Latent Space: The AI Engineer Podcast
00:07:42 · Aman Singh
[00:07:42] S0: Yeah. So this is an interesting interesting one to think about is we have tons of these signals like I described in the talk. Some are, for example, you can imagine there's an email thread that is receiving responses and there's chatter happening. Right? You can imagine that that any additional response to that goes to the same agent that's kind of like reading that that email thread and reacting to it. Right? But a a fresh signal of... It's like a like a phone call that was made in the middle, That is a brand new signal that isn't attached with any other ongoing process. And so there's like a fresh agent that wakes up to figure out what this means. Right? And the way they way they understand what is happening right now is our internal memory systems. Mhmm. So we have we have this this persistence of... For every client, what is happening right now? What are we trying to service? Who owns what? What has happened so far? What are we tracking for next? Right, what what needs to happen immediately in the next couple of days, what are we tracking for the long term, right, which individual is responsible for which action. All of this is being tracked by our memory systems Mhmm. That our agents contribute to, But, also, there is a a kind of really sort of dreaming process that reflects on the state of the world as it relates to Richard, the client Mhmm. And is able to kind of, like, update these memory systems to to persist long horizon kind of tasks. So that agent that received a new signal quickly ramps up on what the situation is with the client, and he'll know, okay. We're we're actually executing a big tax bill, and we'll be able to see, okay. My signal relates to that tax bill, so let me kind of contribute to the to to the state of that world.
00:09:22 · Richard MacManus
[00:09:22] S1: Can you talk a little bit about the the safety sort of aspects that you've maybe built into your product or harness to to to make sure, obviously, that no money is lost along the way?
00:09:32 · Aman Singh
[00:09:32] S0: Yeah. So all of our safety restrictions are are fully deterministic, and they they take the decision making off the the agent's hands. So for example, certain tools let the let the agent kind of execute the tool itself. So if it's like a simple record keeping kind of tool, it will execute it. We also... With every time a tool is called that writes data, we have LLM based verification running on on that action. These, like, fast LLM calls that that analyze every single write to our database. So that's another layer of verification we're running. And then we also ingest a lot of, like, external information. So there's emails coming in, documents coming in, phone calls being made, which are targets for prompt injection. So we run sort of verifications at the at at the edges that detect presence of certain, know, flavors of prompt injection. And then anytime there is a there is a case where data leaves our system, for example, in, like, a a web search in in the most obvious case, but also if we're sending a calendar invite to Richard. Right? That's an external kind of data where we have both deterministic checks on presence of certain information that we know is PII, but also a consensus of small models that that ensure that there isn't any kind of data exfil being attempted. So we have tons of different different kind of guardrails built into the harness with the principle that we want to kind of contain them at the edges of capability and not earlier than that.
00:11:02 · Richard MacManus, Aman Singh
[00:11:02] S1: Yes. And and because you're in the financial, you know, industry, are there certain kind of regulations that are required that you have to sort of keep to in terms of the technology that you're using or is that is it just more about outcomes and the way you sort of deal with clients? [00:11:18] S0: Yeah, the industry cares about outcomes but compliance cares about auditability. Right. Right? And so our system is such that auditability is by default. Mhmm. We have every single action that that an agent takes produces a change log of what changed, who changed it, from which part of the system, and when. And this applies not just to agents, by the way. It applies to human actors as well. Mhmm. So if you change something in the UI that affects the client, we'll log that action. So it lets us both get auditability by default, but also power some of our agentic capabilities where the same thing that that retracts like a UI change Mhmm. Also could be used to, like, inform the agent that that happened. [00:12:05] S1: Right. [00:12:06] S0: So auditability has been a big part of our our story, both for obviously compliance and regulation, but [00:12:12] S1: also for our agentic loop. Yes. In your presentation, you had a nice line agents prompt people more than people prompt agents. So how do the agents decide who to involve and you know, what sort of how much of the context that they need to provide that person in order to do what they need to do?
00:12:12 · Richard MacManus, Aman Singh
[00:12:12] S1: also for our agentic loop. Yes. In your presentation, you had a nice line agents prompt people more than people prompt agents. So how do the agents decide who to involve and you know, what sort of how much of the context that they need to provide that person in order to do what they need to do? [00:12:32] S0: Yeah. Another interesting one. So this is similar to how humans work in in in in our industry is there is a process that we're tracking over ten days. There's multiple actors involved. The the actor at step seven may not need to know about this just yet. Right? They're pulled in at the right time. And so our agents with our kind of, like, long memory persistence plus the daily reflection on what is happening reflect on where the the state of the world is at the moment. And they're able to pull in the right person at that time when it is... When when there's a signal that that implies that that person must be pulled in. And all of this is work that we have done to operationalize the context of how this industry works. But not just that, but how does Arca want it to work and what are our principles of of how work happens in this industry. And that is another advantage of us being sort of a a a... Not just a SaaS company. We're actually not a SaaS company. We are we are the firm ourselves. So we can standardize the way this work even happens so that our agents can participate in standard ways that that work must happen.
00:12:32 · Aman Singh, Richard MacManus
[00:12:32] S0: Yeah. Another interesting one. So this is similar to how humans work in in in in our industry is there is a process that we're tracking over ten days. There's multiple actors involved. The the actor at step seven may not need to know about this just yet. Right? They're pulled in at the right time. And so our agents with our kind of, like, long memory persistence plus the daily reflection on what is happening reflect on where the the state of the world is at the moment. And they're able to pull in the right person at that time when it is... When when there's a signal that that implies that that person must be pulled in. And all of this is work that we have done to operationalize the context of how this industry works. But not just that, but how does Arca want it to work and what are our principles of of how work happens in this industry. And that is another advantage of us being sort of a a a... Not just a SaaS company. We're actually not a SaaS company. We are we are the firm ourselves. So we can standardize the way this work even happens so that our agents can participate in standard ways that that work must happen. [00:13:45] S1: So earlier in the conference, Anthropic did a workshop about their managed agents infrastructure and a lot of it, even the orchestration is becoming more automated now. So do you foresee kind of using that type of functionality? Because it obviously presents a danger and that the human is not necessarily always in the loop anymore. So have you had any thoughts about using that technology to automate even more of the process?