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.

A
Arcade2026-08-27
ImpactHigh
VerificationVerified

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.

A
Arcade2026-08-13
ImpactHigh
VerificationVerified

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.

A
Arcade2026-07-23
ImpactHigh
VerificationVerified

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.

A
Arcade2026-07-23
ImpactMedium
VerificationVerified

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.

A
Arcade2026-07-16
ImpactHigh
VerificationVerified

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.

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

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.