Jason Adams @jason_the_adams (Team RepTeam RepA Team Rep is a person who represents the Make WordPress team to the rest of the project, make sure issues are raised and addressed as needed, and coordinates cross-team efforts.) – Automattic
AI 1.1.0 has been released and is available for download! “What’s new in AI…” posts (labeled with the #ai-release tag) are posted following every AI pluginPluginA plugin is a piece of software containing a group of functions that can be added to a WordPress website. They can extend functionality or add new features to your WordPress websites. WordPress plugins are written in the PHP programming language and integrate seamlessly with WordPress. These can be free in the WordPress.org Plugin Directory https://wordpress.org/plugins/ or can be cost-based plugin from a third-party. release, showcasing new features included in each release.
We’re pleased to announce the release of AI 1.1.0, the latest update to the canonical plugin powering AI-powered features in WordPress. This release introduces two new experiments, Type-ahead Text and Key Encryption, while continuing to improve content workflows, comment moderation, developer settings, Abilities APIAbilities APIA core WordPress API (introduced in 6.9) that creates a central registry of capabilities, making WordPress functions discoverable and accessible to AI agents, automation tools, and developers. Transforms WordPress from isolated functions into a unified system. integration, and overall interface polish.
What’s new in 1.1.0?
New Experiment: Type-ahead Text
AI 1.1.0 introduces a new Type-ahead Text experiment for the blockBlockBlock is the abstract term used to describe units of markup that, composed together, form the content or layout of a webpage using the WordPress editor. The idea combines concepts of what in the past may have achieved with shortcodes, custom HTML, and embed discovery into a single consistent API and user experience. editor.
When enabled, Type-ahead Text can suggest inline ghost text at the end of paragraph blocks while a user is writing. It can also be triggered manually within supported blocks, giving writers a lightweight way to explore AI-assisted continuation without leaving the editor flow.
The experiment supports:
Context-aware suggestions based on surrounding content
Manual triggering within supported blocks
Keyboard controls for accepting or dismissing suggestions
ProviderProviderAn AI service offering models for generation, embeddings, or other capabilities (e.g., Anthropic, Google, OpenAI). and model overrides through developer settings
Integration with site Guidelines (aka Knowledge)
This brings a familiar AI writing pattern directly into WordPress while keeping it experimental, opt-in, and available for community testing.
New Experiment: Key Encryption
This release also introduces a Key Encryption experiment focused on improving how AI Connector APIAPIAn API or Application Programming Interface is a software intermediary that allows programs to interact with each other and share data in limited, clearly defined ways. keys are stored.
When enabled, AI Connector API keys are encrypted before being stored in the database and decrypted when needed for use. If the experiment is disabled, global AI functionality is turned off, or the plugin is deactivated, keys are restored so sites are not left in an unusable state.
This experiment is especially relevant as WordPress continues exploring Connectors and AI provider integrations. It gives the project a practical place to test API key handling approaches and gather real-world feedback before similar patterns are considered elsewhere.
Smarter content readiness checks
AI 1.1.0 improves when content-based features become available.
Features that rely on post content are now disabled until minimum content thresholds are met. The release also improves those checks by using locale-aware word or character counting, helping content workflows behave more reliably across languages.
This affects workflows such as:
Content Resizing
Content Summarization
Content Classification
These updates should reduce confusing states where an AI action appears available before there is enough content to produce a useful result.
Comment Moderation improvements
The Comment Moderation experiment continues to get more control and refinement.
AI 1.1.0 adds a setting that lets site owners choose whether guest comments should be analyzed automatically. This setting defaults to enabled, but can be turned off to avoid running AI sentiment or toxicity analysis on anonymous comments.
This is useful for sites that receive a high volume of guest or spam comments and want more control over where AI analysis is applied. The release also skips comment analysis and moderation for comments already marked as spam or trashTrashTrash in WordPress is like the Recycle Bin on your PC or Trash in your Macintosh computer. Users with the proper permission level (administrators and editors) have the ability to delete a post, page, and/or comments. When you delete the item, it is moved to the trash folder where it will remain for 30 days., reducing unnecessary AI requests.
New core/read-settingsAbilityAbilityA registered, self-documenting unit of WordPress functionality that can be discovered and invoked through multiple contexts (REST API, Command Palette, MCP). Includes authorization and input/output specifications.
AI 1.1.0 adds a new core/read-settings Ability.
This read-only ability exposes eligible site settings through the Abilities API, providing another example of how WordPress capabilities can be made available to AI-powered workflows in a structured, permission-aware way. The ability requires appropriate permissions and supports filtering returned settings, creating a useful foundation for future admin, assistant, and developer workflows.
Workflow and interface refinements
AI 1.1.0 also includes several workflow and user experience improvements:
Editorial Notes now prompt users to save after running.
Editorial Note loading indicators are scoped to the active block.
Editorial Updates only appear when pending notes are linked to the current blocks.
Title Generation button text and loading states are now more consistent.
Content Classification term suggestions persist more reliably and recover better when term assignment fails.
Experiment modal warnings now use the standard Notice component.
Settings screen snackbars no longer overlap the main content.
AI Request Logs now use a fixed 30-day window so summary cards and the logs table match.
Documentation now more clearly notes that the plugin has targeted support only for the Block Editor.
Developer and extensibility updates
This release includes several improvements for developers and advanced site builders:
A new wpai_has_image_generation_supportfilterFilterFilters are one of the two types of Hooks https://codex.wordpress.org/Plugin_API/Hooks. They provide a way for functions to modify data of other functions. They are the counterpart to Actions. Unlike Actions, filters are meant to work in an isolated manner, and should never have side effects such as affecting global variables and output. allows third parties to declare Image Generation support, including cases where authentication does not rely on an API key.
Abilities Explorer schema output now handles non-ASCII characters more readably.
Ability input handling was improved so omitted input can still allow schema defaults to apply.
Scalar input schema validation is now supported in Abilities Explorer.
These changes help make the plugin a stronger reference implementation for others building AI-powered WordPress features.
What’s next in 1.2.0?
Work is already underway on additional Features, Experiments, and infrastructure improvements planned for 1.2.0 and future releases, including:
As always, we welcome feedback, testing, and contributions from the community. Whether you are interested in editor UXUXUX is an acronym for User Experience - the way the user uses the UI. Think ‘what they are doing’ and less about how they do it., APIs, accessibilityAccessibilityAccessibility (commonly shortened to a11y) refers to the design of products, devices, services, or environments for people with disabilities. The concept of accessible design ensures both “direct access” (i.e. unassisted) and “indirect access” meaning compatibility with a person’s assistive technology (for example, computer screen readers). (https://en.wikipedia.org/wiki/Accessibility), performance, or AI ethics and policy, there are many ways to participate.
You must be logged in to post a comment.