All articles
Engineering·January 15, 2025·1 min read

How we deploy agents at scale across 500+ revenue teams

A behind-the-scenes look at the infrastructure that powers Agent Ai's agent platform.

Sarah Chen
Sarah ChenCo-founder & CEO
How we deploy agents at scale across 500+ revenue teams

When we started Agent Ai, we believed every revenue team would eventually run on agents. Two years later, we're operating that infrastructure for over 500 teams — and we've learned a lot along the way.

The challenge

Most agent platforms assume a single tenant, low concurrency, and predictable workloads. None of those assumptions hold in production.

Our architecture

We split the platform into three layers:

  1. Data layer — unified identity resolution across every source
  2. Tools layer — shared workflows, routing, and scheduling primitives
  3. Agent layer — LLM orchestration with full observability

Every agent action is logged, reviewed, and reversible before it touches your systems.

Why this matters

The result is a platform that handles billions of decisions per month while staying explainable and safe.

// Example: deploying an agent
const agent = await default.agents.create({
  name: "Lead Router",
  tools: ["enrichment", "routing", "scheduling"],
  guardrails: { requireApproval: true },
});