Disney+ Databricks
AI Gateway · Foundation Model API

AI Coding Agents.
Enterprise Governed.

Claude Code, Cursor, Codex, and Gemini CLI — running through Databricks AI Gateway with centralized governance, observability, and cost controls. No API keys. No vendor lock-in.

Learn More →
Databricks AI Gateway · Enterprise AI Coding · 2026

What happens when teams go direct.

Direct adoption of AI coding agents creates fragmented governance, disconnected procurement, and limited visibility.

🔓

Security Exposure

MCP tools can grant agents excessive privileges to sensitive data — engineering tickets, design docs, customer issues. No centralized policy enforcement across tools.

💸

Cost Acceleration

Multiple teams adopting different AI tools create disparate billing streams. No unified view of spend, no budget controls, no capacity planning.

👁️

Visibility Gaps

When teams use different assistants simultaneously, leadership loses insight into adoption rates, usage patterns, ROI, and developer productivity impact.

🔗

Vendor Lock-In

Direct API keys to a single provider create dependency. Over-provisioning or under-provisioning capacity as the market evolves rapidly.

🪪

Identity Fragmentation

Separate logins per service, inconsistent authentication policies, no unified audit trail across coding tools.

📊

No FinOps

Token usage, model costs, and team attribution scattered across vendor dashboards. No way to tie AI spend to business outcomes.

Deep dive on the problem and Databricks' approach →
Governing Coding Agent Sprawl with Unity AI Gateway

One gateway. Every agent.

Databricks AI Gateway centralizes governance, observability, and cost management for all AI coding agents.

Pillar 1

Centralized Security & Audit

Single identity system via OAuth — no separate API keys per tool. Agent data access governed centrally with audit logs in Unity Catalog. MCP servers managed within Databricks infrastructure. MLflow tracing for compliance.

Pillar 2

Cost Management & Billing

Consolidated billing across all coding tools via Foundation Model API. Per-team quotas, rate limiting, and cost guardrails applied organization-wide. One invoice — developers choose their preferred tool.

Pillar 3

Observability & Analytics

OpenTelemetry metrics flow into Delta tables in Unity Catalog. Track adoption by team, department, or region. Measure developer velocity. Self-service AI/BI dashboards on gateway telemetry.

Blog: Governing Coding Agent Sprawl ↗ Docs: Coding Agent Integration ↗ GitHub: databricks/ucode ↗

How it works.

Developers use their preferred coding agent. The gateway handles authentication, routing, governance, and telemetry.

Developer Tools
Claude Code
Cursor
Codex CLI
Gemini CLI
GitHub Copilot
OpenCode
Coding Gateway CLI (ucode)
Auto-detects AI Gateway · Writes managed configs · OAuth authentication · No API keys required · github.com/databricks/ucode
Databricks AI Gateway
Unity Catalog
Rate Limiting
Per-team quotas
Guardrails
PII, model allow-lists
Audit & Compliance
Unity Catalog logs
Telemetry
OpenTelemetry → Delta
Foundation Model API
Claude
Anthropic
GPT-4o
OpenAI
Gemini
Google
Qwen / OSS
Open-source

Every major coding agent. One command.

The ucode CLI auto-detects AI Gateway, authenticates via OAuth, and configures each agent automatically.

# Install
uv tool install git+https://github.com/databricks/ucode

# Launch any agent — routes through AI Gateway
ucode claude # Claude Code
ucode codex # OpenAI Codex
ucode gemini # Gemini CLI
ucode copilot # GitHub Copilot CLI
ucode opencode # OpenCode

# Check usage
ucode usage

# Add MCP servers (Databricks SQL, Vector Search, UC Functions)
ucode configure mcp

Zero Config

First launch prompts for workspace URL, authenticates via OAuth, and writes managed config files. No API keys, no manual setup, no environment variables.

MCP Integration

Add Databricks MCP servers to any compatible agent — SQL execution, Vector Search, UC Functions. Centrally managed, token-authenticated.

Multi-Model Flexibility

Switch between Claude, GPT-4o, Gemini, and open-source models without changing tools. The gateway handles routing — developers choose their preferred agent.

From pilot to production.

A phased approach to rolling out governed AI coding at enterprise scale.

01

Provision

Databricks workspace with Foundation Model API + AI Gateway. Tier 4 capacity for production scale.

02

Pilot

10–50 developer cohort using ucode CLI. Validate adoption, measure velocity, collect feedback.

03

Govern

Per-team quotas, model allow-lists, PII guardrails in AI Gateway. Cost attribution by team.

04

Scale

Provisioned throughput for guaranteed capacity. System tables for FinOps. AI/BI dashboards on telemetry.

6
Agents supported
0
API keys to manage
1
Consolidated invoice
Model flexibility
Ready to get started? Reach out to the Databricks Disney team.
Email disney-team@databricks.com → Databricks-Disney Teams Channel ↗