For its user assistant, Brex moved beyond a single agent with many tools. Instead, they built a network where specialized sub-agents (e.g., policy, travel) have multi-turn conversations with an orchestrator agent to collaboratively solve complex user requests.
Related Insights
Instead of one monolithic agent, build a multi-agent system. Start with a simple classifier agent to determine user intent (e.g., sales vs. support). Then, route the request to a different, specialized agent trained for that specific task. This architecture improves accuracy, efficiency, and simplifies development.
To build a useful multi-agent AI system, model the agents after your existing human team. Create specialized agents for distinct roles like 'approvals,' 'document drafting,' or 'administration' to replicate and automate a proven workflow, rather than designing a monolithic, abstract AI.
True Agentic AI isn't a single, all-powerful bot. It's an orchestrated system of multiple, specialized agents, each performing a single task (e.g., qualifying, booking, analyzing). This 'division of labor,' mirroring software engineering principles, creates a more robust, scalable, and manageable automation pipeline.
When building Spiral, a single large language model trying to both interview the user and write content failed due to "context rot." The solution was a multi-agent system where an "interviewer" agent hands off the full context to a separate "writer" agent, improving performance and reliability.
The popular concept of multiple specialized agents collaborating in a "gossip protocol" is a misunderstanding of what currently works. A more practical and successful pattern for multi-agent systems is a hierarchical structure where a single supervisor agent breaks down a task and orchestrates multiple sub-agents to complete it.
Don't fear deploying a specialized, multi-agent customer experience. Even if a customer interacts with several different AI agents, it's superior to being bounced between human agents who lose context. Each AI agent can retain the full conversation history, providing a more coherent and efficient experience.
Agentic AI will evolve into a 'multi-agent ecosystem.' This means AI agents from different companies—like an airline and a hotel—will interact directly with each other to autonomously solve a customer's complex problem, freeing humans from multi-party coordination tasks.
Separating AI agents into distinct roles (e.g., a technical expert and a customer-facing communicator) mirrors real-world team specializations. This allows for tailored configurations, like different 'temperature' settings for creativity versus accuracy, improving overall performance and preventing role confusion.
The next frontier in AI is not just developing individual agents, but orchestrating teams of them. Users will move from dialoguing with a single chatbot to managing multiple agents working in parallel on complex, long-running workflows. This becomes a new core skill for knowledge workers.
Replit's leap in AI agent autonomy isn't from a single superior model, but from orchestrating multiple specialized agents using models from various providers. This multi-agent approach creates a different, faster scaling paradigm for task completion compared to single-model evaluations, suggesting a new direction for agent research.
