How "Supply side agents" capture org context without needing user access | Max Agency #podcast
Skills:
Agent Foundations80%
Key Takeaways
Introduces supply side agents for capturing organizational context without user access
Full Transcript
The way to think about feedback is you need to have a product that creates value to the user and your product needs to have enough engagement for the user to see value to give feedback. I think that's like pre-rec, right? Like independent of like any technology choices. And with that as kind of the the main, I would say, like pre-rec here, I think it's really important to have an agent that lives where the work is. And that's like a product principle that we have. I think in order for you to maximize for a context capture, you need to one, be where the work is happening, right? Whether that's Slack or Teams or in some ticketing system or in some other cases it could even be like offline, right? Like there are ways to capture that telemetry. I think two, you need to build what we're calling supply side agents, right? So, you don't really need to have access to the user. What you need access to is the system of context as well as decisions are being made throughout the organization. And with enough agents that can do enough long-running tasks, you can basically figure out, oh, like here are the five tickets that were closed in the last day. Here are the people that commented on it. Here are the decisions that were made as a result of closing this ticket. And capturing that in a way that is almost like a nervous system of like how this organization works is highly valuable.
Original Description
Gng Sng, Co-Founder and CTO of Cogent Security, explains why agents need to live where the work is happening — tickets, routines, decisions — not just where users are. He introduces the idea of "supply side agents" that capture organizational context at scale, building what he calls a nervous system for how an org actually operates.
This clip is from Max Agency, a #podcast about how the best AI agents are actually being built. Hosted by Harrison Chase, CEO of LangChain, each episode goes deep with the builders designing, deploying, and learning from real agent systems in the wild. From architecture decisions to evals, tooling, and failure modes, Max Agency is for people who want to understand what it really takes to build useful agents.
#AIAgents #EnterpriseAI
Watch on YouTube ↗
(saves to browser)
Sign in to unlock AI tutor explanation · ⚡30
More on: Agent Foundations
View skill →Related Reads
📰
📰
📰
📰
Bitemporal AI Memory: How to Preserve What an Agent Knew Then
Dev.to · Ethan Beirne
I run my one-person business with 12 AI employees. Here's the actual org chart.
Dev.to · Luna
Why Agentic AI Needs More Than Standard Model Risk Management
Medium · AI
What is Anyscale? The Platform Powering Scalable AI and Python Applications
Medium · Startup
🎓
Tutor Explanation
DeepCamp AI