Chain of Thought | AI Agents, Infrastructure & Engineering

If your agent's memory lives inside one model provider, switching models or harnesses means starting over. You need portable memory - yet when switching agent memory between models, you can swing accuracy by thirteen points or more, depending on which model reads them back. This episode is sponsored by Walrus.

Show Notes

If your agent's memory lives inside one model provider, switching models or harnesses means starting over. You need portable memory - yet when switching agent memory between models, you can swing accuracy by thirteen points or more, depending on which model reads them back.

Kimberly Logan, Head of Product at the Walrus Foundation, where she builds Walrus Memory, joins Chain of Thought to discuss how to build portable and verifiable memory for AI agents - and why Walrus's decentralized storage network has proved an apt primitive. She and host Conor Bronsdon get into why model lock-in is a memory problem, what people use agent memory for beyond coding, how you prove what happened to your data, and why Walrus doesn't publish memory quality benchmarks, plus more. This episode is sponsored by Walrus.

We cover:
  • Why longer context windows don't help once you switch models or harnesses, and why an import function only fixes one point in time
  • Why Kimberly doesn't benchmark Walrus Memory against memory startups, and why she sees the opportunity as bigger than memory alone
  • What people build with Walrus Memory besides coding agents, which Walrus puts at maybe 30% of usage: long-running study aids, trading agents, and security teams comparing production snapshots with code changes
  • Walrus's figure that almost 85% of the memories written are read back more than 30 days later
  • How attestations on the blockchain and a delegate key you control let you show what happened to your data, and why unchanged data still isn't proof that it's accurate
  • Why Kimberly treats recall quality and latency as table stakes, and how a knowledge graph keeps recall on the freshest memories
  • Why she left almost 20 years in traditional software, including seven at Google, for a blockchain company, and where shared memory across companies and trust boundaries goes next
  • Walrus Console, announced this week: one place to manage agent memories and files through an interface or an MCP connection, without knowing how the storage underneath is configured
Connect with Kimberly Logan:
Connect with Chain of Thought host Conor Bronsdon:
🔗 More episodes: https://chainofthought.show

Chapters:
(0:00) Why agent memory has to move with you
(1:25) Context windows don't follow you to a new model
(4:41) Why an import function doesn't fix lock-in
(6:38) Why Walrus isn't competing head-on with memory startups
(8:39) Where Walrus Memory goes next
(10:38) Trading agents and security snapshots on Walrus Memory
(14:44) Verifiability: answering what happened to your data
(17:21) Fresh recall, and why Walrus doesn't publish memory benchmarks
(20:22) From traditional software to a blockchain company
(24:40) A record other companies and regulators can check
(25:42) What Walrus Console is for
(29:09) Use agent memory beyond coding agents
(30:52) Plugging in your own agent stack
(31:41) Memory across companies and trust boundaries
(35:48) Closing thoughts

Thanks to Walrus, presenting sponsor of season four of Chain of Thought. Walrus Memory gives AI agents portable, verifiable memory that carries context across apps, sessions, and other agents. Get started at https://walrus.xyz/cot

#AI #AIAgents #AgentMemory #SoftwareEngineering #DevTools

Creators and Guests

Host
Conor Bronsdon
Creator and Host of the Chain of Thought Podcast
KL
Guest
Kimberly Logan
Head of Product at Walrus Foundation

What is Chain of Thought | AI Agents, Infrastructure & Engineering?

AI is reshaping infrastructure, strategy, and entire industries. Chain of Thought is the podcast where builders reason through what's changing. Host Conor Bronsdon sits down with the engineers and founders shipping AI in production to get past the hype into what's working and what isn't. Episodes cover model infrastructure, inference, agent frameworks, evaluation, and developer tools.

Guests have come from NVIDIA, Google DeepMind, AMD, Databricks, Vercel, and more. Every episode carries a full transcript and show notes at chainofthought.show. New episodes weekly.

Conor Bronsdon is an independent consultant and angel investor in AI infrastructure and developer tools. He led technical ecosystem at Modular, acquired by Qualcomm in 2026; led developer awareness at Galileo, acquired by Cisco; and ran developer marketing at LinearB, where he was GM of the Dev Interrupted podcast and community.

Views expressed by the host and guests are their own.

[0:00] Kimberly Logan:
Almost 85% of memories that get written Are accessing read back over 30 days later. But if I decide I wanna switch models, for any type of reason. or try a different type of Harness I shouldn't have to start over. that no one has to choose. And where they start doesn't need to be where they end.

[0:29] Conor Bronsdon:
A controlled study published three weeks ago moved agent memory between models. and found something uncomfortable. The notes your agent wrote about you can swing its accuracy by thirteen points. or sometimes more. in either direction. purely based on which model reads them back. We need memory to be portable. So avoid lock-in. Welcome to Chain of Thought. It's great to see you all. I am your host, Conor Bronsdon. Joining me today is Kimberly Logan. Kimberly is head of product at the Walrus Foundation. Huge shout out to Walrus.

[0:59] Conor Bronsdon:
For sponsoring this season of Chain of Thought. It's been a pleasure having them. And Kimberly is building the memory layer on top of a decentralized storage network that's been running in production since March of 2025. Kimberly. So good to have you on.

[1:13] Kimberly Logan:
Thanks so much for having me, Conor. I'm really excited to talk about what we're building and why we're building it.

[1:19] Conor Bronsdon:
Same here because I think Agent memory is such an important part of the ecosystem today, But Let's start by setting the stage a bit. Kimberly, why is agent memory so important? And what prompted Walrus to take it on as a a memory product?

[1:36] Kimberly Logan:
So agentic memory is important because Context is what makes it Data valuable and while we have seen the companies that are Creating the models themselves, building longer and longer context windows. Mm. That is only as good as when you are in that provider for the context window that you have. Those million tokens are gonna get you pretty far. But if I decide I wanna switch models, for any type of reason. or try a different type of Harness I shouldn't have to start over. And as you rightfully pointed out at the top of this, The context swings how valuable your data becomes.

[2:23] Kimberly Logan:
when you switch. And so we sat down when we were thinking about How do we address this problem? Because we heard it from our builders, from our users, and from our partners, that this is where they were getting stuck. People wanted to be able to use agents and use the technology but they were overly constrained. And so When we looked at the unique properties of The protocol today, we were sitting on essentially the perfect gold mine. for solving this problem. Because it is built on top of a decentralized storage protocol, We were able to make that infrastructure useful to people.

[3:09] Kimberly Logan:
By building Walrus memory. to allow them to carry their agents' memories with them. and remove the concept of of them being locked into whatever provider they started with.

[3:24] Conor Bronsdon:
Quick disclosure, Walrus Memory sponsored not just this season, but obviously this episode.

[3:30] Conor Bronsdon:
I think this is a very apt moment to be talking about this because You know, as we're recording this, we're a couple days out from some big announcements for Walrus that we're going to be talking about a little later in this episode. And we've also Seen multiple major model announcements pop up where you know Cloud Opus 5.5 and then Sonnet 5.5 both just dropped in the last what week, week and a half. And today, as we're talking, uh OpenAI dev day is happening, and it sounds like Sol 6.1 is accidentally dropping while they have also delayed Astra 6.1.

[4:04] Conor Bronsdon:
So Depending on those models, you may want to adjust where you're spending time. Uh you may be really excited by DeepSeek V1 Flash and want to be using uh a more open layer. And if you have gotten locked into you know, the chat GPT system or the Anthropic. Ecosystem. or another ecosystem There is just simply data that you're going to lose, and your models will not be as accurate when you try to switch over. Like, yes, I know there's some import features that have been set up, but. There's so much rich context and memory that is set kind of locked into these systems.

[4:41] Kimberly Logan:
Yeah. I I completely agree with that and the problem is not solved with an import function either. because that is a point in time. solution. That is not how real workflows happen and that's not How we see Our users and builders trying to create today. They want to be able to use different models for different use cases and different purposes. They're not setting something up and then moving it over and then Continuing on. I personally use different models for different types of work. Just in my own day to day.

[5:20] Kimberly Logan:
And we also know that are Users want to be able to take The Walrus Memory Solution and embed it into their own products with their own agents. that they're creating so that no one has to choose. And where they start doesn't need to be where they end.

[5:42] Conor Bronsdon:
Totally. We've talked to folks on this show at the enterprise level who For example, Fergal Reid at Intercom and FinAI talked to us earlier this year about. basically getting off of OpenAI for certain workflows. And saving $250,000 a month by switching it to open models for these different workflows that he was running. for their customer support agents. But when you do that, it's a ton of work. And as an individual dev, I see this as well. I'm using Codex, I'm using Cloud Code. But I've also got a cheap cursor subscription right now.

[6:16] Conor Bronsdon:
I've got an open code Go subscription. I'm using OpenRouter for some stuff. I've got Jev running as a classifier on some of my emails. There are all these models and classifiers that are interacting. I need to be able to easily port information between them. And this gets down to the value prop that I think walrus memory is providing. But There is quite a bit of conversation around the primitives here. Why aren't you positioning against memory companies like Mem0 or Lang Mam, it feels like Water Memory is more about the storage permit of here.

[6:50] Kimberly Logan:
While we did build on top of the storage protocol. I do not believe that we are primarily solving a pure memory. Problem? in the opportunity space for us. is much bigger. than memory alone. And so I don't consider it Uh Apples to apples. comparisons so I don't publicly benchmark or position it. in that way. Because We are building and see opportunities. to create more ways for people to own and use their data. and share it with others. in the way that works for them. and to allow companies to verify What that memory and that data is across company boundaries.

[7:04] Conor Bronsdon:
Mm. Hmm.

[7:44] Kimberly Logan:
And that goes way beyond. Simply managing your memory or creating better harness plug-ins to allow you to move. beyond Coding. different coding agents. And in fact, a lot of our users aren't even using it. to build coding agents. It's only maybe 30% of the actual usage that we have. is is for switching coding agents. People are using it for everything. From it. creating long running Study aids. to building trading agents that trade on their behalf and build portfolios.

[8:24] Kimberly Logan:
to tracking security incidents and comparing production snapshots. And so I think that our opportunity landscape is much broader. than some of the more targeted memory offerings.

[8:39] Conor Bronsdon:
I would love to understand this a bit more. Where do you see this infrastructure layer that you've built with Walrus Memory going in the coming months?

[8:49] Kimberly Logan:
So what do what do people need to To feel confident about where their data is and where it's going. First of all, they need to know. that it's going to be owned by them forever. They need to control it. They need to choose who accesses it and where. And they need a way to verify it and it needs to work across Dick trust list. uh boundaries. because as we look to a more agentic world where agents are going to be doing more and more things on our behalf.

[9:21] Kimberly Logan:
We the things they can do today. we c we would like them to be able to do more, but we need to be able to do it in a way that we feel confident that it's safe and we can prove what happened. as well. Um But We have we're building the infrastructure to make that possible. across many different Industries and use cases. And so, concretely, we're going to be thinking about building more entry points for people. continuing to make it more performant and more robust. and adding in additional verification functionality that's workflow-based.

[9:59] Kimberly Logan:
because we're seeing people deploy agents in a workflow. Cut. context for for enterprise versus Just more uh one-off types of use cases. The vast majority of our users are using our products for long running workflows. Uh as well. And Almost 85% of memories that get written Are accessing read back over 30 days later. And so we feel confident that we're building for long running. consequential workflows, not just spin up, tear down. uh types of use cases.

[10:38] Conor Bronsdon:
This is obviously a through line for the show, this idea of having great data. curating that data. and ensuring that you build this contextual Moat. You know, Richmond Alake came on the show earlier this year and called Agent Memory the last battleground in the AI stack. Jerry Liu from Alma Index argued that the frameworks era has ended because context is the new mode. You know, we've been talking about context hardnesses recently. And I think it's fascinating to see how Walrus is enabling This evolving contextual memory harness.

[11:16] Conor Bronsdon:
for its users. Can you maybe talk me through a bit of an example of what one of those longer running workflows looks like when it is interacting with the primitive uh of the memory and data storage that you developed.

[11:32] Kimberly Logan:
Sure, so I'm going to select some of our Mm-hmm. agentic. Um trading workflows that we're seeing. So People want their accumulated knowledge to keep working. For them. Because rebuilding things Costs time, energy. Any tension? And so what we are seeing is people embedding Walrus memory in with their agents from the day that they creating them. Sharing using that delegate key. to accumulate knowledge. for that agent. And then the as the agent goes on throughout its activities of trading or gathering other information. What are the other business rules?

[12:19] Kimberly Logan:
The it has been asked to do. It logs that data encrypted. with those memories back to Walrus through Walrus memory. And so we're seeing people's agents become more intelligent over time. and remember things Mm more efficiently. And so in cases where are we even have a customer that's Create offered this embedded knowledge. to get agents started out of the box. We're seeing it become cheaper. For agents to operate and to do so in a more accurate way because they are learning. from other agents as well as business knowledge as as it's long running.

[13:03] Kimberly Logan:
And so actually it becomes more and more valuable the longer that it runs. In a case where we have something like security, Instances, we have a user that has it embedded in their day-to-day workflows. They are going to be taking snapshots of what's happening in production, comparing it with code changes, and using it to verify what's changed. to help them do their security analysis. So It's Not only cases where you're making coding more efficient. But any time that you need something to accumulate knowledge over time. and understand how that knowledge has changed and what's applicable and what's not. we're going to get more value from it.

[14:44] Conor Bronsdon:
Kimberly, how is the Walrus team thinking about the verifiability and trust side of this extremely important data.

[14:55] Kimberly Logan:
So Verifiability is key to being able to answer the question of What happened? and when. And for us to be able to trust agents with our data and these AI systems with our data. That's a critical question we have to answer. Right now, AI feels a lot like a black box. We even see that. with a lot of the news stories that have come out. Open AI agent does XYZ thing messing with the government. It we have the hugging face incident that we remember from earlier in the summer.

[15:33] Kimberly Logan:
And so If you're putting your data in, you need to be able to be able to answer the question. Of what happened to it. And so that's why the verifiability piece of it is so important to us. in our value prop, but also in terms of making this product available to people because It's hard to get those questions answered, but if you are using Walrus memory, you can because the attestation. lives on the blockchain and because you control the delegate key and access to it, you can choose to share that. With anyone else. That that you want to.

[16:16] Conor Bronsdon:
Yeah, I think this verifiability piece is really important because Memories may be true at a point in time, but as the context of the business changes, as my personal context changes, As the world changes around us, we may need to adjust the decisions we've made around them. And data is constantly evolving and growing. And just because a fact was true back in March doesn't mean that uh let's say GPU prices are the same as back then. So this verifiability piece is crucial, I think, to allow scalability for this kind of underlying Data permit does.

[16:24] Kimberly Logan:
Mm-hmm. Yeah. I completely agree with this and if I even think about what has changed in terms of recallability in In six months of my own life, like my preferences now, and even where I see the product going now. are different now. after I've I've had some months of of it being in market. And so That's W Walrus memory and what we're building Doesn't Just right. The memory. to the blockchain. It does that, but we also have Um a knowledge graph layer that Oh. provides the logic.

[17:04] Conor Bronsdon:
Yeah. Yeah, the models are gonna keep hill climbing across a variety of benchmarks. We need to have the domain expertise and the contextual harness to Actually Ensure this is successful when you're trying to apply it to enterprise workflows and elsewhere, to your point. And something else you said that I want to just drill down on very briefly, and this is a bit of a sidebar, but I love that we're seeing blockchain as a technology um come to fruition this digital distribution of data and verifiability. I think it has been so valuable for AI in particular because the scale of how much data we're creating.

[17:30] Kimberly Logan:
to make sure that the recall Is against the freshest memories. All the memories are there, but we also. think that it needs to be usable too. And so while we don't publish memory quality benchmarks. To me, That is a product choice because I believe that good recall quality fast latency, all of that. That isn't something I should be out there bragging about. It's table stakes that anybody should expect to make a quality. Uh memory product work. For them, and so I prefer to let the product speak for itself in terms of the usefulness of it.

[18:12] Kimberly Logan:
And I believe that to be competitive in the market, it needs to be useful for people not just portable. But People need to be able to win through expertise, workflow and results. not through necessarily benchmarking competitions. And I have found a lot more value in keeping Uh the product team focused on what people are trying to do and how to make it more usable for them. versus necessarily f focusing on what the latest uh benchmarking quality measuring contest uh looks like.

[18:51] Kimberly Logan:
Yeah. Yeah. Mm-hmm. Mm-hmm. Yeah. Yeah. Uh-huh. Yeah. So I will start by saying that this is the first blockchain company I've ever worked at. I come from traditional software. And I never thought I would work at a blockchain company. Uh but the reason that I came to work at a blockchain company in Phil's Data infrastructure. was because after spending almost 20 years working in traditional software. I saw concerns with how things were going, especially around things like what happens to our data after we put it out there.

[19:26] Conor Bronsdon:
and the autonomous nature of agents. Uh means that this Yeah. Basically, supply chain verifiability. uh that can now be applied to n the knowledge supply chain. And there is so much data being created on the internet today, and that's just going to continue to 10x as we have more and more agents out there doing things for us that we need to track and understand and verify. And so to me, it's very exciting to see The promise of this technology that has been talked about 10. 20 years ago now, come to fruition.

[19:56] Conor Bronsdon:
And Uh It makes me wonder. how Walrus is thinking about the fusion of all this digital you created agent data and then The human data that you are also bringing in. We talked a bit earlier about the access leveling, but. How are you thinking about this data infrastructure? in the kind of next era.

[20:57] Kimberly Logan:
What how much AI generated content is is taking over the internet. Um We're forging ahead with all of these really exciting ambitions and plans and technology for to power an agentic future. Where's the other side of this? And in the past, we might have been more comfortable putting. our data into a centralized system in order to gain Connection with people. We put all of our data into Facebook so that we could connect with our friends. Uh we put published our whole professional history on LinkedIn so that I could meet other like-minded people.

[21:41] Kimberly Logan:
But I was I think that's good idea. Solve the problems that I was seeing. Seeing becoming more and more Prevalent. And so I f I came to Walrus to solve those problems because I believe the decentralized technology and infrastructure. is what is needed. to make AI actually valuable in a human driven world. and to make sure that human people have control and autonomy. In it? In which I think is so critical, especially 'cause Things feel so out of control in a lot of ways. Like, we don't know what's happening, we don't know.

[22:24] Kimberly Logan:
What's being deployed or where it went. So I want to people to have a sense of control and people also includes businesses. the control over their what makes their business run? What makes their proprietary data valuable to them. so that people didn't have to choose. between taking advantage of new technology And knowing what was being done with it.

[22:51] Conor Bronsdon:
And Kimberly's not going to brag about it herself, but I I will for her when she says, oh, you know, it's the first blockchain company I've worked at. What she means is she spent seven years at Google before this, along cite other uh pieces of her career as well, but let's just focus on the Google piece. where she led Google searches client infrastructure program management organization. and uh had to understand how reams of data would come together. So I think it's awesome to see folks like yourself who have such a deep background in scaled data.

[23:22] Conor Bronsdon:
Saying, okay. How do we solve this problem for the future, We know that agentic data is only going to continue to increase, assuming that we down this pathway, which Given the value of AI in so many areas, it seems very clear we will. As the Simplicity of using something and the the price of it goes down, the actual usage massively increases. And we see this with roadways, right? You know, when we have three lanes on a highway, it's full, but then we have six lanes, and we're thinking, oh, great, we're gonna have all this space.

[23:45] Kimberly Logan:
Mm-hmm. Right. Yeah. And we believe that Hmm. What we're doing goes even beyond What a good access log. can provide. Um because there's many solutions already out there available um for access logs. Um but we believe people should have a record that other people can check. that other other companies Uh regulators users Um and to be able to compare contents against an earlier commitment. Um to detect changes. We also think that though that unchanged doesn't necessarily mean true. So integrity doesn't establish accuracy authorization. or complete.

[23:54] Conor Bronsdon:
No, more people drive because now there's more space. And we see this, I think, with Jev and classifier models suddenly becoming much more useful. Yeah. Great, it's so much cheaper right now, but that means we're going to use classifiers on everything. And that just means more and more data being created, more stuff that we want to track. um more need for verifiability, more need to be able to control our data. And it seems pretty clear to me that uh a tamper evident memory solution um like what Walrus is building on the data side.

[24:25] Conor Bronsdon:
can be crucial. For a establishing databases that have Good access logs in the long term, especially as agents start to run amok a bit. And we can look at all the examples this year. to point to why this matters.

[25:26] Kimberly Logan:
capture so We do think though that um We want to be able to have the evidence in order to have frankly, and open and transparent. way to even be able to look at what happened in one.

[25:42] Conor Bronsdon:
And I think an exciting part of this is what you're going to be announcing today when this episode comes out. which is the new Walrus console. Can you tell us a bit about what Walrus console is before I spoil the surprise.

[25:49] Kimberly Logan:
Mm-hmm. Yes. I'm so excited for Walrus Console. It is It's solving problems that I've been hearing from builders and users since day one. Walrus Console is all about bringing these awesome properties that we just have been spending the last uh minutes together the talking about to more people. So the properties of portable verifiable programmable access for your data. to more people through a simple to use interface Or MCP connection. to be able to manage your agent memories. your files. and your other information all in one place.

[26:44] Kimberly Logan:
And Walrus Console is not only about what you can do today. But it will be The Front page into Walrus for all of this other functionality, we're going to continue to build. in the future. Um and all the workflows we're going to be in. to enable all of the different ways that you're going to be able to have your agents interact with agent other agents And so we're excited because this is the first step in a long journey of making this technology. accessible to more people because I think for a long time, a lot.

[27:25] Kimberly Logan:
of great blockchain technology has not been accessible to most people. It was just too hard. It's hard to figure out how to configure it. how the blockchain technology itself and how it Operates blobs and their expiration and all that. That's a very high bar to clear and requires lots of education to people. That Is frankly a lot to ask, and we don't think it should be that way anymore because we think that this infrastructure should be available. to everyone um and you shouldn't have to have complex knowledge regarding how the underlying infrastructure is configured or works. It should just work for you from day one.

[28:12] Conor Bronsdon:
And if I understand it correctly. You know, console lets any developer who's using cloud code, codex, et cetera, to build with the walrus data primitive through an API through an MCP inheriting the kind of three default properties of portability. privacy and verifiability that we've been talking about throughout this conversation. Um and is essentially designed to supercharge the ecosystem. uh of builders around Walrus.

[28:24] Kimberly Logan:
Yes. Yes. Yeah. Yes, that's exactly right. And We are going to be sharing more news about exciting partnerships and new use cases. that are building on Walrus that are powered by this new technology in the coming weeks as well.

[28:59] Conor Bronsdon:
what other key takeaways should folks uh have as they think about potentially building with Walrus memory. and leveraging it in their tools.

[29:09] Kimberly Logan:
I would encourage people to Use Walrus memory beyond their coding agents. The coding agents A Obvious use case, it's built For that, we have treated that as a first class. uh opportunity, but where we have seen people get unique value from the wow moments that we've heard both from like actual end users as well as partners that have reached out to us. is realizing that it can be deployed anytime That your data not forgetting what happened in and accumulating over time. is beneficial Which means it can solve a super large variety of use cases, and I would encourage people.

[29:17] Conor Bronsdon:
Hmm. And I'll say I have been impressed by the engagement of the Walrus Foundation. A Twitter account. for sure as I've interacted with it a bit. Um If I'm someone who's listening to this, and let's say I'm using A personal agent stack. Maybe it's Hermes, maybe it's Openclaw. Maybe I'm starting to use Grokbot or the new Dots that OpenI released How can I use those with Robbox memory and with console.

[29:58] Kimberly Logan:
not to be limited to it. uh and and what seems immediately in in front of them. Um and the second is that like It's a product under very active development. And so the feedback from both our partners on the small and medium business as well as enterprise side. as well as our very active user community. Their feedback directly informs what we build next. And so I would encourage people to. Uh participate in our Okay. community activation events as well as interact with myself and other members of the product team.

[30:35] Kimberly Logan:
Um through Discord, Twitter, or one of our many other channels. Uh because we have built functionality specifically because we have we have heard from people. So Think beyond Coding. And second, work with us to make it even better.

[31:06] Kimberly Logan:
Mm-hmm. Yeah. Uh-huh. It works. Today already we support OpenCloud. And NemoClaw out of the box today, and because it is available. through an API. Um or an MCP service. People can Connect. their their personal tooling stack into it as well and I would love to hear from folks about what they're using it for.

[31:41] Conor Bronsdon:
And as we think about the next stage of the Agentic future as I am kind of terming the next year. Uh Six months or a year from now. How do you want console and wall risk memory to be positioned and used as you continue to see new? Uh use cases.

[31:47] Kimberly Logan:
Hmm. Yeah. So I want people to be using it actively as part of managing real workflows that they have. Expect to see people using it. also to manage workflows. with other companies or other users beyond their own like trust boundaries. So I'm gonna in this agentic future that we have. We will go beyond agents only being for personal use and hopefully being able to interact with other humans or other agents beyond Uh our own Particular area, and so I want to see people using it. for multi-tenant, multi-organization. Multi-user types of scenarios, and we're going to be building functionality that makes that easier. to do in the coming months as well.

[32:56] Conor Bronsdon:
And this is where I think Walrus building with verifiability in mind from day one is a huge opportunity because. Multi-agent coordination is a challenge if you're not able to trust the handoffs between agents. We already see challenges in my owned agent fleets. Where, if there's a negative handoff between different model families or different agents, there can be major problems. Whereas if I'm able to verify and have accurate data, they can be much more successful. the coordination effects of that are going to be much more significant.

[33:10] Kimberly Logan:
Totally. Yeah, agree. And Shared records shouldn't depend on one participant's private system or else it will not work in in the future that both you and I are envisioning. But I feel confident that we're laying the foundation now to make that actually feasible at scale for consequential actions. As well as those ones where You know, maybe it only costs me. a dollar, but I'd like to be able to do a lot more than that.

[33:30] Conor Bronsdon:
as we look at Cross team coordination. We're seeing this already of people trying to to coding and coding channels in Slack, for example. Um but increasingly we're starting to see people's personal agents interact with people using their muse agents to communicate and schedule things. OpenCloud agents who are doing work together. Um I've just had my first pitches of independent AI agents pitching me for Work from Islands. I paid an agent $8 to write me an article just as a test and write about it on Substack.

[34:03] Conor Bronsdon:
It was very fun. And I would be stunned if there's not a future where we are all interacting with technology through our agents in many ways and instructing it through voice or text. Maybe thoughts in the future to go out and do things on our behalf, and they will be interacting with other agents. We've seen this sometimes with customer service agents that are calling that now have a voice agent that have set up to answer questions. So I think this is where for me it's really exciting to see The intentionality around not just you know, retaining understanding data, but being able to verify it and Uh only handed off when There has been you know, valid acceptance of that handoff. And so I think that is both a hill to climb and a problem to solve, but like a really exciting future us.

[35:20] Conor Bronsdon:
Mm-hmm. Absolutely. Uh Kimberly, thank you so much for joining me today. It's been fantastic chatting with you, and thank you for taking us through perspective behind Bobus Memory and the new console launch. Excited to tinker with console. And for folks who are listening, where should they go to check it out and find out more?

[35:38] Kimberly Logan:
Yep, you can We will include the links in the podcast, but you can go to walrus.xyz slash console.

[35:48] Conor Bronsdon:
Fantastic. And I will remind everyone who's listening here that if you made it all the way through this conversation, you clearly loved it. You should definitely be subscribed on your platform of choice. because it really does make a big difference to us. Uh and I I deeply appreciate it. do you have closing thoughts for us around the future of AI agents and uh agent memory?

[36:08] Kimberly Logan:
Yeah, I just Wanna say that this is There's a huge opportunity here. And we're only at the start of it. I know that those of us that live and breathe the technology, it feels like we're very far along in this journey. Um but if we look at the l the larger set of industries that can be brought along and the larger groups of of uh people that can can take value from where we're going. I believe we're really just at the start and so Being putting the guard rails in place now and building the infrastructure.

[36:46] Kimberly Logan:
that will allow for the type of future that we've been talking about. to become A reality for most people versus something that they have to hope to put in later. Now is the time for us to be building and integrating this type of technology. So that we can feel confident in In the agentic future that that's in front of us.

[37:11] Conor Bronsdon:
Absolutely. Kimberly, thank you so much for joining me and super excited to keep building the Agentic Future with you.

[37:14] Kimberly Logan:
Yeah. Great, thank you so much.