as well as what scheduled tasks I have running currently and all the other things that I do on a regular basis to provide with me a list of suggestions for agents to create.
00:14:08.600 --> 00:14:10.519
And so here's the prompt that I used.
00:14:10.840 --> 00:14:27.320
I said, I'm wanting to automate my business via a series of claude-managed agents doing a variety of tasks that are currently being done either manually or via scheduled tasks in co-work or routines in Claude Code.
00:14:27.720 --> 00:14:37.320
I want to be quite niche with those agents so that tasks can be delegated to a high degree of detail across those agents.
00:14:37.720 --> 00:14:48.840
That means I'll also need some agents that coordinate with each other to get broader tasks done by their subteams, much like a team structure works in the workplace.
00:14:49.080 --> 00:14:57.320
I would like you to do an audit of my business based on conversations I've had with Claude and tools that you have access to.
00:14:57.560 --> 00:15:05.159
Then create a detailed list of agents you suggest be created to help automate and coordinate this work.
00:15:05.480 --> 00:15:10.440
Also, make suggestions for additional tools needed to execute this work.
00:15:10.600 --> 00:15:16.680
However, try to manage within the tools that we already have in our tech stack.
00:15:16.840 --> 00:15:26.600
Ask me any clarifying questions you have until you have 100% certainty of the task you need to accomplish and that you'll execute it to a high degree of accuracy.
00:15:26.840 --> 00:15:32.120
So that is the prompt that I will include in the show notes, but that is the prompt that I gave it.
00:15:32.279 --> 00:15:41.720
It asked me two rounds of questions, mainly around uh, you know, more finite scope of what I wanted it to, uh what I wanted these agents to be.
00:15:41.879 --> 00:15:49.000
It also asked me whether I wanted to exclude certain things that weren't really in the realm of what I do, but I just asked Claude about.
00:15:49.080 --> 00:15:51.639
Of course, I, you know, I asked Claude about a bunch of stuff.
00:15:51.720 --> 00:15:53.800
So I didn't include any of that.
00:15:54.040 --> 00:15:58.840
It asked me how much autonomy these agents should have.
00:15:59.080 --> 00:16:09.879
And I basically suggested that we do somewhat of a tiered, you know, set of autonomy behaviors based on the risk involved in some of this.
00:16:10.360 --> 00:16:20.040
Um yeah, and so, you know, it asked me then a second round of questions around what manual work that I do that it may not uh be able to see.
00:16:20.120 --> 00:16:25.800
And so some of it was like accounting related and administrative related.
00:16:25.960 --> 00:16:28.519
And it asked me about budget, so that was very important.
00:16:28.680 --> 00:16:33.320
Obviously, when you're running this kind of stuff, you don't want it to go super, super, super wild.
00:16:33.399 --> 00:16:38.680
And so I gave it kind of this parameter of budget that I wanted it to stick within.
00:16:38.920 --> 00:16:48.200
So then what it did is it essentially spit out a suggested blueprint for me and my uh agents.
00:16:48.680 --> 00:16:53.879
Now, what it did is it gave me a whole list of the things that I do on a regular basis.
00:16:54.040 --> 00:16:57.320
It gave me uh, you know, kind of some operating rules.
00:16:57.399 --> 00:17:09.480
So, like the risk tiers that we talked about, things that it would just do automatically for me versus things where it would like just draft things for me and things where it wouldn't touch anything at all.
00:17:09.799 --> 00:17:14.119
Then it started to give me essentially an org chart.
00:17:14.279 --> 00:17:22.680
And so when you think about, you know, uh a podcast like this and a show like this, there are a variety of different things that go into it.
00:17:22.839 --> 00:17:30.039
Um, there's much more behind the scenes that goes into this than just me sitting here yapping in front of a camera.
00:17:30.200 --> 00:17:35.799
And so what it did was it basically gave me the parameters of what a chief of staff would be.
00:17:35.960 --> 00:17:44.119
And so this is a chief of staff that is over a variety of different work streams and kind of dictating a certain set of things.
00:17:44.279 --> 00:17:49.480
And then it prescribed a series of uh desks, if you will.
00:17:49.720 --> 00:17:59.000
So, you know, one of them was a content studio, and so the the agents within the content studio, it it recommended a topic scout.
00:17:59.240 --> 00:18:12.759
So a scout that would go out and look at uh you know things that are being talked about in CS, happenings in CS, and then it would cross-reference it with my knowledge base that I've built around this show and everything I've talked about.
00:18:12.920 --> 00:18:18.839
It gave me, you know, it per kind of social channel, it gave me a writer.
00:18:18.920 --> 00:18:24.279
So like somebody who would uh an agent that would basically draft things for me.
00:18:24.440 --> 00:18:29.079
I don't think I'll ever get to the point, by the way, where I have an AI just post stuff for me.
00:18:29.240 --> 00:18:33.000
Like drafting, I can do, but straight up posting, I don't think so.
00:18:33.159 --> 00:18:34.680
It gave me a clip producer.
00:18:34.839 --> 00:18:41.639
So I already use a tool called Opus Clip to create clips for me of uh fully published episodes.
00:18:41.799 --> 00:18:55.079
However, this clip producer then does some analysis on those clips and helps to or makes recommendations for which ones that should be posted and then also what kind of captions should uh go along with that.
00:18:55.319 --> 00:19:00.519
Uh it recommended a an agent for thumbnail and graphics creation.
00:19:01.079 --> 00:19:04.839
It uh recommended an agent for a queue scheduler.
00:19:05.000 --> 00:19:08.279
So, you know, queuing up episodes and really planning those out.
00:19:08.439 --> 00:19:14.919
Again, it seems like a small task, but in the aggregate, when you do it over and over again, it's a it's a it's kind of a big thing.
00:19:15.799 --> 00:19:18.359
And then also like a monthly trend scout.
00:19:18.439 --> 00:19:23.319
So, what are the monthly trends that it's kind of seeing out there that we might want to talk about?
00:19:23.559 --> 00:19:25.159
And that's just the content studio.
00:19:25.240 --> 00:19:28.839
There were 36 total agents that it recommended.
00:19:29.000 --> 00:19:30.439
So that was the content studio.
00:19:30.599 --> 00:19:36.679
There's a podcast desk, which one of them that it suggested, which is quite interesting, is a pitch triage.
00:19:37.079 --> 00:19:47.719
I can't tell you how many emails I get from like podcast placement services about, you know, people that should be on the podcast.
00:19:47.879 --> 00:19:53.559
And look, I'm I'm all for folks reaching out and saying, hey, I've got this cool thing that I'm working on.
00:19:53.719 --> 00:19:55.000
Can I be on the podcast?
00:19:55.159 --> 00:19:56.519
I love that kind of stuff.
00:19:56.839 --> 00:20:07.639
I pretty much flat out ignore anybody who uses like a podcast pitch service because there's a ton of them out there, and I get probably five of them a day, and I just ignore them.
00:20:07.799 --> 00:20:12.279
And so it suggested an agent that actually looks at those pitches.
00:20:12.679 --> 00:20:17.240
And if there are guests that do make sense, okay, maybe I can engage those.
00:20:17.399 --> 00:20:19.079
But oh man, it's crazy.
00:20:19.240 --> 00:20:31.399
One of them is a guest coordinator, so an agent that actually handles some of the coordination that happens before uh recording an episode and after, show notes writer, knowledge base librarian.
00:20:31.559 --> 00:20:37.240
So, you know, there's all these kind of sub-agents that do really minute things.
00:20:37.399 --> 00:20:41.159
One of them is a growth or another desk is a growth desk.
00:20:41.319 --> 00:20:49.240
So that has, you know, agents that are working on funnel and nurture campaigns and kind of more marketing related things.
00:20:49.319 --> 00:20:50.759
Then I have a revenue desk.
00:20:50.839 --> 00:20:55.879
So that's like, you know, a sponsor, prospect, or sponsor account manager.
00:20:55.959 --> 00:20:59.480
I don't know if I'm gonna do an agent for that, but whatever.
00:20:59.639 --> 00:21:01.399
These are just Claude suggestions.
00:21:01.639 --> 00:21:08.199
An invoicing clerk, so somebody who takes care of some of the invoicing and sending them and following up on invoice invoices.
00:21:08.359 --> 00:21:11.719
Now for the master class, it actually made a couple of suggestions that I really like.
00:21:11.879 --> 00:21:13.319
One of them is student support.
00:21:13.480 --> 00:21:27.480
So if a student in master class needs support with certain things that are maybe more technical in nature, can't find certain things, I want to you know have an agent able to provide some base level of support there at all hours.
00:21:27.719 --> 00:21:29.959
Um, a testimonial collector.
00:21:30.039 --> 00:21:35.959
So if somebody goes through masterclass, I have a video platform that allows me to collect testimonials, super cool.
00:21:36.199 --> 00:21:37.559
Takes manual effort to do that.
00:21:37.639 --> 00:21:40.759
So maybe I have a testimonial collector that does that for me.
00:21:41.000 --> 00:21:42.039
Product operations.
00:21:42.519 --> 00:21:46.519
It takes a lot to maintain a course like that on the back end.
00:21:46.599 --> 00:21:51.559
So you have you know registrations and all kinds of different things that happen on the back end.
00:21:51.639 --> 00:21:55.480
And so basically having somebody to monitor all of that.
00:21:55.639 --> 00:22:03.159
And then lastly, it's it's back office stuff, it's you know, kind of bookkeeping and spend auditor and all those kinds of things.
00:22:03.319 --> 00:22:23.319
So it, you know, again, you can do this as well by using a prompt or something modified off of my prompt to have Claude do an audit of your business and your daily life and what it is that it feels like it could do a good job of with an agent.
00:22:23.559 --> 00:22:27.240
And from there, it's about creating these agents.
00:22:27.480 --> 00:22:32.119
And I've started to create a few of these that have made sense.
00:22:32.279 --> 00:22:34.039
I'm not gonna implement all of those.
00:22:34.119 --> 00:22:42.279
I think that would be a little bit overkill, but I think you can tell from what I just talked about that there are certain ones that I think you know could be quite good.
00:22:42.359 --> 00:22:54.439
I do want to include a few more that help me triage my email a little bit better, help me triage my calendars, yes, multiple calendars a little bit better, help me manage just that day-to-day a little bit.
00:22:54.599 --> 00:23:00.119
One of the things that I'm really sad about is that, you know, there isn't much out there for LinkedIn.
00:23:00.439 --> 00:23:04.919
I know there's some platforms that that do kind of work with LinkedIn.
00:23:05.079 --> 00:23:19.799
And I have, you know, I do have a LinkedIn like post automator tool that I use that is quite good and does have have an MCP, but that's really more for pushing content out, less so about engagement and communication.
00:23:20.119 --> 00:23:27.000
Now, I think that's actually kind of a good thing with LinkedIn because it's hard to be spammy in LinkedIn.
00:23:27.399 --> 00:23:35.399
It's hard to, you know, unless you're using some kind of you know computer use agent or whatever.
00:23:35.559 --> 00:23:38.679
LinkedIn makes it really, really hard to be spammy on LinkedIn.
00:23:38.759 --> 00:23:47.959
And I think that's generally a good thing because if agents could do, you know, all kinds of different marketing y things, I think it would kind of erode LinkedIn a little bit.
00:23:48.199 --> 00:23:52.359
All of that aside, that's how I'm planning on using management.
00:23:52.759 --> 00:23:56.519
Managed agents specifically for this business.
00:23:56.679 --> 00:24:08.839
Now, when it comes to a CX perspective, my mind just goes nuts with all of the different use cases that you could use managed agents for in a CX environment.
00:24:09.159 --> 00:24:12.439
Think of customer success managers.
00:24:12.519 --> 00:24:18.599
I mean, we've we've all been talking about QBR prep and those kinds of things forever.
00:24:18.839 --> 00:24:32.199
I think a couple of the things that an agent can really help with is the monitoring of accounts, monitoring for signs of trouble and churn, monitoring for wins, things that customers are doing well.
00:24:32.439 --> 00:24:53.000
And so if you're in an environment that does allow you to integrate with, you know, Claude, I would highly recommend using some managed agents and some very specific ones per CSM so that they can manage their book of business in an agentic type of way.
00:24:53.240 --> 00:24:59.559
So what I would what I would suggest is you you create essentially a chief of staff per CSM.
00:24:59.719 --> 00:25:14.359
And that chief of staff has access to these sub-agents that monitor their book of business, monitor their renewals, monitor their upsells, monitor for signs of trouble, monitor for adoption trends, monitor for upsell opportunities.
00:25:14.599 --> 00:25:18.519
You know, I mean, we we can go nuts with this stuff, really.
00:25:19.240 --> 00:25:39.079
The point, though, is giving your CSMs some breathing room when it comes to digging through reports and giving them the lay of the land, maybe on a daily basis, where you know, they know what's happening across their book of business based on what your business's specific criteria is.
00:25:39.240 --> 00:25:42.119
Now, I know a lot of CSPs kind of do some of this.
00:25:42.279 --> 00:25:46.519
I know there's a lot of evolving technologies that kind of do this out of the box.
00:25:46.599 --> 00:25:49.799
However, they may not be connected to your entire tech stack.
00:25:49.959 --> 00:25:51.719
There may be some different things happening.
00:25:51.799 --> 00:26:00.199
There may be some environmental things where you want to specifically ask about certain things that maybe your CSP doesn't have access to or whatnot.
00:26:00.439 --> 00:26:03.959
This would be a really great way to automate that for your CSMs.
00:26:04.119 --> 00:26:12.279
As a leader, I find Claude to be incredibly helpful to get me that overarching high-level view of my entire business.
00:26:12.519 --> 00:26:18.039
So looking at it from a management perspective, what are certain CSMs doing well?
00:26:18.199 --> 00:26:19.480
What are they not doing well?
00:26:19.719 --> 00:26:23.399
You know, I manage a support org, I manage an implementation org as well.
00:26:23.480 --> 00:26:34.439
And so, you know, I'm going to be using these managed agents to manage stalled implementation projects, uh, for example, or um, you know, customers that are graduating implementations.
00:26:34.519 --> 00:26:39.159
So I can reach out and say congratulations and welcome them and do all that kind of stuff.
00:26:39.559 --> 00:26:47.399
All the stuff that's really hard to do manually and take a lot of effort to do manually will now be able to build these agents around.
00:26:47.559 --> 00:26:50.439
And sure, we've kind of had this ability for a little while.
00:26:50.519 --> 00:26:59.240
And I've I have quite a few scheduled agents set up or scheduled tasks, I should say, set up in Claude Cowork already that do some of this stuff.
00:26:59.399 --> 00:27:12.119
However, pulling it all together in a set of managed agents gives me a sense of coordination between those managed agents, not just separate tasks firing off and creating kind of more noise.
00:27:12.359 --> 00:27:18.199
This gives me, through my chief of staff agent, gives me a centralized place to look at this stuff.
00:27:18.439 --> 00:27:22.439
So, look, I'm going to be building some of these things in the coming weeks.
00:27:22.519 --> 00:27:27.480
I'll take you along for the ride because I'm a big fan of like building in the open and sharing this kind of stuff.
00:27:27.639 --> 00:27:30.679
If you've played with managed agents in Claude, let me know.
00:27:30.759 --> 00:27:38.519
We'd love to hear what you've been building, what you've been working on, so that I can benefit from that and maybe pass along some of those things as well.
00:27:38.679 --> 00:27:43.879
I know there's a bunch of folks who've been building stuff with like HubSpot agents as well and whatnot.
00:27:44.039 --> 00:27:49.639
So if you're building agents elsewhere, let me know as well and how that's been working for you.
00:27:49.799 --> 00:28:01.079
If this is something where you are kind of mondo confused and don't know where to go and don't know what to do, I will be doing some screen shares in the coming episodes that walk you through this kind of stuff.
00:28:01.319 --> 00:28:07.480
Because I mean, I'll be honest with you, setting up a scheduled task in Claude is a relatively easy thing.
00:28:07.639 --> 00:28:11.799
When you get into the platform side of things, it becomes a little bit more technical.
00:28:11.959 --> 00:28:14.279
Now, Claude can help you through all this.
00:28:14.519 --> 00:28:16.919
It's totally doable, even as a layperson.
00:28:17.240 --> 00:28:19.480
You don't need to know any code or anything like that.
00:28:19.639 --> 00:28:26.119
But it does get a little bit more technical, especially if you're working with God, Gmail and Google and all that kind of stuff.
00:28:26.199 --> 00:28:28.519
Like the API keys get a little bit weird.
00:28:28.759 --> 00:28:31.240
So anyway, let me know your thoughts.
00:28:31.399 --> 00:28:37.240
If you're working on this stuff, I'd love to hear from you and love to share my experiences with you as well.
00:28:37.559 --> 00:28:39.240
I hope you've enjoyed this episode.
00:28:39.319 --> 00:28:43.559
I hope it's given you something to think about in terms of how to automate things a little bit more.
00:28:43.719 --> 00:28:46.279
And we'll catch you next week on the next one.
00:28:46.439 --> 00:28:47.240
Have a good day.
00:28:47.399 --> 00:28:50.599
Thank you for joining me for this episode of the Digital CX Podcast.
00:28:50.679 --> 00:28:55.399
If you like what we're doing, consider leaving us a review on your podcast platform of choice.
00:28:55.480 --> 00:28:56.119
It really helps.
00:28:56.279 --> 00:29:09.000
Don't forget, digitalcustomer success.com is where you can find extra resources, a chat bot trained on this show's content, and the Digital CX masterclass that helps you master digital and AI in CX.
00:29:09.159 --> 00:29:10.439
My name is Alex Turkovich.
00:29:10.599 --> 00:29:13.719
Thanks again for joining, and we'll see you next time.