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
Funding / partnership
Arize AI entered into a definitive agreement to be acquired by observability vendor Dynatrace in a cash and stock transaction valued at $915 million. The acquisition will combine Arize's AI agent evaluation and experimentation software with Dynatrace's production monitoring capabilities.
Enterprise buyers can anticipate deeper integrations that connect agent output evaluations directly with runtime telemetry and infrastructure logs. This consolidation provides a unified platform for teams looking to automate the continuous improvement cycle of custom AI agents from development into production.
Agent capability
Arize announced Signal, a capability within Arize AX that utilizes autonomous agents to investigate and resolve software issues automatically. Signal surfaces failure patterns from production telemetry, uncovers root causes, and generates review-ready fixes as part of a self-improving feedback loop.
Engineering teams can move beyond manual debugging to autonomous software issue resolution to reduce downtime and operational overhead. This represents a shift from traditional observability to self-healing agentic systems.
Observability / auditability
Arize added a User Friction Evaluator to both the Python and TypeScript SDKs. This built-in classification evaluator automatically detects and labels user frustration, corrections, or challenges to unrequested actions during conversational turns.
Product teams can systematically measure and flag negative user interactions. This makes it easier to track application quality and evaluate whether product updates effectively improve the user experience.
MCP / tool calling / API
Arize released Phoenix 19.1.0 with a one-command setup via the Phoenix CLI to connect coding agents like Claude Code and Cursor to the Phoenix MCP server. The command automatically registers the server into the agent configuration and defaults to OAuth login.
Developers save time and reduce configuration errors when connecting their preferred AI coding agents to Phoenix observability data. This accelerates the adoption of agent-based workflows within an organization.
Security / enterprise
Arize Phoenix 19.0.0 introduces an embedded OAuth2 authorization server and centralized REST CRUD capabilities for API key management. The release also includes a beta Remote MCP server that allows MCP-compatible clients to directly query and operate on projects, traces, and datasets without requiring a local installation.
Enterprises benefit from robust authentication controls and centralized credential management. The built-in Remote MCP server securely connects coding agents directly to the platform to simplify local development workflows.
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