Search papers, labs, and topics across Lattice.
This paper analyzes 138 practitioner conference talks to understand the adoption, architectures, and technologies used in real-world AI agent deployments. The analysis reveals common architectural patterns, including the prevalence of LLMs for planning and reasoning, vector databases for memory, and API integrations for tool use. The findings provide a grounded perspective on the current state of AI agent development in industry, contrasting with more theoretical research.
Forget the hype, here's how companies *actually* build AI agents: LLMs for planning, vector DBs for memory, and lots of API wrangling.
To support practitioners in understanding how agentic systems are designed in real-world industrial practice, we present a review of practitioner conference talks on AI agents. We analyzed 138 recorded talks to examine how companies adopt agent-based architectures (Objective 1), identify recurring architectural strategies and patterns (Objective 2), and analyze application domains and technologies used to implement and operate LLM-driven agentic systems (Objective 3).
