Changelog

Visual Editor multi-select: Visual Editor now supports multi-select, making it easier to select multiple elements while editing a page.

Atoms platform information support: AI can now read Atoms FAQ, platform capability notes, and related knowledge on demand, improving answers about Atoms features, usage, and common questions.

Skill capability updates: Skill-related capabilities have been updated to support AI task understanding, tool usage, and execution workflows.

Visual Editor editing experience: Improved the Visual Editor entry point, toolbar position, element selection, and sandbox startup feedback for a clearer editing flow.

Visual Editor startup speed: Improved Visual Editor startup speed, reducing wait time when entering editing mode.

Component toolbar display: Removed toolbars from some components that cannot be edited directly, reducing misleading interaction cues.

Design to Visual Editor entry experience: Improved the path and interface feedback when entering Visual Editor from Design, reducing confusion during mode switching.

Chat labels and interface details: Improved the removal action for pinned labels above Chat and unified some label naming for more consistent interface wording.

Select to Chat flow: Select to Chat has been consolidated with the related Chat interaction, so users can select content and start a Chat through a more unified flow.

AI context understanding: Improved how AI understands task environment information such as the current date, project root, platform, Shell, OS, and model, reducing irrelevant information in replies and execution flows.

Atoms platform knowledge organization: Improved the structure and triggering logic for Atoms platform knowledge, helping AI better match topics such as Atoms Cloud, Remix, file upload, image upload, and LLM models.

Default project titles: Updated the default project title template to reduce unnatural or overly generic titles in newly created projects.

Fixed an issue where the issue resolve button and guidance were missing after a version build failed.

Fixed loading state interference during Publish. Publish status is now correctly tied to the current Chat route, reducing confusing state displays across sessions.

Fixed an issue where VIP users’ Live site updates could fail to take effect or occasionally return a 503 error.

Fixed an issue where clicking Generate once could create two duplicate images, reducing repeated generation and resource waste.

Fixed incorrect user working status displays in collaboration scenarios.

Fixed version selection logic so the latest available version is used by default, reducing issues caused by fixed version selection.

Fixed the display condition for the left progress bar in the thinking content area. It now appears only when multiple thinking items exist.

Fixed an issue where the confirmation dialog in the design panel could not be closed properly.

Fixed unclear feedback when the selection limit is exceeded.

Fixed confusion between Atoms Cloud and Cloud & AI Wallet, helping AI distinguish product capabilities from wallet and billing concepts more clearly.

Fixed unclear prerequisite guidance for Atoms Cloud in AI capability tasks, reducing misleading instructions.

Fixed repeated processing of Stripe payment events and invoice paid flows, reducing duplicate processing or billing risk.

Fixed workspace invitation expiration time parsing to improve invitation link validity checks.

Video Mode entry points and video editing: Video Mode and Create Video prompts are now easier to find from the homepage and creation entry points. Eligible users can enter the video generation, preview, and editing flow, with smoother zooming, clip selection, splitting, and local export in the editor.

Project dropdown menu and immersive workspace: Project pages now include a Project dropdown menu for Go to Dashboard, Credits, Settings, Connectors, Rename project, and Details. The sidebar now collapses inside Projects for a more focused workspace, while staying expanded outside Projects for easier navigation.

Project references: Chat references have been expanded to support combining different content types in the same message. Each message can include up to one Project reference, making it easier to provide context when Remixing, copying, or referencing an existing project.

More flexible Keys fill-in flow: When a task requires an API Key, users can skip some Key configuration and continue the task, then return later through the Fill in API Key prompt. This reduces interruptions during the current chat flow.

Improved multimedia generation: Generation quality has been improved for scenarios such as AI SaaS and POD ecommerce. Video, music, and image capabilities have also been refined so generated results, previews, and follow-up editing flows feel more connected.

Improved Chat reference experience: Files, Projects, AI capabilities, and Keys can now be combined more naturally. File reference names and preview names have also been aligned to make referenced content easier to recognize.

Improved Video Mode interactions: Video Mode state management, entry points, announcements, and page layout have been refined to reduce conflicts with other generation goals and make it clearer when the current task is in a video generation context.

Improved Keys experience: The Keys fill-in flow has been improved across skipping, later completion, Key status refresh, and button display. Form state is also less likely to be reset during submission.

Improved password reset security: Password reset pages now better protect sensitive link information, reducing the risk of reset tokens being exposed through third-party plugins, analytics tools, or browser referrers.

Improved Agent message ordering: Message ordering in some multi-agent collaboration scenarios has been improved, reducing cases where messages appear out of sequence.

Fixed state and display issues in Project Picker, Project references, and file references.

Fixed drag-and-drop upload hint placement and disabled-state detection issues.

Fixed Video Mode state management, video parameter settings, video card previews, and video masonry layout issues.

Fixed Keys fill-in issues related to skipping Keys, incorrect button display, Key count display, and form state resets during submission.

Fixed some Agent message ordering issues, and reduced cases where internal project context files appeared in version diffs or file lists.

Fixed sensitive link protection issues in the password reset flow.

Fixed display and state issues in icons, warning banners, Stop button, modals, and sidebar interactions.

New database management interface: A new database management interface is now available in Atoms. It supports viewing PostgreSQL table structures, browsing and editing table data, and importing or exporting CSV files, making everyday database management easier.

Storage management in Settings: Settings now includes a storage management entry. You can view storage usage by project and folder, search, sort, paginate, navigate with breadcrumbs, and batch clean up large project files.

Build completion sound notifications: Chat now supports sound notifications when a build completes. You can choose first-build notifications, every-build notifications, or turn them off in Settings, with an option to preview the sound.

Upgraded `#` selector: The `#` selector has been upgraded into a multi-category popup with Upload, AI, Keys, and Projects categories. It supports searching files, AI capabilities, and Keys, along with keyboard navigation and improved desktop and mobile layouts.

URL link and Secret references: Chat now supports more flexible URL link and Secret references. Link content can be converted into usable file references, and Secrets can be added to the current project and used in chat.

More personalized homepage experience: Homepage notices can now be updated more dynamically. Personalized greetings also use recent visits and publish history to show content that better matches each user’s context.

More stable database and storage management: Database table structures, data editing, search and filtering, CSV import and export, and error messages have been improved. Storage management loading, search, pagination, deletion, and empty states are also clearer.

AppWorld Discover improvements: AppWorld Discover now supports language filtering, with improvements to app cards, exposure counts, filters, and mobile category browsing.

Publish and Team Mode improvements: Domain editing, publish status, and settings areas in Publish have been refined. A Team Mode guidance card now appears after first Publish to help users continue with team collaboration.

More concise agent responses: Agent responses and team collaboration summaries have been optimized to reduce repeated explanations and overly long replies, making responses shorter and more direct.

Public pages and SEO improvements: Sitemap management, public page indexing rules, and some SEO tags have been optimized to reduce private, functional, or invalid pages appearing in search results.

Fixed issues in database management related to dates, JSON, primary keys, empty values, pagination, filtering, import/export, and permissions.

Fixed storage management issues, including missing deletion failure messages, search errors, pagination issues, and root project display problems.

Fixed homepage greeting flicker, sound notification setting failures, and Team Mode guidance card state issues.

Fixed AppWorld Discover issues related to language filtering, filter display, mobile category scrolling, and app list syncing.

Fixed Publish issues related to domain editing display, publish status updates, and custom domain syncing.

Fixed URL link handling and Secret reference issues related to error messages, security validation, and file cleanup.

Fixed issues related to billing states, public pages, editors, clipboard behavior, draft recovery, and @ mention navigation.

Language filtering in App World: App World now supports filtering public apps by app language. The app language is identified based on the app content, and Remix apps inherit the original app language, making it easier to find apps in a specific language.

Audio and video deliverable cards: Audio and video deliverables in chat can now be displayed as cards instead of plain text links. Generated multimedia content is easier to recognize and review.

Folder drag-and-drop upload: Chatbox now supports dragging folders directly into the upload area, making it easier to import multiple local files at once. Drag-and-drop hints and upload status feedback have also been improved.

More accurate app language detection: App language detection has been improved to reduce misclassification in short text and mixed-language content. Language filtering results in App World are now more accurate.

Improved Chatbox input and upload experience: The maximum Chatbox height has been increased, making long-form input easier to read and edit. Drag-and-drop highlighting, upload status feedback, folder upload, and edge-case handling have also been improved.

Improved multimedia generation and preview: Audio, video, and image generation results are now displayed and previewed more reliably. Generated files are more likely to open in preview automatically, reducing first-preview failures, incorrect download prompts, and cases where audio or video results appear only as plain links.

Publish and Production Keys improvements: Publish modals, publish status, sharing entry points, domain hints, and Production Keys states have been improved for a more reliable post-publish management experience.

Public pages and SEO improvements: Blog, Insights, video, and usecase pages received updates to multilingual access, sitemap behavior, and indexing rules. This reduces empty pages, redirected pages, and incorrect language pages appearing in search results.

Fixed inaccurate, empty, or mixed-language results when filtering apps by language in App World.

Fixed cases where Traditional Chinese content could be incorrectly grouped under Simplified Chinese results.

Fixed unstable audio and video deliverable card display, including cases where video thumbnails did not appear.

Fixed first-preview failures, media file path issues, and incorrect download prompts for generated files.

Fixed duplicate uploads, interrupted uploads, folder drag-and-drop issues, and flickering upload hints.

Fixed cases where files could still be dragged into chat during manual task execution, and cases where the file tree did not refresh after upload.

Fixed Publish issues related to status updates, domain actions, paused-state hints, and Production Keys button states.

Fixed layout issues in narrow admin views and sidebar hover states.

Improved privacy protection on the password reset page to reduce the risk of sensitive link information being exposed through third-party pages.

Improved Git repository sync stability to reduce failures when fetching the latest code changes.

Mobile app generation: Atoms now supports creating mobile app projects, expanding from web apps and websites into mobile app experiences. The new flow supports mobile project generation, preview, and build preparation.

Mobile preview and QR code access: Mobile app projects now support preview links and QR code access, making it easier to test an app on a mobile device. Loading and readiness states have also been improved during preview preparation.

Android build support: Android builds can now be triggered for mobile app projects. Build status can be checked during the process, and the generated build package is available once ready.

Improved Publish flow: The Publish experience has been redesigned across first-time Publish, published project view, update flow, success modal, app status switching, and Unpublish entry. It is now easier to understand whether an app is live, copy the published link, visit the live app, and manage domains.

Cloud & AI Balance auto top-up: Cloud & AI now supports auto top-up configuration, including payment method setup and monthly limits to help avoid interruptions when Cloud & AI Balance runs low.

More stable preview experience: App preview loading, refresh, and recovery behavior has been improved to reduce long loading states, unavailable previews after idle time, and repeated waiting before preview is ready.

Clearer domain management: The domain experience in Publish has been refined. Default subdomains are easier to reuse, custom subdomain editing provides clearer validation feedback, and multiple domains are displayed in a more organized way.

Better mobile app creation guidance: Mobile app generation now provides clearer guidance around supported project types and templates, helping users create the right kind of mobile project with fewer confusing steps.

Improved chat input and file preview: Drag-and-drop file upload is easier to use with a larger available drop area. Text file previews have also been adjusted so file content is easier to read inside chat.

Homepage and public page updates: Mobile performance on the Atoms homepage has been improved. Homepage content was refreshed with updates related to Ads Specialist. Public app pages, Discover pages, template pages, and comparison pages were also optimized for clearer presentation and better search visibility.

SEO Agent and multilingual content support: SEO-related workflows now have additional support for translated content, helping multilingual public content stay more consistent across supported languages.

Improved Theme and UI controls: Theme selection and shared UI components such as Select and Dropdown received visual refinements for a cleaner, more consistent interface.

Google profile avatar support: New users who sign in with Google can now have their Google profile avatar filled in automatically. Manually changed avatars remain unchanged.

Fixed issues where mobile app projects were not always recognized correctly during early creation.

Fixed mobile preview issues, including unstable preview links, expired preview sessions, long loading states, and blank preview screens.

Fixed Android build issues related to build status updates, build recovery, and build package download behavior.

Fixed preview access issues that could cause blocked access pages, repeated redirects, or unclear error states.

Fixed Publish flow issues, including modal closing behavior, published state updates, success page navigation, and production key display.

Fixed UI issues affecting the chat input area, upgrade modal behavior, payment method display, auto top-up defaults, image previews, and text file previews.

Improved password reset link protection to reduce the risk of sensitive link information being exposed through third-party pages.

Fixed display issues on public pages, resource lists, and SEO-related pages.

Added readable AI-generated URL slugs for public pages, improving link clarity and shareability.

Added public tag display for shared chats, making published content easier to understand and browse.

Added translation support for AI SEO content, improving multilingual content workflows.

Added dark mode preview thumbnails for themes, so previews better match the selected appearance.

Added profile image syncing during Google sign-in, making account setup smoother.

Added language fallback for video content, so English results can be shown when the selected language is unavailable.

Added protected preview access, including dedicated authentication flows for secure preview pages integrated with the app viewer.

Added preview access blocking screens with clearer reasons and multilingual guidance when access is restricted.

Added "AI Code Review" to support development and quality-check workflows.

Added "Cloud AI" auto-recharge support with related configuration options.

Added updated homepage content, visuals, and a new "Ads Specialist" card.

Added public SEO-friendly AppWorld routes for "Discover", "Templates", and app detail pages.

Added scheduled "GitHub Stars" refreshes so displayed counts stay more current.

Fixed an issue where users could still receive updates after stopping generation.

Fixed cases where failed builds could leave the interface stuck in a "building" state.

Fixed public chat tag, visit log, and user lookup display issues.

Fixed Google Ads keyword validation compatibility issues.

Fixed text display in JSON responses to improve readability.

Fixed template configuration handling so non-standard settings are less likely to interrupt normal use.

Fixed preview and publishing flows so certain preview wake-up and publishing scenarios on the Pro plan can continue even after usage credits are depleted.

Fixed App Viewer preview state handling to reduce failed previews and inconsistent preview status.

Fixed preview tabs that did not consistently follow the authentication flow.

Fixed preview authentication routing and legacy route compatibility to improve protected preview success rates.

Improved proxy and route forwarding compatibility for supported scenarios.

Improved AI SEO retry behavior and compatibility with older data.

Improved presentation cover screenshot selection and configuration loading for more reliable cover generation.

Improved AppWorld Discover browsing experience for finding recent public content.

Improved the protected preview access flow, making secure preview links more reliable across different environments.

Added configuration validation for JSON and YAML to reduce setup errors.

Updated underlying database support for new fields and related features.

Agent collaboration

Metrics, logging, and observability

Workspace and development tools

Long-form content and document handling

Storage resource management

Frontend and product experience

AI skills and multimodal workflows

Added an in-app notification center: users can now view release updates, check unread indicators, open detail modals, and mark all as read directly from the Header, with read state synced across devices.

Revamped the AI Capability Library: browsing and search experience is now significantly improved.

Added image preview and document analysis capabilities to the editor: users can now view and interpret files directly during content creation and processing.

Enhanced interactions for the AppWorld sidebar and project cards, delivering a smoother experience when browsing, switching, and managing projects.

Fixed wallet refund status display: refund information now renders more accurately.

Fixed multiple notification issues, including unread badge behavior, CTA dismiss logic, missing fields, and panel styling/positioning: message display is now more stable.

Fixed an issue where notification data could be stale each time the notification panel was opened: content now refreshes as expected.

Fixed incorrect changelog URLs.

Fixed a routing issue with shared links: public shares now correctly redirect to the shared page.

Fixed cover image and layout issues in the share modal affecting DR display and Free Plan users.

Fixed a bug where the Overview status dropdown failed to appear after the initial publish.

Resolved an issue where the "unpublished" status was not synchronizing properly across publish views.

Fixed a glitch where the page title would incorrectly persist as the app name after returning to the homepage from the app page.

Resolved an issue preventing horizontal scrolling for tables in the chat interface, improving readability for wide tables.

Fixed an iframe authentication passthrough issue in the mobile AppViewer, ensuring stable access to related pages.

Fixed a display issue with the help icon in the mobile Remix modal.

Fixed an issue where the prompt warning monthly users about non-rolling credits upon downgrading was not prominent enough.

Fixed a layout overflow issue with onboarding experience in the Spanish locale.

Fixed an unresponsive click handling issue on the database sync button.

Fixed an issue where the homepage still displayed examples under certain DR modes.

Fixed an issue where the logout status was not synchronized across other Atoms pages within the same browser.

Resolved an authentication recovery issue, significantly reducing the occurrence of abnormal login states.

Fixed various stability issues related to the editor, settings toggling, app launching, and analytics tracking.

Optimized the AppWorld sidebar structure, animations, and collapsing logic to support smarter auto-collapsing on desktop and better mobile adaptation.

Improved sidebar analytics tracking, tag interactions, list responsiveness, and project cover displays for a more intuitive browsing experience.

Implemented state persistence for the sidebar in non-chat scenarios, retaining the user's preferred collapsed/expanded state upon returning to the page.

Standardized the width and visibility settings of the share modal, streamlining the sharing workflow.

Enhanced the display logic for sharing and project cover adaptations, improving visual consistency between shared pages and project cards.

Optimized notification center panel positioning to anchor directly to its trigger button, and added unread state to Hero cards for a more unified interaction pattern.

Improved notification center styling on mobile and in empty states: reading and interacting with notifications now feels more intuitive.

Added a skeleton loading screen to the chat list: loading feedback is now more visible and informative.

Added a Remix loading state indicator after forking: the processing status is now more clearly communicated to users.

Updated documentation and configuration references for in-app notifications.

Updated Test ID injection and CI pipeline configuration to support more stable automated testing.

Introduced template path validation for Atoms Cloud: warnings are now logged when a template path is missing, enabling faster diagnosis of configuration issues.

Added a clear command to the template Redis management script for easier cleanup of template-related cache data.

Introduced the sentry_filtered_engineio_invalid_session_total metric to track and monitor filtered invalid session errors.

Fixed root path handling in the Atoms thinking template, improving template loading stability.

Addressed "Too many requests" errors under high concurrency, enhancing request handling stability.

Fixed an issue in the frontend notification flow after the version release.

Launched Ads Agent：

Expanded AI capabilities with support for video, audio, text-to-speech, and speech-to-text workflows.

Added PDF analysis tools, plus new Markdown-to-PDF conversion and chart rendering capabilities.

Improved chat theme switching by notifying the frontend of the current theme in real time via WebSocket.

Added locale-aware support for video documents and tags, enabling language-specific filtering and localized tag names.

Fixed an issue where certain configuration/version lookup failures could leave chat tasks stuck and block future messages in the same chat.

Fixed GitHub remote-only branch switching issues to improve branch handling reliability.

Improved image validation for local SVG and raster images, with better error handling and logging.

Theme: Customizable themes and templates for personalized interface styling.

Video i18n Support: Video content now supports multiple languages.

Cloud & AI Pricing Plan - Phase 2: Enhanced pricing plans with more flexible options.

Global Tooltips Style Update: Unified tooltip component styles for consistent interactions.

Affiliate Program Update: Affiliate commission rate adjusted to 10%. All affiliate-related copy updated across the platform.

Added voice input support, including speech-to-text in message inputs on the home and chat pages.

Expanded language support with Traditional Chinese (zh-TW) and Swedish (sv) across frontend and backend.

Added homepage CTA experiments with multilingual template suggestions that can be inserted directly into the prompt box.

Added an Audience & Analytics section entry with navigation into the Growth experience.

Added an expandable/collapsible Atoms Cloud sidebar for backend projects.

Added route navigation dropdown support in App Viewer so users can quickly switch between available app routes.

Added backend support for Gemini text-to-image, and set gemini-2.5-flash-image as the default image generation model.

Added GPT-5.4 model support and related localized labels.

Improved multilingual CTA content with updated translations for English, Spanish, Turkish, and additional supported languages.

Improved Growth setup UX for GA4 and GSC with clearer guidance, privacy messaging, publish hints, blocked-popup fallback flows, and better no-data messaging.

Improved domain cards to show dynamic status labels such as Live and Paused.

Added a new Magic Link sign-up flow with email verification, including email check, send, verify, and resend capabilities for smoother registration.

Launched the new Overview panel after publish, with improved post-publish navigation and state handling.

Added version restore and preview controls directly in the message/version list for faster iteration workflows.

Added image attachment support in chat, allowing uploaded images to be passed through the chat flow more reliably.

Introduced Cloud & AI Wallet / Balance pages and top-up flows, including transaction history, usage breakdown, and balance display across desktop and mobile.

Added Growth block capabilities with deeper GA4 and Google Search Console (GSC) integration, including property/site connection, verification, reporting, and onboarding flows.

Added Claude 4.6 models and updated the default recommended/default model configuration.

Improved chat input responsiveness and first-screen performance with lazy loading, deferred heavy modules, and optimizations around hydration and editor initialization.

Improved wallet UI layout across desktop and mobile, including clearer balances, upgraded tooltip content, better spacing, and more polished tables/cards.

Improved Growth block user feedback, prompts, and authorization states to make GA4/GSC setup easier to understand.

Improved support for custom domains by prioritizing preferred/custom domains in more scenarios.

Added version restore for projects, including restore actions, restore progress states, completion messaging, and rollback protection for failed restores.

Added preview version switching so you can switch preview environments between versions more directly.

Introduced wallet payment support, including balance, usage, recharge order access, and instant payment creation.

Added custom domain management enhancements, including domain purchase/connect flows, batch unbind, improved primary domain handling, and better custom-domain support across publish flows.

Added support for 10 new languages across backend and frontend: Arabic, Dutch, French, German, Indonesian, Italian, Brazilian Portuguese, Russian, Turkish, and Vietnamese.

Added a new user profile page in the frontend.

Added mobile file preview improvements for chat blocks, DR content, and action editor workflows.

Added homepage, workspace, and landing page upgrades, including new homepage modules, responsive layouts, and improved content presentation.

Added analytics events for key user actions, including version creation/failure, app viewer readiness, agent mentions, secret flows, and more.

Added version rating feedback in chat, including thumbs up/down and structured feedback options.

Added SEO Specialist Sarah and expanded SEO-related project support.

Improved version restore reliability with locking, stronger validation, better error messages, safer rollback behavior, and long-running operation handling.

Improved chat performance by reducing redundant backend refreshes, caching tab content, and optimizing message scroll/positioning behavior.

Improved first-screen and bundle performance with more lazy loading, better chunking, deferred initialization, and LCP-focused optimizations.

Improved i18n refresh strategy on both frontend and backend to reduce backend pressure and avoid synchronized refresh spikes.

Improved workspace and editor experience by simplifying component structure and making file/task interactions more consistent.

Introduced custom domain support for apps, including domain binding, DNS/SSL checks, primary domain management, subdomain support, and related user tooling.

Added backend integrations for app configuration and secrets management, including improved environment variable syncing for deployed apps.

Added Stripe connection guidance and improved Stripe/Supabase integration flows for app setup.

Added AI capability features in the frontend, including model library, usage overview, model tags in plans/tasks, and richer model metadata.

Introduced auto model-selection experiments and expanded model options, including new Gemini, DeepSeek, GLM, and image-capable model entries.

Added a MetaGPT landing page and a new Atoms landing/branding experience.

Added support for larger Max plan storage, with Max plan capacity increased from 40 GB to 100 GB.

Added support for bucket limits in App Storage, including a maximum of 10 buckets per user.

Improved security around uploads, route handling, and rendered content, including stronger filename sanitization and safer HTML handling.

Improved storage and quota handling across plans, including clearer quota enforcement and larger Max-tier allocations.

Improved AI model presentation and organization with richer labels, descriptions, icons, and categorization across languages.

Improved landing page, pricing, and header/footer experiences.

Human-in-the-Loop

Human-in-the-Loop is a new review step that ensures Atoms Agents fully understand your intent. It presents a clear to-do list you can edit by typing #. After you approve it, the agents execute the plan with greater accuracy.

Power Up with Deepseek 3.2 Exp

The DeepSeek 3.2 Exp model is now available. Enjoy faster reasoning, stronger execution, and improved reliability across your projects.

New Edit Mode in the Editor

A dedicated Edit Mode is now available in the Editor, giving you finer control and a smoother experience when refining content.

Prototype Shortcut

Prototype is now accessible directly from the main page for faster iteration.

AI Feedback Assistant & Help Center Link

Using the Feedback button (as shown in the picture below) on any message now opens a guided assistant to help you resolve issues. Additionally, a direct link to the Help Center is now available in your profile menu and Settings.

Enhanced Slides: Improved visual quality and layout for all generated slides.

Faster Page Rendering: Wiki and Video pages now load noticeably faster.

Quick Sharing: Deep Research articles now auto-generate clearer, more descriptive share titles.

Platform Stability: Resolved multiple known issues to deliver a smoother, more reliable experience.

AI Image Generation (Nano Banana Model)

Added support for automatic, context-aware image generation. The Nano Banana model enables Alex (The Engineer Agent) to produce consistent, high-quality visuals that match website content and design style.

Introducing How-to Guides (Creator Playbook)

The new How-to Guides page provides step-by-step tutorials on building various projects with Atoms, such as high-converting SaaS landing pages, calendar & scheduling projects, and an English learning platform.

Better Downloads: Resolved garbled text in Deep Report downloads and enhanced overall download reliability.

Clearer Credit Usage: Redesigned the free credit usage bar for better clarity, so you can easily track your monthly credits.

Smoother UI/UX: Improved key interactions, including Deep Research report downloads, in-chat message sending, and block display logic.

Platform Stability: Fixed multiple known bugs to enhance overall performance and reliability.

Introducing the Video Center

In Video Center, users can find official tutorials, in-depth guides, and practical case studies. It helps you learn more about Atoms' powerful features and quickly start building.

Discover the App World Showcase

We have added a Showcase tab in App World. It helps users to explore the potential of Atoms with a selected group of high-quality projects.

Enhanced Account Security

We've strengthened our password requirements to include special characters.

Instant Connection Alerts

If the Supabase connection is disabled, you'll now receive a clear, instant notification during a chat.

Smoother UI/UX: Enhanced expand and collapse behavior for the "Task for human" input box. Updated visual indicators for files that can't be previewed.

Improved Security Logic: Added clearer expiration details and retry limits to email verification and password reset links to prevent misuse.

Clearer Billing: Clarified billing and deduction logic for users upgrading from an annual plan to a higher-tier monthly plan.

Platform Stability: Updated backend logic for the Affiliate Program and fixed multiple bugs to improve overall platform performance.

Annual Subscription Plan

We've introduced an annual subscription option to provide users with greater cost efficiency for long-term projects. When purchasing the first-tier credits in the Pro or Max plan, you'll receive a 21% discount. For all other tiers, the discount rate is 18%.

For details about pricing, billing, and credit allocation, refer to the Atoms Annual Payment Plan.

Brand New Use Cases Page

We've redesigned our use cases page to better communicate our mission of bringing ideas to life with AI Agents. The new layout delivers a cleaner look, clearer messaging, and a more intuitive start for new users.

Language Switching

We've added four official languages, including:

Users can switch languages from the top-right menu.

Replay

Replay in App World — You can now watch the full step-by-step creation process of any app directly in App World. The new Replay feature reveals how complex projects are built from a single prompt.

Explorer Program Launched

Join the Atoms Explorer Program to gain early access to major beta versions, verified identity status, monthly rewards, and official exposure opportunities. Explorers can contribute by engaging with the community, sharing feedback, and promoting Atoms across platforms. Apply now to shape the future of AI collaboration.

Affiliate Program Launched

You can now earn commissions by referring new users to Atoms: 30% commission on each referred user's first six payments + 10 credits for your friend.

For more details, see Affiliate Terms of Service.

Default Engineer Mode

Workspaces now default to Engineer Mode for a more powerful initial experience.

UI/UX Improvements

Enhanced wording for Supabase connection prompts and improved visual effects for slides.

Bug Fixes

Resolved multiple known issues, significantly improving platform stability and performance.

Fully refreshed product design.

Simplified pricing plans: Free, Pro, and Max. Pro and Max can be paired with different credit tiers.

Launched a new AI agent, Iris, the Deep Researcher, supporting in-depth research scenarios.

Introduced BON (Race Mode).

Added semantic Actions.

Rebuilt the PPT creation flow with improved prompts and outputs.

Released new models: GPT-5, Gemini 2.5 Pro, Qwen3, and DeepSeek 3.1.

Updated sidebar layout and added "star" for chat lists.

Publish settings are now integrated with Domain in the Settings panel.

Added support for connecting Supabase projects directly from the homepage.

Paid users can now set default chat permissions (e.g., default private) in Settings.

Improved Remix display format.

Optimized model list presentation.

Enhanced quick-access interactions.

Fixed several known bugs.

Instant Answers, Zero Wait: For simple Q&A, get replies instantly without the agent environment spin-up.

Introducing Engineer & Team Modes: A game-changer for your workflow and credits! Use Engineer Mode (just Alex the Engineer) for focused dev tasks to boost speed and save costs.

Supercharged Sharing: New chats are public to the App World by default, plus one-click social sharing and a new Export function for your files.

Supabase Edge Functions: Pro users can now write custom logic, handle webhooks, and more.

Smarter Help Center with AI: Our revamped Help Center now has AI-powered Q&A.

Automatic Terminal Error Detection: Spots and helps fix tricky errors for you

Customize Your Profile: You can now change your avatar and username.

Model Update: We've officially sunsetted the claude-sonnet-3.5 model and updated the claude-4-sonnet model.

Blazing-Fast Dev Experience: We've slashed the time from prompt to live preview and made deployment more flexible.

Cleaner, Smarter UI: The interface is now more streamlined and transparent during agent thinking.

Rock-Solid Stability: We’ve fixed multiple bugs for a more stable and reliable experience.

Enhanced Human Task Interaction: The input box now serves as the central hub for all tasks. Each step keeps a single focus point for a clearer workflow. All task entry points are consolidated in the input box for better usability. Agent task types are dynamically analyzed to optimize interactions.

Mobile Support:Complete end-to-end experience on mobile browsers (register → login → chat → deploy → share).

Promotional Plan Redemption: Redeem special plan packages using codes from official Atoms events.

Conversation Improvements: Added "scroll to latest" shortcut for better message navigation.

Slidev (Presentation) Enhancement: PDF export support for presentations.

Storage Management: Improved interaction when agent storage is full, with quick access to cleanup options.

UI Enhancements: Added Exchange explanation on Plan page showing credit conversion formulas; Toggle option for preview/deployed page corner icons.

Bug Fixes: Resolved various known issues for improved stability.

Email Notifications: Subscription cancellation alerts; 70% credit usage warnings with usage optimization tips; 3-day expiration reminders with remaining credit info.

One-Click Google Auth: PC users with Google accounts can now authorize with a single click.

Storage Optimization: System now supports more users with improved efficiency.

App World Enhancements: New category tags for quick App filtering; Template gallery with curated examples you can remix; Create new apps directly from these templates.

Enhanced Security: Improved chat share links with access tokens to prevent unauthorized access.

UI Improvements

Terminal Enhancements: Extended no-output timeout to 5 minutes for large dependency downloads.

Bug Fixes

Free Remix: Updated remix logic - remixing is now completely free!

Streamlined Payment Flow: Payment method selection now comes before the Stripe payment page.

App World Enhancements: Added like/upvote functionality; Added credit cost display on App cards; Updated default placeholder images for shared Apps.

UI Improvements: Updated names for some homepage shortcut cases; Improved mobile responsiveness for the homepage; Updated prompts for conversations exceeding 5 rounds.

Navigation Improvements: Added 404 redirects to the homepage for non-existent URLs; Added webpage titles for chat, share, and App World pages (searchable in the address bar).

Fixed various Remix bugs.

Improved App image loading speed in App World.

Fixed business card bug in quick access shortcuts.

Optimized web dependency management logic - develop more projects within the existing storage.

Fixed editor bug where file name changes and deletions failed to reset state

Improved shared version handling - redirects to pinned or latest version when specified version doesn't exist.

Optimized runtime update handling - chat messages now directly update the runtime state.

Improved loading speed for homepage and chat pages.

Fixed queue display error.

Fixed editor diff bug.

Improved homepage layout and chat bottom shortcuts.

Increased message limit for Free Plan users from 3 to 5 messages per chat.

Added "Continue" or "Remix" options after conversation interruptions.

Added countdown timer for the "Ask Human" feature.

Repositioned Remix button for better visibility.

Enhanced "Ask Human" functionality - automatically clicks Reply and pre-quotes the agent's message in the input field.

Enhanced source chat navigation after remix - your own chats open in editable mode, and others' chats open in read-only mode.

Simplified Share functionality for better user experience.

Added guidance on the subscription page: read App World and Help Center for Atoms usage tips.

Fixed memory issues with Remix.

Improved chat recovery logic and payment-related functions.

Fixed David's terminal run functionality.

Resolved template code reading errors.

Optimized page handling for excessive versions.

Fixed version screenshot font issues.

Fixed 404 content display when sharing non-existent files.

Enhanced Remix memory processing.

Improved payment pages and logic.

Fixed occasional token limit issues.

Made the Deploy button more prominent.

System Expansion: Enhanced server capacity and concurrency for more reliable user experience.

Complex Requirements Strategy: Introduced a new feasibility assessment logic for new projects, helping users gauge the viability of proposed ideas.

Token Optimization: After further testing in multiple incremental development scenarios, we have achieved an average reduction of approximately 56% in token consumption.

Bug Fixes & Optimizations: