What’s New
- Scheduled batches: a schedule can re-read a spreadsheet on every tick and fan out into a batch run, created straight from the Batches tab, with its own concurrency cap per schedule.
- Queued executions: scheduled runs appear as queued executions before they start, and execution timelines are anchored to when the run actually began.
- Custom skills for Astro: upload your organization’s own skills and invoke them with a slash picker in the chat composer.
- Live environments as a first-class API: boot browser environments without an execution, connect over CDP, and run executions against an already-live environment.
- Structured answers: a message can ask Astro for a structured, schema-validated result.
- Argument sources: pin exactly where each script argument comes from in the builder, with the resolution shown in the execution player.
- Rotate your own proxy gateway credentials from the platform.
- Astro chats use the full 1M-token context window.
- Astro shows what a running subagent is doing in its card header.
- Batch column mapping only requires columns for required inputs, not every declared one.
- Overview batches filter by start date and remember your grouping preference.
- The builder flags workflow inputs that no prompt references.
- Fixed healthy long-running executions being cancelled as “Stopped due to inactivity”.
- TOTP codes generate correctly in Astro live environments, and 2FA secrets can be filled from a QR code.
- Fixed a stopped Astro message reappearing and corrupting new input.
- Cancellation no longer overrides an execution that has already finished.
What’s New
- Asteroid Integrate: the agent catalog launched with Asteroid Integrate — clone a pre-built template, add credentials in one step, and start with a guided Astro kickoff.
- Astro runs on the latest frontier model.
- Download files directly from Astro chats.
- Insight Q&A: insights can pose a question, and you can answer it right from the insight dialog or chat widget.
- Run-on-enable schedules: optionally trigger a run immediately when a schedule is switched on.
- Edit agent profiles from an Astro widget, and let Astro open the portal credentials dialog for you.
- Much faster Astro turns.
- Computer-use reliability: full keyboard vocabulary, key repeat, and action failures returned as proper errors.
- Invoice history on the billing page, plus in-app top-ups.
- Insights link to their agent and open chats in agent context.
- Clear warnings as credit runs low.
- Large file previews no longer freeze the file explorer.
- Astro tool calls are visible while a turn is running and pair correctly with their outputs.
- Saving a same-name credential replaces it instead of duplicating.
- Live environments no longer blocked by unrelated billing checks.
What’s New
- Background subagents in Astro: subagents run in the background by default, each with its own card — docked while running, settled into the thread when done.
- Deploy page: a state-derived go-live checklist, API key dialog, and multi-language quick-start snippets.
- Agent profiles as a filterable table with name search.
- In-chat execution viewer when using Asteroid through MCP connectors.
- The latest frontier model is available on the platform.
- Dedicated hand tool for canvas navigation in the builder.
- Decluttered execution activity panel and table toolbars.
- Model picker grouped by provider.
- Filter executions by trigger source.
- Insights support collapsible markdown for long bodies.
- Fixed refused agent renames reporting “Saved” — name validation issues now surface clearly.
- LLM usage is reported even when an execution is cancelled mid-node.
What’s New
- Profile pools in batches: batch runs draw agent profiles from a pool, so parallel executions each get their own browser profile.
- Schedules and Batches tabs on the Overview page.
- Astro insights: Astro analyses your executions and surfaces insights on the overview page, with statuses you can update and a “Discuss with Astro” jump-off.
- Agent-scoped memory: Astro remembers context about an agent across conversations.
- Publish safety: a warning before publishing schema-breaking agent versions, and itemised input-schema diffs in version compare.
- Ask Astro to filter executions by workflow version.
- Rename Astro chats inline from the conversation list.
- Agent names are unique per organization, with automatic suffixing on create.
- Execution summaries say “errored” instead of “failed” for infrastructure errors.
- The Run dialog prefills booleans from your previous run and never clobbers edits you’ve made.
- The Files view stays fresh after Astro writes scripts.
- Fixed queued Astro messages being dropped at the end of a turn.
- A lost browser session now shows a friendly error instead of a raw stack trace.
What’s New
- Customize with Astro: fork a catalog template straight into an Astro chat seeded with the agent.
- Drag-and-drop file upload in Astro chat.
- @Node references: mention other nodes in instructions with autocomplete.
- Industry-aware onboarding: the signup wizard tailors your starting experience to your industry.
- Rename agents via the API and MCP server.
- New agents start with a seeded start node instead of a blank canvas.
- Astro’s reported context-window usage is now accurate.
- Astro-written browser scripts fail fast on bad selectors instead of hanging on long timeouts.
- Clicking a script now opens that script, not a random file.
- The files modal remembers your selected file across close and reopen.
- Numeric-string inputs are preserved verbatim instead of collapsing into exponential notation.
- Browser downloads without an extension get the correct file type.
- Omitted optional inputs no longer fail a run with an opaque template error.
- Astro chat drafts persist across tab switches.
What’s New
- Live file updates: the builder’s Files view updates in real time as Astro edits files.
- File management: multi-select, bulk delete, folder delete, and rename in the Files tab.
- Sticky notes are part of the workflow’s file representation, with better interaction and resizing.
- Typed script args: scripts declare their arguments instead of relying on placeholder substitution.
- Filter executions by script failure.
- Cost visibility: per-execution cost and cost-over-time on the billing page.
- Redesigned Astro chat with cleaner message rendering; tool output details collapse by default.
- Astro conversations are organization-scoped, so one chat can work across multiple agents.
- Failed webhook deliveries are retried instead of dropped.
- Playback speed persists across recording navigation.
- Dead live environments no longer resurface in Astro’s browser tools.
What’s New
- Batch insights: detailed timing metrics, predicted end time for running batches, and explanatory tooltips on batch stats.
- Build Sessions: watch recordings of live build sessions in a dedicated tab.
- Per-transition output schemas: attach a custom schema to each handoff so downstream nodes receive exactly the shape they need.
- Start nodes: every workflow now begins from an explicit start node.
- Faster agent starts: lower cold-start latency.
- Filter executions by agent profile; the script-failures column is visible to everyone.
- Slack notifications include the execution result, batch notifications link to their executions, notification configs can be edited in place, and integrations can be renamed.
- The visual output schema builder supports complex nested schemas.
- Execution result and inputs sections collapse to free up debugging space.
- Batch uploads warn when a column targets an unpublished agent variable.
- Recording playback falls back to a durable stored copy, so replays keep working.
- Fixed the executions page crashing when a filter value contained a comma.
- Profile-pool exhaustion surfaces a clear error during execution instead of failing silently.
- Browser code snippets get a wall-clock cap so a stuck script can’t hang a run.
- Fixed OS and snapshot settings being reset by an Astro save.
What’s New
- Typed workflow inputs: define string, number, and boolean inputs with a schema so runs are validated before they start.
- Node capabilities: toggle browser code, Google Sheets, PDF handling, and user questions per node.
- Versioned agent files: files are versioned alongside agent versions, with diffs in version compare.
- Fix with Astro: jump from a script failure straight into an Astro session to repair it.
- Astro subagents: Astro dispatches a specialized execution analyzer to debug runs, shown as a card in chat.
- Astro runs on our most capable model by default for all users.
- Stopping Astro is instant and reliable, and queued messages are restored after a stop.
- Script failures are recorded on executions, with clearer node transitions on the recording timeline.
- Faster executions table via on-demand sync.
- Slack integration cards show the channel name instead of its ID.
- Shut down a live environment directly from the environment view.
- Fixed input and metadata variable expansion on the execution page.
- Fixed questions being hidden inside collapsed step groups.
- Batch metadata values are sent as raw strings instead of being mangled.
What’s New
- Astro inline questions: Astro asks structured multiple-choice questions in chat when it needs your input.
- Live environments: Boot, attach, and manage browser sessions from Astro without starting a full execution first.
- MCP agent creation: Create agents programmatically via the Asteroid MCP server.
- Model-aware prompts: Agent instructions now adapt per provider/model variant for better results across Anthropic, OpenAI, and Google models.
- Faster browser automation: Playwright tools reuse a single long-lived connection across steps.
- More reliable downloads: browser downloads capture consistently via a shared CDP connection.
- Astro chat management: Rename or delete conversations; queued messages show above the input while a turn is running.
- Batch import ordering: Spreadsheet batch runs preserve row order from your upload.
- Fixed dead MCP transports hanging executions instead of failing cleanly.
- Fixed Slack OAuth callback race when auth token was not yet available.
What’s New
- Astro action widgets: Run agents and publish drafts as new versions directly from Astro chat.
- CLI execution runs: Trigger agent runs from the Asteroid CLI and deep-link straight to the execution in the platform.
- Connect to environment: Reattach Astro to a running browser session mid-conversation and jump to the execution view.
- File attachments in Astro: Upload PDFs and Office documents for Astro to read during a session.
- Message during runs: Send Astro messages while an execution is in flight; messages queue and preempt cleanly between tool calls.
- Context window visibility: Astro shows live context-window usage so you know when a conversation is getting full.
- Conversation compaction: When Astro compacts long chats, the compaction event appears inline in the thread.
- Guided next steps: Astro proposes a concrete next step at the end of each turn.
What’s New
- Script filepath fast path: Attach a script file to an agent node for a dedicated scripted execution path without a full agent loop.
- Script with Astro: Shortcuts in the builder and Files panel to generate scripts with Astro, plus an editable Script section in the iris sidebar.
- Redesigned Create flow: New home for starting agents, including environment templates for common setups.
- Builder files view: Browse and manage workflow files directly inside the agent editor.
- Live environment test runs: Spin up browser sessions for debugging without a full billed execution.
- Browser code execution in Astro: Astro can run browser-side code with the same tooling as production agent-loop runs.
- Clearer handoffs: Handoff summaries and variables are tighter, making multi-step workflows more predictable.
- Agent profile clarity: Profile cards show stealth and proxy status more clearly.
- Unified email tools: Send-mail and get-mail capabilities are merged into a single email toggle on agent nodes.
- Fixed node renames breaking shared file paths across the workflow.
- Fixed live-view iframe stealing keyboard focus during automation.
What’s New
- Astro live browser: Start a live browser from Astro with auto-resume and jump straight to the active execution.
- Astro feedback: Thumbs up/down on assistant messages to flag helpful or unhelpful responses.
- Google Sheets in Astro: Read and write Google Sheets when a live browser is attached.
- Execution controls: Pause, cancel, and resume runs from Astro and the CLI.
- Collapsible browser tray: Playwright tool calls in Astro collapse into a tray instead of flooding the thread.
- Structured browser actions: Playwright steps render as structured browser-action events in activity logs.
- OS agent defaults: Linux snapshot is the default for OS agents; custom snapshot names are optional.
What’s New
- Platform design refresh: Redesigned overview, executions, and agents listing pages with a new design system and shared UI primitives.
- Astro full workspace: Astro operates against a full agent workspace with shared files synced for executions.
- Live browser control from Astro: Astro can drive an execution’s browser via Playwright tools.
- Computer Use viewport lock: Workflows with Computer Use enabled default to a locked 1280×800 viewport for consistent coordinate automation.
- Conversation compaction: Compaction events now appear in execution activity so long Astro chats are easier to audit.
- Astro productivity: TodoWrite progress appears as a sticky widget; you can start fresh New Astro conversations. Fixes
- Fixed Computer Use viewport settings not tracking form state in the graph editor.
- Fixed workflow save edge cases that could drop changes.
What’s New
- Legacy migration helper: Added an in-app migration banner and modal to make moving older agents into the current experience easier.
- Visual output schema builder: You can now build JSON output schemas from a structured UI instead of editing raw JSON only.
- More predictable long-running executions: Soft timeout controls are now available, so runs end more gracefully when they exceed expected duration.
- Better run transparency in Activity: Handoff arguments and script-variable substitution steps are now surfaced, making it easier to understand why an execution behaved a certain way.
- Fixed key run-flow UI issues in execution views, including missing upload access in the run modal and sticky headers not tracking the active node consistently.
- Fixed multiple edge-case input issues (including dropped first characters after click-and-type in batch CUA flows) to improve automation accuracy.
What’s New
- New Overview page: You can now see a high-level summary of agent and execution performance in one place.
- More powerful command palette: Quick actions and navigation are faster and easier to access.
- More stable long-running runs: timeout handling, provider fallback behavior, and execution pipeline routing were tightened to reduce stalled runs.
- Better instruction quality for form/data entry tasks: prompt guardrails were refined to reduce incorrect field handling during automation.
- Fixed memory file preview staleness and improved recording/execution status alignment for more trustworthy run monitoring.
What’s New
- Build from empty: You can now generate an agent starting from a blank state.
- Email inbox view: Execution mode now includes an inbox view for email-driven automations.
- Faster heavy runs: snapshot compression and larger snapshot support improved performance for complex sessions.
- Run modal is simpler and now remembers batch settings between runs.
- Re-runs link more clearly to previous executions, making comparisons easier.
- Prompt updates improved action batching and script execution guidance, which helps agents complete multi-step tasks with fewer retries.
What’s New
- Dashboard outcome cards now show totals for faster at-a-glance monitoring.
- More reliable high-volume automation: file-sync and download handling were hardened to better recover from rate limits and transient storage failures.
- Output result and activity visuals were refined for clearer execution feedback.
- Handoff and file-path prompt guidance was clarified so agents transfer work between phases more reliably in remote browser environments.
- Fixed empty script results not displaying correctly.
What’s New
- Unified file workspace: Memory and files are now combined into one file experience with richer previews.
- Better tab management: Added tab context menus and drag-and-drop tab reordering.
- Added TOTP QR code reader support for easier MFA setup in automations.
- Faster execution paths: optimized mode defaults and reduced unnecessary model calls improved throughput on simpler workflows.
- Playwright code and script-failure cards are clearer, making debugging easier.
- Pause actions feel more responsive with optimistic UI updates.
- Prompt updates improved cross-node data flow and script output conventions, making multi-step workflows more predictable.
What’s New
- Google Sheets import for batch runs: You can now launch bulk jobs directly from Sheets data.
- Added custom proxy gateway controls with better egress-IP visibility in profile setup.
- Better batch throughput controls: concurrent batch execution limits and per-agent defaults now make large runs more predictable.
- Batch execution settings are remembered per agent to reduce repeated setup work.
- Run modal prefill and execution results layout were cleaned up for faster review.
- Prompt behavior for selector transitions and learning/script modes was refined so agents finalize tasks more consistently.
- Fixed cancelled-message behavior and reliability issues that could cause confusing execution outcomes.
What’s New
- Command palette and quick search: Navigate and run common actions faster.
- Mermaid diagram viewer: Diagram content now renders directly in the app.
- Improved execution traceability: activity logs now show richer assistant/turn context so slow or failed runs are easier to diagnose.
- Activity logs now group turns more clearly and include assistant text messages for better traceability.
- Workflow version differences are easier to review.
- Fixed hanging and multi-tab execution edge cases, with matching prompt updates to reduce instruction drift during long tasks.
What’s New
- Shared files now support full in-app management, including creating, updating, and deleting files.
- New execution mode controls give you more flexibility over how runs are executed.
- File tooling expanded with a dedicated files tab and node-level file explorer.
- Faster startup for file-heavy runs: execution initialization and tool timeout behavior were improved for better stability.
- You can now export all files as a ZIP for easier sharing and archival.
- Prompt system updates introduced clearer execution-mode guidance and stronger save/script instructions, improving agent follow-through on complex runs.
- Reduced deterministic-mode failures by tightening fallback and script-format guidance in prompts.
What’s New
- Shared files across runs: You can now store and reuse files across executions from the new shared files area.
- Organization renaming: Organizations can now be renamed directly.
- More graph-building flexibility: You can now drag a transition onto empty canvas space to create and connect a new node in one step.
- Better run stability controls: Long-running executions now handle timeouts, cancellation, and budget limits more reliably.
- Clearer context-window failures: When context limits are exceeded in Astro, the UI now shows a clear error state with recovery flow.
What’s New
- Agent file manager: You can now browse agent files with a directory tree and manage files directly in the platform.
- Excel batch uploads: Batch runs now support
.xlsxand.xlsfiles in addition to CSV. - Save PDF tool: Agents can now save page content as PDFs and surface those files in the file manager.
- Larger file support: Execution-start file uploads now support significantly larger files (up to 200MB).
- More reliable recordings: Execution recordings now use in-house storage with more stable playback links.
- Fixed re-run flow so previous execution variables are prefilled correctly.
- Fixed workflow editing so agents with disconnected nodes can still be saved when appropriate.
What’s New
- Duplicate agent profiles across organizations: You can now copy an existing profile into another org instead of recreating it from scratch.
- Smarter batch setup: CSV columns can now auto-map to workflow input fields, making large batch runs faster to configure.
- Webhook targeting filters: You can now set metadata-based filters for webhook notifications so events route to the right destination more precisely.
- Better activity clarity: Transition activity now shows clearer node summaries, making execution timelines easier to understand.
- More accurate analytics dates: Stats now respect your browser timezone to prevent misleading daily grouping.
What’s New
- Agent profile pools: You can now group and manage profile pools, and use them directly from the run dialog.
- Batch executions: You can now launch and manage batch runs with CSV mapping tools from the platform.
- Rich instruction editing: Instruction fields now support rich markdown editing for easier prompt authoring.
- Better tab continuity: The app now remembers your last active tab and preserves search/filter state when navigating.
- Better profile configurability: Agent profiles now expose tracing and Tailscale proxy settings in the UI.
What’s New
- New agent layout: Redesigned UI with tab management for a cleaner, more organized agent building experience.
- Scheduled executions: Schedule agents to run at specific times with the new scheduling system.
- Captcha handling: Agents can now detect, pause and handle CAPTCHA challenges during automation.
- PDF viewer toggle: Enable or disable PDF viewing in agent profile settings.
- Slack approval buttons: Execution notifications in Slack now include View and Approve action buttons.
- Schedule toggle: Enable or disable scheduled executions without deleting them.
- Refreshed UI layout with improved navigation and visual hierarchy.
- Rescheduling support for cancelled scheduled executions.
- Optimized activity component re-renders with memoization.
- Better error handling for validation failures in agent profiles.
- Fixed non-retryable failures when LLM didn’t perform any action.
- Fixed laggy search filter and pagination in model overrides modal.
What’s New
- User profiles: First name and last name fields added to user accounts.
- Run from table: Execute agents directly from the agents table actions menu.
- Browser IP display: See the IP address used by the browser in execution environment details.
- JSON schema validation: Validate workflow data against JSON schemas.
- Enhanced proxy configuration options in agent profiles.
- Execution list now shows agent profile ID and inputs.
- Better agent workflow handling and state management.
- Improved model type definitions with enhanced language model support.
What’s New
- Execution environment API: New API endpoints for managing agent execution environments.
- Key-value filters: Filter executions by custom metadata key-value pairs.
- Temporary file uploads: Upload temporary files when running evaluations.
- Enhanced execution table with agent and human label filtering options.
- Agent actions menu provides quick access to common agent operations.
- Better accessibility with aria-labels throughout the UI.
- Streamlined UI component library with workspace package migration.
What’s New
- Recent execution outcomes: Agent stats now show the last 5 execution outcomes at a glance.
- Stop conversations: Pause or stop active Astro conversations.
- Graph diff visualization: See workflow changes visualized in the graph view.
- Output format validation: Validate output schemas with format constraints.
- Sandbox browser option: Choose between sandboxed and direct browser connections.
- Enhanced workflow publishing with better version handling.
- Improved Astro websocket reliability with hidden transient errors.
- Increased page size for agent profiles to 1000 for faster loading.
- Enhanced billing page usage tracking and visualization.
What’s New
- Asteroid MCP server Beta: New Model Context Protocol server for LLM agent interaction.
- Sandbox environments: Run agents in isolated sandbox environments.
- Rename agent tool: Astro can now automatically suggest and apply agent names.
- List executions tool: Query execution history with workflow version filtering directly from Astro.
- Continue on node: New transition option allows agents to stay on the current node and continue processing.
- Execution status updates: Update execution status programmatically via the SDK.
- Advanced model search with text highlighting for easier selection.
- Connection status indicator shows real-time Astro connection state.
- Enhanced copy-paste in graph editor filters transitions based on connected nodes.
- Resolved file download condition to check for browser availability.
What’s New
- New authentication system for improved security and enterprise SSO support.
- Increased token limits: Maximum tokens increased to 128,000 for more complex agent tasks.
- YAML file uploads: Upload YAML configuration files to your agents.
- Auto-accept workflow changes: Automatically accept Astro’s suggested workflow modifications.
- Auto-expanding chat input: Text area grows as you type for a better editing experience.
- Adblock enabled by default to prevent popup interference during browser automation.
- Renamed “dynamic data” to “inputs” for clearer terminology across the platform.
- Version history component replaces version selector for better workflow tracking.
- Responsive sidebar layout adapts to portrait and landscape modes.
- Enhanced credential management UI in agent profiles.
- Better scroll management in chat components.
- Resolved date range logic in average duration and outcomes charts.
- Fixed workflow state handling in operating context.
- Corrected agent workflows list invalidation on workflow commit.
What’s New
- Screenshot tool: New
browser_take_screenshottool for capturing page screenshots during automation. - Script evaluation: Execute JavaScript directly on web pages with the new script eval action.
- PDF viewer settings: Configure PDF viewing behavior in browser settings.
- Author tracking: Workflows now track who created and modified them.
- Workflow version display: Executions now show which workflow version was used.
- PDF URL validation prevents accidentally navigating to PDFs in URL nodes.
- Lightweight workflow reference listing for faster agent loading.
- Enhanced query context support in activity tracking.
- Removed deprecated execution workflow update endpoints for cleaner API.
- Better error handling for display button tool instructions.
- Fixed execution stats queries to properly join on workflow table.
- Prevented deleting draft versions that have active executions.
What’s New
- Browser live view: See real-time browser activity with the new live view URL.
- Create agent profiles from Astro: Build and configure agent profiles directly from the assistant.
- Workflow diff review: Visual overlay showing pending workflow changes before committing.
- Edit mode requests: Request edit access to workflows when viewing executions.
- Session from execution: Create new Astro sessions directly from execution mode.
- Character count with progress visualization when typing messages.
- Dynamic labels change based on your current operating context.
- Enhanced template agents with clearer login instructions.
- Improved outcomes distribution chart layout.
- Fixed form reset issues during auto-save in execution mode.
- Corrected proxy country code handling when creating agent profiles.
What’s New
- Astro AI assistant: New intelligent assistant panel with interactive demo prompts, welcome header, and capability chips to help you get started faster.
- Auto-layout for graphs: New nodes are automatically arranged in a clean layout when added to the workflow.
- Initial prompts: Set an initial prompt when creating new agents to jumpstart workflows.
- Version notifications: Get notified when new platform updates are available.
- File attachments in chat: Send files up to 24MB through the WebSocket connection.
- Conversation management: Update and rename conversations directly from the UI.
- Markdown support in chat messages for richer formatting.
- Copy-to-clipboard button for UUIDs with improved UI feedback.
- Workflow validation now returns multiple errors at once for faster debugging.
- Force edit mode: Continue editing agents even when executions are running.
- Auto-select most recent conversation when opening the chat panel.
- Better loading and error states in the execution panel.
- Fixed tab reconnection issues when switching browser tabs.
- Resolved flashing when changing query params on agent page.
- Fixed mention menu dismissing when clicking scrollbar.
- Prevented message submission when mention menu is closed.
What’s New
- Execution status counts: New API endpoint to get counts of executions by status.
- Publish workflow: Publish your staged workflow changes directly from the builder.
- Copy-paste for nodes: Copy and paste nodes and sticky notes in the graph editor.
- Script timeout: Set custom timeout values for script execution.
- Concurrent execution limits: Subscription tiers now include concurrent execution limits.
- Enhanced execution table with better data fetching and pagination experience.
- Centralized filter state management for cleaner execution filtering.
- Improved browser playback controls for landscape orientation.
- Better dialog sizing on small screens.
- Fixed current node handling in execution graph extraction.
- Resolved issues with expired subscription migrations.
- Fixed human labels dropdown placeholder text.
- Corrected execution stats dashboard click event handling.
What’s New
- Slack channel management: Select specific Slack channels for your integration notifications.
- Event notification filtering: Filter notifications by specific event fields and values.
- Webhook v2: Expanded execution events with standardized webhook format.
- Output schema validation: Support for regex pattern validation in output properties.
- Resizable panels: New resizable panel components for flexible layouts.
- Billing management: View and manage your subscription directly in the platform.
- Simplified webhook configuration UI with streamlined settings.
- Enter key now sends messages in chat input.
- Activity stream shows transition types when moving between nodes.
- Improved conversation selector with smooth scrolling and sorting.
- Better button sizing and styling consistency across the platform.
- Enhanced execution overlay with double-click to expand.
- Fixed WebSocket “close sent” errors during connection closure.
- Fixed notification mapper errors in v2 notifications.
What’s New
- Slack integration: Connect your Slack workspace to receive agent notifications directly in your channels.
- Documentation search: Agents can now query Asteroid documentation to help answer questions about the platform.
- Undo/redo support: Graph editor now supports undo/redo with keyboard shortcuts (Cmd/Ctrl+Z, Cmd/Ctrl+Shift+Z).
- Keyboard shortcuts modal: View all available keyboard shortcuts in the graph editor.
- Agent profile visibility: Executions table now shows which agent profile was used for each run.
- LLM call tracking: Activity stream now shows when agents are making AI model calls and for what purpose.
- Enhanced activity auto-scroll: Activity progress panel now auto-scrolls to follow agent actions in real-time.
- Streaming messages: Improved real-time streaming when sending messages to running agent executions.
- Better navigation tracking: Browser navigation actions now show timing and status in activity logs.
- Sidebar context: Sidebar items now show helpful subtitles for better navigation context.
- Improved duration charts: Average duration analytics now have better tooltips and layout.
- Fixed double scrolling issue on tables with pagination.
- Corrected line number display in scriptpad content.
- Resolved datetime formatting errors in certain timezones.
- Fixed streaming message handling in agent conversations.
What’s New
- Execution filtering: Filter runs by agent, status, and date range.
- Execution metadata: Add custom key–value metadata to runs for better organization and searchability.
- Version selection when running agents.
- New unified Stats page with full historical analytics.
- Auto-generated node descriptions for clearer, easier-to-understand workflows.
- Playwright scripts now surface browser console logs for easier debugging.
- More detailed workflow failure diagnostics, with line-level script errors.
- Execution statistics now include average-duration metrics and support filtering by agent version.
- More reliable selector transitions with built-in retry logic.
- Better page-state capture during rapid navigation.
- Resolved failures caused by LLM calls returning only reasoning content.
- Corrected file listing display issues.
- Fixed date/time formatting in activity logs.
What’s New
- Output Node Type: Define structured workflow outputs and custom outcomes beyond simple success/failure.
- Query Context Tool: AI Task nodes can agentically retrieve information from previous steps.
- Node-Level Context Management: More targeted, step-specific behavior control.
- get_datetime Tool: Retrieve current date/time in any timezone.
- freeze_script Option: Prevent unwanted script regeneration in Learn & Compile mode.
- Email tools:
send_mailandget_mail. - Sticky notes for annotating workflows.
- Upgraded AI model for Playwright script generation: higher reliability, better selectors, clearer flows.
- AI Task tools reorganized into capability categories.
- Improved workflow activity logs with richer details (API calls, file ops).
- Agents now signal more clearly when they’re blocked and require user assistance.
- Cookie handling during browser initialization.
- Transition failures in specific workflow patterns.
- Occasional browser disconnection issues.
- Workflow rendering issues affecting agent navigation.
- Better reasoning-mode alignment across model types.
- String-variable quoting issues in Playwright scripts.
- Error wrapping in API responses.
- Summarization performance improvements.
What’s New
- Agent Listing API: Paginated, sortable agent listings through the External API.
- Real-time Graph Updates: Live updates to the workflow graph as you edit.
- Learn & Compile Mode: Combines AI-driven decisions with cached Playwright scripts for stable automation.
- AI-optimized node descriptions for more readable workflows.
- Raised file upload limits: 20MB/file and 100MB total.
- Faster, more reliable real-time streaming with better concurrency handling.
- Optional proxy settings in agent profiles.
- Enhanced Playwright script logs with detailed execution output.
- More reliable WebSocket activity updates.
- More specific API error messages and validations.
- More detailed error handling for workflow-graph update failures.
- Execution cancellation reliability improvements.
- Empty proxy fields no longer cause errors.
- More stable long-running automation sessions.
- Playwright LLM variable migration stability improvements.
- TOTP secret generation bug fixes.
What’s New
- Added cookie management to agent profiles, allowing you to store and manage website cookies for your automation workflows
- Added new list_files and read_files tools for agents to work with context files during execution
- Added browser_fill_form action for simplified form completion
- Added support for JavaScript evaluation on web pages with the new browser_evaluate tool
- File uploads and downloads are now tracked in the activity stream, showing important metadata like filename, size, and type
- You can now use longer agent names up to 100 characters
- Special characters are now supported in agent names (previously limited to alphanumeric, #, -, _, and spaces)
- Enhanced file handling with better error messages and more consistent processing
- Browser form filling now shows field details in the activity log for better visibility
- Large model responses now automatically retry with increased token limits when needed
- Improved error handling and reliability for streaming connections
- File uploads for agent executions are more efficient and reliable
- Enhanced agent cancellation with more specific reasons (timeout, max steps, or user-requested)
- Improved reasoning display when the agent is thinking through complex tasks
- Enhanced WebSocket connection handling for more reliable real-time activity updates
- Workflow Flexibility: You can now have multiple end success and end failure nodes in your workflows.
- Better reliability for real-time updates during agent execution - the system now processes messages more efficiently and reliably, ensuring you get immediate updates about your agent’s activities
- Fixed duplicate activity messages that were incorrectly appearing in execution logs
- Fixed an issue where duplicate credential names could cause conflicts
- Fixed occasional connection errors during real-time activity streaming
- Fixed an issue where execution status was incorrectly displayed as “Starting” instead of “Running” when activities begin, providing more accurate status information in the interface
- Fixed issues with image handling in agent conversations
- Resolved a potential issue during execution cancellation that could prevent proper cancellation in certain cases
What’s New
- Real-time activity updates for agent executions with the new activity streaming endpoint
- You can now send messages to a running agent execution via a new API endpoint
- Enhanced activity tracking with filtering options to view execution activities in your preferred order
- Improved file upload capabilities in agents, allowing for more seamless handling of user-provided files within agent workflows.
- Enhanced browser file download features that enable agents to access and work with files downloaded during browsing sessions.
- You can now select Windows as the operating system for your agent profiles, allowing you to run browser sessions that emulate Windows instead of macOS
- Activity streams now show detailed step progress, node transitions, and agent actions
- Agent statistics now include average execution time metrics
- Enhanced error messages for troubleshooting agent issues
- Added comprehensive API documentation to make integration easier
- Introduced API versioning with a new v2 endpoint structure for better backwards compatibility
- Better file metadata handling with improved MIME type detection and extension processing for more accurate file identification.
- Streamlined file notifications for agents, making it clearer when new files are available for use.
- More robust file handling with improved validation, sanitization, and error handling for increased reliability.
- Enhanced file activity messaging.
- Fixed reliability issues with browser actions by improving error handling
- Resolved problems with file downloading
- Fixed an issue where expired subscriptions couldn’t be upgraded without contacting support