# July 2025 > You can now use simulations to evaluate and refine your AI agents before they go live. Simulate both input data and agent tools directly during testing, at design time. This feature is available in the **Test Configuration** panel when you manually run your agent, and when you create evaluations and evaluation sets. ## July 29, 2025 ### Simulate inputs and tools for AI agents You can now use simulations to evaluate and refine your AI agents before they go live. Simulate both input data and agent tools directly during testing, at design time. This feature is available in the **Test Configuration** panel when you manually run your agent, and when you create evaluations and evaluation sets. Use simulations to: 1. Simulate inputs: Use an LLM to generate inputs for your agent arguments. You can let the LLM auto-generate inputs or provide prompts to steer it toward specific examples. 2. Simulate tools: Use an LLM to simulate one or more agent tools. Describe how each tool should respond, and simulate partial or full toolsets your agent relies on. 3. Create evaluation sets with simulations: Generate new evaluation sets (or add to existing ones) using simulated inputs and tools. Simulations are ideal in early development for testing edge cases, when real tools are unavailable or costly to run, or if you want to avoid triggering changes in external systems. For details, refer to the [Evaluations](https://docs.uipath.com/agents/automation-cloud/latest/user-guide/agent-evaluations#configuring-simulations-in-evaluations) section. :::note Simulations are available as a preview feature. ::: ### DeepRAG – Advanced retrieval and synthesis for Agents DeepRAG (Deep Research-Augmented Generation) is now available for Agents. This powerful new capability enables multi-document synthesis and retrieval for advanced agent use cases. With DeepRAG, agents can synthesize information from multiple documents, delivering comprehensive, citation-backed answers to complex queries. Note that this feature is currently supported only for PDF files. The **DeepRAG** option is available as a new search strategy when configuring contexts for an agent. Results returned by DeepRAG include source citations, which are automatically displayed in the agent trace for full transparency. Figure 1. Configuring DeepRAG and how the results are displayed in the agent trace ![docs image](https://dev-assets.cms.uipath.com/assets/images/agents/agents-docs-image-b3bf553a.webp) DeepRAG queries are priced at 0.20 Platform Units (or 1 AI Unit) per request, supporting up to 20 pages or 30,000 tokens. Trial and Enterprise users receive 2 DeepRAG requests per day at no additional cost. Note that advanced ingestion is required for large, image-heavy, or tabular documents to ensure accurate synthesis. For licensing details, refer to [Context Grounding licensing](https://docs.uipath.com/automation-cloud/automation-cloud/latest/admin-guide/context-grounding-licensing). :::note This feature is currently available upon request for Enterprise and Trial customers. ::: ## July 14, 2025 ### Introducing the UiPath-LLamaIndex integration for coded agents The UiPath LlamaIndex Agents SDK is now available. This Python SDK allows developers to seamlessly build and deploy LlamaIndex agents to the UiPath Cloud Platform. With this integration, developers can interact with UiPath Cloud services from within their LlamaIndex-based agents, and leverage Action Center integration to incorporate human-in-the-loop (HITL) workflows. For details, refer to the [Quickstart guide: UiPath LLamaIndex Agents](https://uipath.github.io/uipath-python/llamaindex/quick_start/). ## July 9, 2025 ### Introducing a simplified agent instance management and interactive trace views We have updated the Agents page in Automation Cloud to provide clearer navigation and deeper visibility into agent activity. The **Instances** section is now organized into three distinct tabs: **All agents** for a comprehensive view of all your agents, **Early adopter agents** for agents created as part of the early adopter program, and **Errors** (formerly Incidents) for quickly surfacing failed runs. The **Management** section includes **Templates**, for quickly accessing the Marketplace, and **Indexes**, which brings all the index monitoring capabilities from Orchestrator into a unified, accessible interface. For details, refer to [Managing UiPath agents](https://docs.uipath.com/agents/automation-cloud/latest/user-guide/managing-uipath-agents). ![The new Agents home page featuring the Instances and Management tabs](https://dev-assets.cms.uipath.com/assets/images/agents/agents-the-new-agents-home-page-featuring-the-instances-and-management-tabs-4d67894e.webp) We have also introduced a new trace visualization feature accessible from the **All agents** instances tab. This view presents each agent run as an interactive node graph, allowing you to zoom, pan, and explore execution paths. Hovering or clicking on nodes reveals detailed information such as input/output data, logs, and performance metrics. For details, refer to [Traces](https://docs.uipath.com/agents/automation-cloud/latest/user-guide/traces). Note that trace visualization is a preview feature. ![The node-based visual representation of a trace](https://dev-assets.cms.uipath.com/assets/images/agents/agents-the-node-based-visual-representation-of-a-trace-bce528e8.webp) ## Automation Cloud release digest To find out what changed in Automation CloudTM at the platform level and across other first-party services in July 2025, refer to the [Automation Cloud release notes](https://docs.uipath.com/automation-cloud/automation-cloud/latest/release-notes/july-2025).