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.
Follow this change log by RSS
Free for your reader, newsletter or automation tool. One feed covers the whole index, and every category has its own.
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.
9 entries matching filters
Agent capability
A live preview of the agent's changes now sits next to the prompt in Netlify's Agent Runners, instead of in a separate tab. The agent can also flag a missing capability, such as data that needs to persist, and the user can approve adding a Netlify database from the same view.
Checking agent output and approving infrastructure changes in one place shortens the loop for teams letting nontechnical staff direct a coding agent.
Security / enterprise
Netlify changed its defaults so every new site and app starts as a private project. Teams can build, deploy and preview as normal, but the project stays inaccessible to the public until someone makes it public.
Agent built apps are being deployed by people who are not thinking about exposure. Private by default means a prototype with real data does not end up on the open internet by accident.
Agent capability
Netlify's Agent Runners now manage their remaining credit budget, finishing in progress work and leaving the project in a working state when credits run low instead of stopping abruptly.
An agent that runs out of budget mid change can leave a broken build. Budget aware wrap up is a small feature with a real reliability payoff.
Integrations
Anthropic's Claude Opus 5 model is now accessible via Netlify's AI Gateway and Agent Runners. Developers can utilize the Anthropic SDK in Netlify Functions with zero configuration and automatic handling of API keys.
Organizations can now build and deploy AI agents using Anthropic's Claude Opus 5 model without the overhead of managing separate API credentials. This streamlines the development workflow and centralizes billing within the Netlify ecosystem.
Integrations
Google's Gemini 3 Pro Preview model has been integrated into Netlify's AI Gateway and Agent Runners. The update permits developers to use the Google GenAI SDK in Netlify Functions without manual API key management.
Teams can experiment with Google's latest preview models for their AI agents seamlessly. The zero-configuration setup reduces friction for developers testing new capabilities while maintaining centralized access control.
Integrations
Netlify added support for Google's Gemini 3.7 Flash model in its AI Gateway and Agent Runners. This enables developers to use the Google GenAI SDK within Netlify Functions with zero configuration, bypassing the need to manage API keys or set up authentication manually.
Teams can securely leverage Google's new model for inference without handling secret management or infrastructure overhead. This simplifies deployment for AI-powered applications by routing all requests through a pre-configured, centrally managed gateway.
Integrations
Netlify expanded model choice for its AI Gateway and Agent Runners by adding support for OpenRouter and OpenCode. Developers can now route requests to various open and commercial models using standard OpenAI SDKs or REST APIs, restricted to providers that support a Zero Data Retention (ZDR) policy.
This prevents vendor lock-in and allows engineering teams to easily swap between different LLMs for their agents without changing underlying code. The strict ZDR requirement also ensures enterprise data privacy standards are maintained when using third-party models.
Integrations
Netlify has added support for Anthropic's Claude Opus 5 model to its AI Gateway and Agent Runners. Developers can now use the Anthropic SDK within Netlify Functions to access the model directly, benefiting from built-in caching, rate limiting, and authentication without managing separate API keys.
Engineering teams building agentic workflows can now leverage Anthropic's most capable model without building custom middleware for credential management. Centralizing model access through the platform also ensures organizations can enforce governance and track usage costs consistently.
Integrations
Netlify partnered with Anthropic to embed deployment capabilities directly inside Claude Design. Users can deploy generated designs to a live Netlify site with a single click and push ongoing iterations without manual exports.
This integration collapses the gap between prototyping and deployment, accelerating the release cycle for AI generated applications. It enables rapid iteration by keeping the design tool and the live environment synchronized automatically.
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 1648 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 Oct 21, 2026, covering Equal AI, Kognitos, Findem.
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. The same entries are published as a free RSS feed at agenticindex.io/feeds/changes.xml, with one feed per ranking category listed at agenticindex.io/use-this-data.
Last updated: Oct 21, 2026 · 1648 tracked changes across 550 vendors