Agentic Index
Agentic AI Platform Change Log
Agentic Index tracks material changes across agentic AI platforms, including new agent capabilities, workflow orchestration updates, integrations, MCP/tool-calling changes, memory features, human approval controls, observability, deployment options, pricing, funding, and verification-status updates. This change log is the index that tracks changes to agentic AI platforms, updated weekly. If you are trying to keep up with changes to AI agent platforms without reading every vendor's release notes separately, this is the feed to read.
Public-source research. All entries are sourced from official vendor blogs, changelogs, documentation, or press materials. Support levels marked Needs Review or Publicly Claimed should be independently verified before relying on them for procurement decisions.
7 entries matching filters
Agent capability
UiPath announced the general availability of Autopilot as a coding agent within Studio Desktop STS. Operating on a flexible skills and tools architecture rather than a fixed pipeline, the agent can plan, build, debug, and troubleshoot automations from text prompts. The release also introduces Model Context Protocol (MCP) server support for external integrations and reads project conventions from local configuration files.
Enterprise automation teams receive a native AI assistant that operates across the entire development lifecycle within their primary workspace. The addition of MCP server support allows organizations to securely connect the agent to proprietary internal APIs, while local configuration files ensure generated code adheres strictly to specific team standards.
Pricing / packaging
UiPath introduced a Community plan for organizations on Unified Pricing, providing free access to its agentic platform. The plan includes a fixed set of licenses and a monthly Credits pool for individual developers and builders.
This allows developers and automation enthusiasts to build and test AI agents, coding agents, and orchestration workflows at no cost before committing to paid enterprise tiers.
Security / enterprise
Organization Administrators can now use the Check access API to retrieve effective access permissions for users, groups, or external applications across the entire organization. The results include both organization-scoped and tenant-level assignments.
Security and compliance teams can more easily audit and verify access rights programmatically across all active tenants, improving governance and reducing administrative overhead.
Pricing / packaging
UiPath updated the AI Unit consumption model for Document Understanding, charging per operation rather than a flat rate per page. Under the new model, digitization is free while classification and extraction are billed individually.
Organizations using Document Understanding can better optimize their costs, especially for workflows requiring only partial document processing. Customers can also combine Intelligent Xtraction and Processing licenses with Document Understanding without incurring additional per page costs.
MCP / tool calling / API
UiPath launched a public preview of UiPath for Coding Agents, enabling developers to build automations directly from AI coding agents like Claude Code, Cursor, and Codex CLI. This update introduces a new command-line interface (uip CLI) and UiPath skills that allow coding agents to interact with a user's UiPath organization using natural language. It also introduces a Coding Agents for Test feature that allows these agents to autonomously read test cases, write execution results, and update requirement coverage data.
Engineering and QA teams can now leverage popular AI coding assistants to design, orchestrate, and test enterprise automations without relying solely on a separate visual designer. This allows developers to integrate UiPath automation and testing management natively into their existing AI-assisted development environments.
Agent capability
UiPath upgraded Autopilot in Studio Desktop to function as a fully autonomous coding agent rather than a drafting tool. The agent can now plan, build, run, debug, and refactor automations directly within the Studio environment using official UiPath skills and command line interface tooling.
Developers can streamline their automation building lifecycle without needing separate subscriptions or context switching. By acting as a native coding assistant with full project context, Autopilot reduces development time and simplifies troubleshooting tasks like repairing broken selectors.
Workflow orchestration
UiPath released its July 2026 updates for Automation Cloud and Test Cloud, introducing a preview of Test with Coding Agents for managing test data via AI assistants. The update also brings Azure Private Link support for Test Cloud in the US, new public API endpoints for video recordings, and bulk-edit capabilities for queue items in Orchestrator.
The addition of Azure Private Link enhances network security for US organizations with strict compliance requirements for their testing environments. Furthermore, the Orchestrator interface improvements and testing APIs streamline administrative overhead for managing complex automation queues.
Current rankings
These changes feed the index. See where each category stands: the best vendors of 2026, ranked by verified capability coverage.
Capability coverage
Every change above is graded against the same 14 capability axes. Each axis has its own page showing how much of the index documents it, which categories concentrate it, and the leading platform in each.
The AI agent directory for business · The full feature taxonomy · Pricing research
Common questions
How do I keep up with changes to AI agent platforms?
Read one maintained change log instead of tracking each vendor's release notes separately. The Agentic Index change log records 981 verified updates across agentic AI platforms, updated weekly, covering new agent capabilities, MCP and tool calling changes, memory, human approval controls, observability, deployment options, pricing and funding. Every entry names the vendor, the date, the change type and an impact level, and links to that vendor's profile.
How often is the agentic AI change log updated?
Weekly. The most recent update was Sep 4, 2026, covering LivePerson, Serval, ServiceNow.
How do I track changes for one specific AI agent vendor?
Filter the change log by vendor, or open that vendor's profile page, where the same verified entries appear alongside its capability coverage across the 14 point Agentic Index taxonomy.
Where can I find a single feed of agentic AI platform updates?
This page is that feed. Agentic Index reviews vendor blogs, changelogs, documentation and press materials every week and files what materially changed, so keeping up with changes to AI agent platforms is one page rather than several hundred. Entries are filterable by vendor, change type, impact level and verification status, and each one carries the evidence basis it was graded from.
Last updated: Sep 4, 2026 · 981 tracked changes across 372 vendors