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
Agent capability
Writer released Palmyra X6, a new 744-billion-parameter model optimized for marketing and revenue tasks, alongside a rebuilt Agent harness. The upgraded orchestration engine allows the agent to run unattended on a single objective for up to eight hours, dynamically adapt its reasoning, and delegate work to sub-agents or batch-execute tasks. The release also introduces new AI Studio governance tools for administrators to track token consumption and configure multi-model support, including third-party models from Anthropic and OpenAI.
Enterprise IT and revenue leaders can now deploy complex, multi-step agentic workflows in production with significantly improved token economics and oversight. The combination of Palmyra X6 and the new harness reduces average task costs by 52 percent and execution time by 48 percent, mitigating the runaway spend typically associated with long-running AI agents. Administrators gain centralized reporting and the flexibility to route specific tasks to third-party models when necessary.
Agent capability
Writer released Palmyra X6, its new general-purpose model optimized for agentic work and long-running tasks. Alongside the model update, Writer introduced Agent Memory to retain context across sessions and a new Capabilities tab in AI Studio that allows administrators to enable and restrict browser automation for agents.
The new model improves cost efficiency and performance for complex, multi-step agent workflows. Additionally, the introduction of persistent memory and granular browser automation controls allows teams to build more autonomous, context-aware agents that can safely navigate the web.
Observability / auditability
Writer announced Writer AI HQ, a new enterprise AI agent platform featuring customizable agent workspaces for specific teams. The release includes Supervise in beta, an observability command center that allows administrators to enforce policies, monitor performance, and troubleshoot agents using logs, traces, and execution paths.
Enterprise IT and operations leaders gain granular governance and observability over deployed AI agents. This allows organizations to safely scale agentic workflows across different departments while maintaining strict compliance and performance monitoring.
Security / enterprise
Cybersecurity researchers at Sand Security disclosed WriteOut, a critical session isolation vulnerability in the managed sandbox of the Writer AI platform. The flaw allowed attackers to exploit the agent preview feature to leak session tokens and gain cross-tenant access. Writer promptly deployed a server-side patch that removes session credentials from sandbox previews and isolates the preview origin.
Security-conscious buyers must account for the platform's shared responsibility model and incident response capabilities. The patched vulnerability underscores the importance of session isolation in AI agent deployments, though Writer confirmed no customer data was compromised.
Agent capability
Writer launched WRITER Agent, a single interface merging the conversational Ask WRITER with the task automation of Action Agent. It adds file uploads up to 500MB and new AI Studio admin controls to toggle agent capabilities like browser automation, web search scope, and website hosting.
Folding chat and action into one surface simplifies complex task execution, and granular capability toggles let IT enforce internet-usage policy before scaling agents across the org.
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