The shift from prototyping to having brokers in manufacturing is the problem for AI groups as we glance towards 2026 and past. Constructing a cool prototype is simple: hook up an LLM, give it some instruments, see if it appears prefer it’s working. The manufacturing system, now that’s laborious. Brittle integrations. Governance nightmares. Infrastructure wasn’t constructed for the complexities and nuances of brokers.
For AI builders, the problem has shifted from constructing an agent to orchestrating, governing, and scaling it in a manufacturing atmosphere. DataRobot’s newest launch introduces a strong suite of instruments designed to streamline this lifecycle, providing granular management with out sacrificing pace.
New capabilities accelerating AI agent manufacturing with DataRobot
New options in DataRobot 11.2 and 11.3 enable you shut the hole with dozens of updates spanning observability, developer expertise, and infrastructure integrations.
Collectively, these updates give attention to one purpose: decreasing the friction between constructing AI brokers and working them reliably in manufacturing.
Essentially the most impactful areas of those updates embody:
- Standardized connectivity by means of MCP on DataRobot
- Safe agentic retrieval by means of Discuss to My Docs (TTMDocs)
- Streamlined agent construct and deploy by means of CLI tooling
- Immediate model management by means of Immediate Administration Studio
- Enterprise governance and observability by means of useful resource monitoring
- Multi-model entry by means of the expanded LLM Gateway
- Expanded ecosystem integrations for enterprise brokers
The sections that observe give attention to these capabilities intimately, beginning with standardized connectivity, which underpins each production-grade agent system.
MCP on DataRobot: standardizing agent connectivity
Brokers break when instruments change. Customized integrations grow to be technical debt. The Mannequin Context Protocol (MCP) is rising as the usual to resolve this, and we’re making it production-ready.
We’ve added an MCP server template to the DataRobot neighborhood GitHub.
- What’s new: An MCP server template you’ll be able to clone, take a look at regionally, and deploy on to your DataRobot cluster. Your brokers get dependable entry to instruments, prompts, and sources with out reinventing the mixing layer each time. Simply convert your predictive fashions as instruments which might be discoverable by brokers.
- Why it issues: With our MCP template, we’re providing you with the open customary with enterprise guardrails already inbuilt. Check in your laptop computer within the morning, deploy to manufacturing by afternoon.
Discuss to My Docs: Safe, agentic information retrieval
Everyone seems to be constructing RAG. Virtually no person is constructing RAG with RBAC, audit trails, and the flexibility to swap fashions with out rewriting code.
The “Discuss to My Docs” utility template brings pure language chat-style productiveness throughout all of your paperwork and is secured and ruled for the enterprise.
- What’s new: A safe, ruled chat interface that connects to Google Drive, Field, SharePoint, and native recordsdata. Not like fundamental RAG, it handles advanced codecs from tables, spreadsheets, multi-doc synthesis whereas sustaining enterprise-grade entry management.
- Why it issues: Your crew wants ChatGPT-style productiveness. Your safety crew wants proof that delicate paperwork keep restricted. This does each, out of the field.
Agentic utility starter template and CLI: Streamlined construct and deployment
Getting an agent into manufacturing mustn’t require days of scaffolding, wiring companies collectively, or rebuilding containers for each small change. Setup friction slows experimentation and turns easy iterations into heavyweight engineering work.
To deal with this, DataRobot is introducing an agentic utility starter template and CLI, each designed to cut back setup overhead throughout each code-first and low-code workflows.
- What’s new: An agentic utility starter template and CLI that allow builders configure agent elements by means of a single interactive command. Out-of-the-box elements embody an MCP server, a FastAPI backend, and a React frontend. For groups that want a low-code strategy, integration with NVIDIA’s NeMo Agent Toolkit permits agent logic and instruments to be outlined completely by means of YAML. Runtime dependencies can now be added dynamically, eliminating the necessity to rebuild Docker photos throughout iteration.
- Why it issues: By minimizing setup and rebuild friction, groups can iterate quicker and transfer brokers into manufacturing extra reliably. Builders can give attention to agent logic slightly than infrastructure, whereas platform groups preserve constant, production-ready deployment patterns.
Immediate administration studio: DevOps for prompts
As prompts transfer from experiments to manufacturing belongings, advert hoc modifying shortly turns into a legal responsibility. With out versioning and traceability, groups battle to breed outcomes or safely iterate.
To deal with this, DataRobot introduces the Immediate Administration Studio, bringing software-style self-discipline to immediate engineering.
- What’s new: A centralized registry that treats prompts as version-controlled belongings. Groups can monitor modifications, examine implementations, and revert to secure variations as prompts transfer by means of improvement and deployment.
- Why it issues: By making use of DevOps practices to prompts, groups achieve reproducibility and management, making it simpler to transition from prototyping to manufacturing with out introducing hidden threat.
Multi-tenant governance and useful resource monitoring: Operational management at scale
As AI brokers scale throughout groups and workloads, visibility and management grow to be non-negotiable. With out clear perception into useful resource utilization and enforceable limits, efficiency bottlenecks and value overruns shortly observe.
- What’s new: The improved Useful resource Monitoring tab gives detailed visibility into CPU and reminiscence utilization, serving to groups determine bottlenecks and handle trade-offs between efficiency and value. In parallel, Multi-tenant AI Governance introduces token-based entry with configurable price limits to make sure truthful useful resource consumption throughout customers and brokers.
- Why it issues: Builders achieve clear perception into how agent workloads behave in manufacturing, whereas platform groups can implement guardrails that stop noisy neighbors and uncontrolled useful resource utilization as techniques scale.
Expanded LLM Gateway: Multi-model entry with out credential sprawl
As groups experiment with agent habits and reasoning, entry to a number of basis fashions turns into important. Managing separate credentials, price limits, and integrations throughout suppliers shortly introduces operational overhead.
- What’s new: The expanded LLM Gateway provides help for Cerebras and Collectively AI alongside Anthropic, offering entry to fashions comparable to Gemma, Mistral, Qwen, and others by means of a single, ruled interface. All fashions are accessed utilizing DataRobot-managed credentials, eliminating the necessity to handle particular person API keys.
- Why it issues: Groups can consider and deploy brokers throughout a number of mannequin suppliers with out rising safety threat or operational complexity. Platform groups preserve centralized management, whereas builders achieve flexibility to decide on the best mannequin for every workload.
New supporting ecosystem integrations
Jira and Confluence connectors: To energy your vector databases, DataRobot gives a cohesive ecosystem for constructing enterprise-ready, knowledge-aware brokers.
NVIDIA NIM Integration: Deploy Llama 4, Nemotron, GPT-OSS, and 50+ GPU-optimized fashions with out the MLOps complexity. Pre-built containers, production-ready from day one.
Milvus Vector Database: Direct integration with the main open-source VDB, plus the flexibility to pick distance metrics that truly matter on your classification and clustering duties.
Azure Repos & Git Integration: Seamless model management for Codespaces improvement with Azure Repos or self-hosted Git suppliers. No handbook authentication required. Your code stays centralized the place your crew already works.
Get hands-on with DataRobot’s Agentic AI
In the event you’re already a buyer, you’ll be able to spin up the GenAI Check Drive in seconds. No new account. No gross sales name. Simply 14 days of full entry inside your current SaaS atmosphere to check these options together with your precise information.
Not a buyer but? Begin a 14-day free trial and discover the total platform.
For extra data, please go to our Model 11.2 and Model 11.3 launch notes within the DataRobot docs.
