What Is an AI Factory? Power In, Tokens Out
An AI factory is a fixed power and cooling budget converted into model output. This explainer maps its four parts and the throughput-per-watt trade-offs that connect them.
DatabricksThe Databricks AI Product and Engineering TeamAnnouncement
Organizations face a challenge as new frontier models appear roughly every five days, making it difficult to balance flexibility with governance. Databricks introduces the Unity Gateway CLI, which lets admins centrally configure approved coding agents, models, MCP servers, skills, and spending policies. Developers launch any approved agent with a single ug command, and the CLI handles authentication and applies the published settings. Features include Smart Routing that selects cost-appropriate models per task, budget-aware defaults that switch to lower-cost options as spending thresholds are reached, and tracing to capture tool calls and skill invocations for waste analysis. In internal use, the system processed over 61 billion input tokens across roughly 360,000 requests, and tracing helped identify bugs that saved an estimated 1.2 million per year.
The rapid pace of new frontier models (roughly every five days) creates a tension between adopting the best available model and maintaining consistent governance, security, and cost controls across thousands of developers.
The Unity Gateway CLI provides a single command-line interface that connects developers to centrally configured coding agents, handling authentication and applying admin-defined settings for models, MCP tools, skills, Smart Routing, and spending policies.
Admins can centrally configure coding agents, including default models, MCP servers, skills, Smart Routing, and spending policies, and publish changes that sync automatically to developers’ CLI.
Smart Routing selects cost-appropriate models per task, delivering 35% cost savings on Databricks’ internal coding benchmark.
Unity Gateway tracing captures tool calls and skill invocations, enabling teams to find and fix wasted spend; Databricks used it to identify seven MCP tool bugs, saving an estimated $1.2 million per year.
The CLI handles authentication centrally. When a developer runs `ug` with an agent name, Unity Gateway authenticates the developer and applies the published settings before opening the agent's interface. Developers do not need to configure each agent separately.
Smart Routing selects a cost-appropriate model for each coding task based on complexity. Simpler tasks use less expensive models while harder tasks use more capable ones. In Databricks' evaluation, this approach delivered 35% cost savings on their internal coding benchmark.
Yes. Unity Gateway lets teams recommend lower-cost agents and models as spending reaches defined budget thresholds. These become defaults for new launches without interrupting ongoing work. Developers can also check spending and remaining budget with `ug usage`.
Summaries are generated from the original by a language model. Check the original before relying on it.
See the idea
An AI factory is a fixed power and cooling budget converted into model output. This explainer maps its four parts and the throughput-per-watt trade-offs that connect them.
Boards of directors turn ownership into a governance control loop: shareholders elect directors, directors set strategy and guardrails, committees verify independently, and management executes inside those limits.
The API gateway is the single boundary where protocol translation, auth, quotas, and routing become shared policy instead of per-service code. This layered diagram shows what belongs there and why.
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.