Agentic Index

Zite changelog, updates and release notes

Agentic Index tracks material product changes at Zite and has logged 4 entries since September 30, 2026. Each entry is dated, sourced from the vendor's own materials or the press, and carries a change type and an impact level, so it can be read against Zite's capability coverage across the 14 point Agentic Index taxonomy.

Read the Zite assessment →

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.

All feeds and terms

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.

Z
Zite2026-11-12
ImpactHigh
VerificationPartially Verified

Agent capability

Zite added a Security page where a Zite agent reviews every app and automation in a workspace and lists findings by severity, covering public pages or actions anyone can call, missing permission checks, exposed secrets, data shown to the wrong people and dependencies with known vulnerabilities. Users can choose Fix or Fix all to have the agent make the smallest change that closes each issue, or ignore an issue with a required reason. Scans can also be run from an outside agent such as Claude, ChatGPT or Claude Code through the Zite MCP, and scans and fixes from the Security page are free up to 20 credits a day per workspace. Build chats now also run in the background on Zite's side, so closing the tab or losing the connection no longer stops a build.

Teams publishing AI built apps get a built in review for access control and secret leaks before customers or attackers find them, with an audit trail of ignored findings and their reasons.

Z
Zite2026-10-22
ImpactMedium
VerificationPartially Verified

MCP / tool calling / API

Outside agents connected to Zite, such as Claude, ChatGPT or Cursor, can now upload files from the user's computer straight into the database and create or edit AI fields. Their changes appear in a feed of their own, and version history shows which agent made each one. A new Bring your own agent link on Home connects an agent without opening a workspace first.

Teams that run Zite from their own chat or coding agent can hand it more of the work and still see afterward exactly which agent changed what.

Z
Zite2026-10-09
ImpactLow
VerificationPartially Verified

Agent capability

Zite's Plan mode can now connect integrations such as Airtable or Notion while planning and read the actual tables, fields and records in those tools before it writes the build plan.

Plans grounded in a company's real data structures should need fewer corrections once the agent starts building, which cuts rework on apps built on top of existing systems.

Z
Zite2026-09-30
ImpactHigh
VerificationVerified

Human approval / guardrails

Zite added Auto, a fourth agent mode next to Build, Plan and Chat, that changes an app the way Build does but applies most changes without waiting for an Approve click. It still stops for integration sign ins, secrets, new apps, clarifying questions and pending workflow runs, and auto approved changes are marked in the Changes panel. Build remains the default.

This moves where a person signs off on the build agent's work, so admins should decide which workspaces allow longer unattended builds and how auto approved changes get reviewed.

What has changed at Zite recently?

The most recent change Agentic Index logged at Zite is dated November 12, 2026. Zite added a Security page where a Zite agent reviews every app and automation in a workspace and lists findings by severity, covering public pages or actions anyone can call, missing permission checks, exposed secrets, data shown to the wrong people and dependencies with known vulnerabilities. It is one of 4 dated, sourced entries the index holds for Zite.

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 2396 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 Nov 15, 2026, covering Propel AI, Shapes, Qwen Code.

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: Nov 15, 2026 · 2396 tracked changes across 670 vendors

Contact us

Found a vendor we missed? Have feedback on the index? We'd love to hear from you.