MongoDBAnnouncement
MongoDB announced the public preview of Atlas Agent Engine, a secure platform for building, deploying, and governing AI agents with built-in memory, retrieval, and open flexibility to choose any LLM or framework. The company validated the platform internally with Holly, a unified agentic workspace that replaces seven disconnected tools for sales reps and is powered by Atlas Agent Engine’s runtime, orchestration, and governance. Compared to manually hopping between tools, Holly cuts the time to research and build an outbound prospecting list by roughly 95%, reducing account prep from hours to minutes. Atlas Agent Engine enforces centralized controls and governance while granting developer autonomy, addressing CIO fears about agents running amok in enterprise systems. It is part of a trio of launches alongside MongoDB 9.0 and Atlas Infinite, giving builders a governed platform to run agents grounded in real-time operational data.
MongoDB’s CIO describes the launch of Atlas Agent Engine, a governed platform for building AI agents, and the internal dogfooding with Holly that demonstrated its effectiveness.
MongoDB developed Holly, an internal agentic workspace, on top of Atlas Agent Engine to unify seven sales tools into a single interface, using the engine’s runtime, security, orchestration, and governance capabilities.
Atlas Agent Engine provides built-in memory and retrieval to index enterprise data in place, delivering real-time context while reducing token costs.
Holly, MongoDB’s internal dogfooding project, unifies seven sales tools into one agentic interface, cutting prospecting list research time by roughly 95% and reducing account prep from hours to minutes.
The platform is designed for governance and scale, separating developer autonomy from centralized IT control, with an architecture that remains stable whether running 30 or 3,000 agents.
Atlas Agent Engine indexes enterprise data where it lives and delivers precise context in real time, which improves accuracy and cuts token costs by avoiding unnecessary data transfer and generic responses.
Before Holly, sales reps spent 4 to 6 hours per account hopping between seven disconnected tools with no shared context. Holly unifies those tools into one agentic experience, cutting research time by roughly 95% and reducing prep from hours to minutes.
The platform is designed for secure and governed deployment, allowing developers to ship agents quickly while giving IT leaders centralized control, visibility, and cost optimization levers over agent behavior at scale.
Summaries are generated from the original by a language model. Check the original before relying on it.
See the idea
Consolidating agent memory, retrieval, and governance onto MongoDB Atlas removes sync and vendor layers, but ties scaling and control to one platform. This trade-off view shows the payoff, the cost, and the condition that decides it.
Keep reading
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
One useful email. Unsubscribe anytime.
