Building a custom agents platform is one of the key pieces to unlocking AI for complex business workflows. Monte Carlo is the sales-specific system we’ve built to help scale Monaco’s revenue: a platform where revenue teams encode their own playbooks as agents that run against everything we’ve ingested about their business, including pipeline, outbound, calls, and CRM. Sales is a particularly complex vertical for the following reasons: no two revenue orgs look alike, the data is large and heterogeneous, and the expertise that matters lives in per-rep workflows nobody has written down.

Making it work at scale meant rebuilding the agent runtime on per-run microVMs, a decision that propagated much further than we expected into how we handle context, how much of a playbook ends up as prose versus code, and what an agent is permitted to do at all. In this talk, I’ll break down the components a verticalized agent platform needs in order to be fast and correct, including an execution substrate, memory and context, how expertise gets represented, and the evaluation loop, along with what is still unresolved.