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.
6 entries matching filters
Agent capability
Deputy Agent, launched by Cresta, is a long running agent that carries customer operations work such as refunds, transaction disputes and insurance claim appeals through to completion. A workflow can start during a live call, come from a handoff, or begin when a document or request enters a back office queue, and when it has to wait for a document or approval, Deputy saves its progress and picks up when the information arrives.
Contact center buyers get an agent that keeps working after the conversation ends, with an audit trail of actions and approvals and business rules that decide what it may do on its own.
Deployment / data residency
Agent configurations in Cresta can now move through testing, staging and production with new environments and deployments. Environments hold shared variables and secrets, and deployments set which revision runs where, split live traffic and promote or roll back a configuration.
Teams running customer facing agents can stage changes, split traffic between versions and roll back inside the platform, instead of pushing a prompt or tool change straight to production.
MCP / tool calling / API
Cresta introduced a Command Line Interface (CLI) that provides a developer surface for interacting with its platform. The tool allows builders and coding agents to examine conversations, agent configurations, knowledge bases, and evaluation histories through a single terminal interface.
Engineering and operations teams can programmatically access platform context and integrate it directly into their workflows. This supports quality reviews, regression testing, and continuous improvement of AI agents by carrying evidence across systems.
Observability / auditability
Cresta expanded its Cresta Insights platform with a new Real-Time Trends feature that detects conversational anomalies and spikes minute by minute. The release also upgrades the AI Analyst to autonomously execute multi-step research queries and enhances Topic Discovery to automatically generate multi-layered conversation taxonomies.
Contact center leaders can proactively catch emerging issues, such as outages or product faults, as they happen without relying on predefined keywords. The autonomous research tools reduce the manual labor required to categorize customer interactions and extract actionable insights.
Funding / partnership
Cresta received an investment from W23 Global, a venture capital fund backed by five leading global grocery retailers including Ahold Delhaize, Tesco, and Woolworths Group. The funding supports Cresta's platform, which combines autonomous AI agents with real-time coaching and conversation intelligence for human teams.
This investment from major retail corporations signals strong enterprise validation and financial stability for Cresta. Buyers evaluating Cresta can expect continued development of AI features tailored for large-scale consumer-facing operations and enhanced support for complex retail contact center environments.
Agent capability
Cresta launched Training Simulator, an agentic training product that replaces scripted role-play with live, adaptive simulations. The product generates simulated customers based on a company's actual historical conversation data, allowing human agents to practice handling complex interactions like retention saves and upselling.
Contact center leaders can use this tool to reduce agent onboarding time and improve readiness before agents interact with real customers. By grading simulated scenarios with the same artificial intelligence quality criteria used on live calls, buyers gain a unified system for training, quality management, and performance measurement.
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