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
ServiceNow introduced AI Specialists, a new agentic capability designed to autonomously handle end-to-end workflows such as incident resolution. The first generally available specialist, the L1 Service Desk AI Specialist, can triage incidents, diagnose issues, apply fixes, and communicate with requesters. It operates in either an autonomous Autopilot mode or a human-in-the-loop Copilot mode.
This allows IT teams to fully offload routine Level 1 support tickets to an AI agent rather than just using AI for single-turn assistance. The inclusion of a Copilot mode provides a safe deployment path by requiring human review before the agent posts solutions, ensuring oversight during initial rollout.
Human approval / guardrails
ServiceNow rebranded Now Assist for Creator to ServiceNow Otto for Creator and introduced several updates to its Build Agent. The release adds the ability to define custom skills and rules for the agent, allows developers to run and roll back scripts directly from the chat panel, and enables the agent to build within isolated Developer Sandboxes.
Development teams can now enforce organizational coding standards by providing the AI agent with custom rules and skills. The addition of isolated sandboxes and script rollback capabilities significantly reduces the risk of AI-generated code causing unintended issues in shared environments.
Security / enterprise
ServiceNow launched Autonomous Security, a suite of six unified security solutions integrated into its AI Control Tower. The release introduces AI Specialists, including Agentic Exposure Management and Vulnerability Resolution, which autonomously consolidate vulnerability findings, orchestrate triage, and execute low-risk patches at scale.
Security and risk teams can transition from reactive vulnerability management to autonomous, prevention-first defense. By leveraging AI agents to handle routine patching and exposure triage, organizations can significantly reduce their attack surface and accelerate remediation times without adding headcount.
MCP / tool calling / API
ServiceNow published an overview of Action Fabric, an interoperability framework connecting AI agents across the enterprise. It features an MCP Server Console for external clients to invoke ServiceNow tools, an MCP Client for ServiceNow agents to call external systems, and Agent2Agent protocol support for peer collaboration.
This prevents the creation of isolated AI agent silos by enabling cross-platform orchestration. Buyers can securely expose ServiceNow workflows to external assistants or empower Now Assist with specialized external capabilities while maintaining strict governance and access controls.
MCP / tool calling / API
ServiceNow released version 1.0.0 of its Advanced Approval Management AI, which includes Model Context Protocol (MCP) tools. This integration allows agents and approvers to submit, review, and act on quote approval requests directly from external MCP clients, such as Anthropic's Claude desktop app.
Surfacing approval workflows directly within an enterprise's chosen conversational AI assistant removes the need for users to switch context to the ServiceNow platform. This reduces friction for managers and accelerates decision-making by placing administrative approvals in their natural flow of work.
Agent capability
ServiceNow launched the NOW Quote AI Agent within the Quote Management application. The agent automates B2B sales quoting by reading opportunity notes, automatically configuring products, resolving non-standard names, applying discounts, and generating ready-to-review quotes with full audit trails.
Sales operations teams frequently face compliance risks and administrative bottlenecks when handling manual pricing and catalog configurations. This automation enables reps to bypass manual quoting entirely, accelerating deal velocity while ensuring price list accuracy.
Agent capability
ServiceNow integrated Agentic AI into its Telecommunications Network Inventory (TNI) application via version 2.0.2. The release introduces an autonomous infrastructure-allocation agent that processes free-text change requests and converts them into validated, policy-aware network allocations.
Telecom operators deal with complex, manual infrastructure provisioning that requires strict adherence to network policies. This update ensures that operators can provision resources faster with fewer errors, offering full traceability directly within the Network Inventory workspace.
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