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.
5 entries matching filters
MCP / tool calling / API
Arcade has introduced the ability for developers to bring any third-party Model Context Protocol (MCP) server to the Arcade.dev platform. This update enables teams to integrate external or custom MCP servers directly into their Arcade environment.
This capability allows organizations to leverage their existing custom or third-party MCP servers while still benefiting from Arcade's centralized authentication, governance, and runtime infrastructure. It significantly reduces vendor lock-in and accelerates the deployment of proprietary tools.
Security / enterprise
Arcade has launched Role-Based Access Control for its platform, allowing teams to assign organization admin, project admin, and member roles. This introduces an administrative layer that controls who can manage the workspace and configure the underlying tools.
Governing AI agent infrastructure is a key requirement for moving from pilot projects to company-wide deployments. By providing granular administrative roles, teams can safely distribute tool access without risking unauthorized configuration changes to the broader environment.
MCP / tool calling / API
Arcade updated its runtime to support the new stateless Model Context Protocol (MCP) specification. The platform simultaneously maintains support for older session-based MCP versions, allowing both stateful and stateless connections to run in parallel.
Platform teams can incrementally migrate their MCP servers to the new protocol version on their own schedule without causing downtime for existing long-running agent workflows.
Integrations
Arcade launched four new agent-optimized toolkits for Power BI, Postman, Fireflies, and Insightly. The release also includes functional upgrades to the existing integrations for Gmail, Excel, Outlook, and Linear.
These native integrations allow agents to securely authenticate and execute complex tasks within familiar enterprise systems, expanding the range of delegated actions without developers needing to build custom connections.
Workflow orchestration
Arcade launched SkillBench, an evaluation index that grades the quality of AI agent skills. The platform currently scores approximately 39,000 skills across six dimensions, including safety and tool boundaries. It assigns each skill a letter grade from A to F to help developers assess reliability.
Enterprise engineering teams can use this tool to vet third-party agent skills before deployment. It provides a transparent framework to ensure that integrated workflows meet production safety and quality standards. This reduces the risk of insecure or poorly defined agent actions.
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