> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.rightbrain.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.rightbrain.ai/_mcp/server. # Changelog Product and API updates, published twice monthly. Every release is tagged: filter by product area or search the full archive to find changes relevant to your work. Entries describe changes at the time of release. Follow each entry's current documentation links for today's setup, API behavior and model availability. Subscribe with [RSS](/changelog.rss), [Atom](/changelog.atom), or [JSON Feed](/changelog.json). ## Evals and Run Operations > Replay file-backed evals, inspect agent run activity and costs, and use Azure OpenAI deployments. ## What's New ### File-Backed Task Evals Task evals can replay reference runs that used direct image or PDF inputs. Stored processed values are reused, and direct model-facing files are restored from Project storage for the candidate run. See [Evals](/docs/production/evals). ### Detailed Agent Run Operations Agent run views now combine total cost, status, failure reasons, phase timing, tool and skill activity, approval duration, actor identity, and the connection account used by each integration call. Agent lists also support server-side name and creator filters with grid and table layouts. ### Azure OpenAI and Claude Fable 5 Tasks can use supported Azure OpenAI deployments, and Claude Fable 5 is available for demanding reasoning and agentic workloads. ## Improvements * Leaving an agent page no longer cancels its live run; reloads warn before disconnecting an active stream * Deleting an integration preserves historical revision references and reports visible blocking dependencies * Approval resumes preserve the original run actor identity * Task fallback changes discard incompatible stale temperature settings * Agent phase timings remain monotonic and consistent ## Current documentation [Evals](/docs/production/evals) · [Observability](/docs/production/observability) · [Model governance](/docs/production/model-governance) · [Run agents with files](/docs/api/run-agents) ## Connections, Approvals, and Xero > Choose personal or shared connections, sample tool calls for human review, and trace the identity behind a run. ## What's New ### Personal and Shared Connections Supported integrations can now hold both a user-owned connection and a shared Project connection. Each Task or agent binding selects the invoking user's credentials or the Project default, and the integration catalog reports the scopes and policies each provider supports. See [Connections](/docs/concepts/connections). ### Sampled Human Review Approval-gated tools can send a configurable percentage of eligible calls for review while retaining 100% as the default. Approval requests can also include the agent's model-authored reason alongside the sanitized argument preview. See [Approvals](/docs/production/approvals). ### Xero Integration Xero is available as a Project-shared Connection for contact lookup, accounting reference data, contacts, invoices, repeating invoices, and manual journals. Mutation tools remain opt-in when tools are attached. ### Run Actor Identity Task and agent run records now identify whose authority caused a run, why that identity was trusted, and the platform surface through which execution entered. Nested tool calls preserve the parent authority. See [Observability and audit](/docs/production/observability). ## Improvements * Tasks receive their UTC run start time in model context for consistent relative-date interpretation * New model options include Claude Opus 5, Gemini 3.5 Flash-Lite, and Gemini 3.7 Flash * Connected Slack apps send a welcome message after installation * Empty-document processing returns a consistent response across supported strategies * Integration disconnects and approval workspace changes are more reliable ## Current documentation [Connections](/docs/concepts/connections) · [Approvals](/docs/production/approvals) · [Observability](/docs/production/observability) ## Model Governance and Evaluations > Control model availability, customize agent eval rubrics, and automate API access through named CLI environments. ## What's New ### Model Availability Controls Organization and Project administrators can exclude models by model ID, provider, or vendor. Organization rules flow into every Project, and safety checks prevent a policy from removing every active model. See [Model governance](/docs/production/model-governance). ### Custom Agent Eval Rubrics Agent eval runs can now use a custom objective and ordered rubric. The resolved policy is stored with the run, while evals without a custom policy continue to use functional equivalence. See [Evals](/docs/production/evals). ### Project-Wide Share Management A unified Shares view brings Task and agent shares into one searchable, filterable list. Share tags can be managed from the same Project-level workflow. ### CLI Access Tokens and Environments The Rightbrain CLI can return a refreshed access token with its deployment and Project context. JSON environment listings make authenticated API automation independent of the CLI's private credential-file format. See [Rightbrain CLI](/docs/api/cli). ## Improvements * Oversized agent tool responses are replaced with a bounded omission record before they enter model-visible history * Failed agent runs retain more context and report accurate total charged credits * MCP servers support safer deletion, reauthorization, and bulk tool registration * OpenAPI error contracts and request-body documentation now align with live API behavior * New model options include GPT 5.6 Sol, Terra, and Luna, plus Gemini 3.6 Flash * Agent chat validates file-size limits before starting a run ## Current documentation [Model governance](/docs/production/model-governance) · [Evals](/docs/production/evals) · [CLI](/docs/api/cli) · [Sharing and cloning](/docs/production/sharing) ## Approvals, Chaos Mode, and Audit Integrity > Review approvals, test recovery with Chaos Mode, attach integrations to tasks, and verify audit-log integrity. ## What's New ### Approvals in the Dashboard Human-in-the-loop approvals now have a home in the dashboard. A new Approvals tab surfaces every pending request across your agents, so a reviewer can see what a tool is about to do and approve or reject it. An approved API run resumes when the client calls the resume endpoint. The record captures who decided what, with recognized secrets redacted from its argument preview. See [Approvals](/docs/production/approvals). ### Chaos Mode Test how your agents recover from failure before it happens in production. Chaos Mode injects bounded, deterministic tool and model faults into a single run, so you can confirm that fallbacks and retries behave as expected. Each run records exactly which faults were applied for later inspection. See [Chaos testing](/docs/production/chaos-testing). ### Integrations on Tasks Integration tools can now attach directly to a Task, without wrapping it in an agent. A single task can call a connected service as part of its run, making lightweight automations simpler to build. ### Tamper-Evident Audit Logs Audit logs now carry cryptographic integrity. Entries are chained so the log can be verified as unaltered, giving you a defensible, tamper-evident record for compliance. See [Observability and audit](/docs/production/observability). ## Improvements * Task tools attached to an agent can follow the task's active revision, so improving a task rolls out to every agent that uses it. See [Versioning and revisions](/docs/production/revisions) * Richer Slack responses with formatted text, tables, facts, and sources, plus live progress while the agent works * Gemini context caching lowers the cost of runs that reuse the same context * Agent Observe adds server-side run-history filters and surfaces primary-model and integration failures with specific reasons * Tags can now carry a description and be updated in place > **Note** > > Chaos Mode pairs with fallback models: inject a provider outage and watch the run fail over to your backup model, with the fallback recorded in the run's telemetry. ## Current documentation [Approvals](/docs/production/approvals) · [Chaos testing](/docs/production/chaos-testing) · [Connections](/docs/concepts/connections) · [Observability](/docs/production/observability) ## Slack, Mistral, and File Attachments > Connect agents to Slack, use Mistral models, and inspect uploaded or generated files in agent runs. ## What's New ### Slack Integration Connect Slack as a Connection and let your agents work inside your workspace. Agents can list channels and post messages through your connected Slack app, and the dashboard shows each connection's authentication status with clear prompts when a reconnect or scope upgrade is needed. See [Connections](/docs/concepts/connections). ### Mistral Models Mistral's models are now available for your tasks and agents, widening the range of providers you can build on and fall back to. ### File Attachments in Agent Chat Upload files directly into an agent conversation and the agent can use them during the run. Uploaded files appear in the run's input on the Observe page, and files the agent generates download under their original filenames. ## Improvements * A project-wide approvals view lists pending approval requests across every agent in a project * Request Rightbrain support on a specific run, capturing the diagnostic context needed to investigate while keeping secrets redacted * Agents can load runtime files at the start of a run > **Note** > > Because Mistral models sit alongside every other provider, you can set one as a primary model or as a fallback. See [Fallbacks and reliability](/docs/production/fallbacks). ## Current documentation [Connections](/docs/concepts/connections) · [Model governance](/docs/production/model-governance) · [Run agents with files](/docs/api/run-agents) ## Approvals, Runtime Files, and Gmail Triggers > Pause tool calls for approval, pass files between tools, and start runs from Gmail or schedules. ## What's New ### Human-in-the-Loop Approvals Gate any agent tool call behind a human decision. Mark a tool as requiring approval and the run pauses when that tool is about to fire, so a person can approve or reject the action before it happens. This is built for tools with real-world side effects, like sending an email or updating a record. See [Approvals](/docs/production/approvals). ### Runtime Files Between Tools Tools within a single agent run can now pass files to one another. A tool that produces a file, such as an attachment saved from an incoming email, makes it available to a later tool that consumes it, so multi-step document workflows hold together from start to finish. ### Gmail Inbox Triggers Start an agent automatically when an email arrives. Connect a Gmail inbox as a trigger and incoming messages kick off a run, turning your agents into always-on inbox responders. See [Triggers and runs](/docs/concepts/triggers-and-runs). ### Scheduled Runs Tasks now have a Schedule tab for running them on a recurring schedule directly from the dashboard, with no external scheduler required. ## Improvements * Agent overview now shows a seven-day run summary and indicates which agents are shared with the project * A new Trigger column on run listings shows what started each run * Clickable resource links in skill instructions * Trigger event errors appear in a dedicated column with one-click copy * API keys now show their expiry date in the dashboard and via the API * Broader image support, including HEIF, with correct handling of image orientation > **Note** > > Approvals are configured on the agent revision, so every change to an approval policy is versioned. Rolling an agent back restores its previous policy alongside the rest of its wiring. ## Current documentation [Approvals](/docs/production/approvals) · [Run agents with files](/docs/api/run-agents) · [Triggers and runs](/docs/concepts/triggers-and-runs) ## Context Usage, Audit Log, and File Attachments > Inspect agent context usage, trace project changes in audit logs, and attach files to agent conversations. ## What's New ### Context Usage Breakdown See exactly what fills an agent's context window on every run. A new usage panel attributes input tokens across instructions, conversation history, tools, Skills, and integrations, and an expandable context chip highlights the breakdown at a glance. Usage is aggregated across the runs in a session. See [observability](/docs/production/observability) for details. ### Audit Log A new [audit log](/docs/production/observability) page records activity across your project, with filters by resource type and identifier so you can trace exactly what changed and when. ### File Attachments for Agents Drag and drop multiple files straight into an [agent run](/docs/api/run-agents), or use the new attachment button. Uploaded files are tracked with their source and appear inline against the message that introduced them, in both single runs and multi-turn sessions. ## Improvements * Paginated agent run history plus a single-run detail view * Visibility indicators on agent cards * More reliable eval judging, with model parameter defaults applied consistently * Smarter handling of uploaded files across an agent's tools, so each tool receives only the files it needs * Function names now appear in streaming events for clearer run traces * A memory compaction indicator in the context usage panel > **Note** > > The context usage breakdown makes it easy to spot what is driving token cost on a run. If a single integration or Skill dominates your input, you can see it directly and trim what the agent carries. ## Current documentation [Observability](/docs/production/observability) · [Memory and context](/docs/concepts/memory-and-context) · [Run agents with files](/docs/api/run-agents) ## Evals, Agent Sharing, and Memory Compaction > Evaluate task and agent revisions, share and clone agents, and compact conversation history within context limits. ## What's New ### Evals for Tasks and Agents Test changes before you ship them with [evals](/docs/production/evals). Replay real past runs against a candidate revision and let a judge model score each result as pass or fail, so you catch regressions before they reach production. Eval pages are now shared across both Tasks and agents. ### Agent Sharing and Cloning Share an agent with a public read-only link that shows its configuration without exposing credentials or run history, and let others clone it into their own project. Cloning is recursive and reports exactly what was copied, reused, or left for setup. Connections are copied as metadata only, so every project keeps control of its own credentials. ### Memory Compaction Keep long-running agent conversations within the model's context window using [memory compaction](/docs/concepts/memory-and-context). Agents can compact conversation history on a set cadence or automatically once a token threshold is reached, and compaction is billed and reported separately so you can see its cost. ### Agents-First Navigation Agents are now the landing page after sign-in and sit at the top of the sidebar. A new Connect tab brings Slack channels, schedules, and API keys together for wiring up how an agent runs. ## Improvements * Support for the Standard Webhooks signature format when verifying incoming events * New "created by me" filter on Tasks and revision and status filters on Logs * Removed team member seat limits from the invite flow * Added an OCR fallback so scanned and image-based PDFs are read more reliably * Agents now handle context window overflow gracefully instead of failing the run * Real Slack channel picker and a live next-run preview for scheduled agents > **Note** > > Evals turn a subjective "does this still work?" into a repeatable release gate. Point an eval at your recent production runs and require a minimum pass rate before promoting a new revision. ## Current documentation [Evals](/docs/production/evals) · [Sharing and cloning](/docs/production/sharing) · [Memory and context](/docs/concepts/memory-and-context) ## Skills, Connections, and Agent Versioning > Manage versioned skills and connections, select active agent revisions, and configure agent fallback models. ## What's New ### Skills Give your agents reusable, focused abilities with [Skills](/docs/concepts/skills). Browse ready-made Skills from the marketplace or build your own with instructions and reference files, all managed through a new create-and-detail interface. Skills are versioned, so you can iterate safely and pin the exact revision an agent uses. Skills can also declare the tools they depend on, and those dependencies are provisioned onto your agent automatically when the Skill is attached. ### Unified Connections [Connections](/docs/concepts/connections) brings integrations and MCP servers together in one place. Add native service connectors and Model Context Protocol servers, manage their authentication, and wire them into your agents from a single page. ### Agent Versioning Changes to an agent’s execution configuration now create a new [revision](/docs/production/revisions) instead of overwriting the live configuration. Pick the active revision from a dropdown in the configure panel, tag revisions for reference, and roll back at any time. In-progress runs keep using the revision they started on. ### Agent Fallback Models Choose a fallback model for your agents so a run can continue on a second model if the primary one fails. The fallback model name now appears in your run logs when it is used. ## Improvements * Google integrations gained richer tool metadata for more reliable results * Permission controls now extend to Skills, Connections, Collections, and agents * The `url_fetcher` input processor added a direct fetch mode * More reliable agent streaming, with the session identifier emitted as soon as a run starts * Skill files render as formatted Markdown and JSON in read-only views * Renamed the data view to Logs, with clearer OAuth error messages when adding a connection ## Current documentation [Skills](/docs/concepts/skills) · [Connections](/docs/concepts/connections) · [Revisions](/docs/production/revisions) · [Fallbacks](/docs/production/fallbacks) ## Integrations and Agent Experience > Connect Google Workspace tools, authenticate MCP servers with API keys, and inspect agent runs and audit logs. ## What's New ### Integrations Integrations are native, platform-managed connections to external services, starting with Google Workspace: Sheets, Docs, Slides, Calendar, and Gmail. Your agents can read and write these services directly, without you standing up an MCP server. Integrations join tasks, Skills, and MCP servers as a way to give agents tools. See [Connections](/docs/concepts/connections). ### API Key Authentication for MCP Servers Connect an MCP server using an API key as an alternative to OAuth, for servers that authenticate that way. MCP servers are now scoped to the user who created them, so credentials are never shared across a project by default. See [MCP](/docs/interop/mcp). ### Redesigned Agent Experience A rebuilt agent interface makes building and running agents clearer, with a new Observe page that surfaces a runs table, the trigger behind each run, and specific failure reasons. Agent streaming now persists as you switch tabs, with a stop button and clickable tool badges. See [Observability](/docs/production/observability). ### In-App Audit Logs Audit events are now stored in the product and are queryable and exportable directly, covering activity such as task and forwarder changes. This makes it straightforward to review and hand off a record of what happened in a project. ## Improvements * Slack responses now render Markdown for cleaner formatting. * View a project's most recent runs at a glance. * Calendar-based date selection and log period management in Logs. * Failed runs now preserve tool metadata to make debugging easier. * The slug is optional when creating a Skill. * Non-actionable background errors are filtered out for a quieter experience. > **Note** > > With Integrations, Rightbrain manages the connection and credentials for you, so enabling a Google Workspace service for an agent takes a single authorization step. ## Current documentation [Connections](/docs/concepts/connections) · [Authentication](/docs/api/authentication) · [Agents](/docs/concepts/agents) · [Observability](/docs/production/observability) ## Skills and Knowledge Bases > Equip agents with skills, ground tasks in document collections, transcribe audio, and interact through Slack. ## What's New ### Skills Skills are reusable, versioned abilities your agents can call on to complete focused work. Browse a marketplace of ready-made Skills, or create your own project-scoped Skills with their own instructions and reference files. Skills are added to an agent alongside its tasks and tools. See [Skills](/docs/concepts/skills). ### Collections Group documents into a Collection and connect it to a task to ground answers in your own content. Upload and manage files, then choose retrieval options directly on the task so responses draw on the right knowledge base. See [Collections](/docs/concepts/collections). ### Audio Transcription for Tasks A new audio transcription input processor lets a task accept an audio file, transcribe it to text, and run any model over the result. The model you choose only ever sees text, so audio input works regardless of provider. See [Tasks](/docs/concepts/tasks). ### Slack for Agents Connect a Slack workspace to your project and interact with your agents from Slack using mentions, direct messages, thread replies, and the `/rightbrain` command. Route different channels to different agents, with a default agent as a fallback. See [Connections](/docs/concepts/connections). ## Improvements * Project-level usage reporting with visibility controls. * Global tags, and the ability to assign tags when you create a task. * Date filtering on run listings. * Richer task run output for easier inspection. * Redesigned API and MCP tabs, plus a new preferences area with project deletion. * Templates are now built on shared tasks. ## Current documentation [Skills](/docs/concepts/skills) · [Collections](/docs/concepts/collections) · [Input processors](/docs/concepts/input-processors) · [Connections](/docs/concepts/connections) ## Agent Triggers and Execution Modes > Schedule agents, choose agentic or sequential execution, attach MCP tools, and inspect run performance. ## What's New ### Triggers for Agents Triggers can now start an agent, not just a task. Fire an agent from an incoming webhook, or run it automatically on a recurring schedule with cron and time zone support. Webhook-triggered agent runs are accepted immediately and processed in the background, so long-running work never blocks the caller. See [Triggers and runs](/docs/concepts/triggers-and-runs). ### Sequential Execution Mode Agents now run in one of two modes. In agentic mode the model decides which tools to call and in what order; in sequential mode the agent runs a fixed pipeline where each step feeds the next. Choose the mode that fits the job when you build an [agent](/docs/concepts/agents). ### Direct MCP Server Connections Attach an MCP server straight to an agent for direct, single-hop access to its tools, with no intermediate task required. A redesigned MCP servers area and marketplace make it easier to add, browse, and connect servers. See [MCP](/docs/interop/mcp). ### Agent Observability and Reporting New token, credit, timing, and usage reports give you an aggregate view of how your agents perform. Run, session, and event data is now enriched with per-step timing and error detail, so you can trace a run without opening each underlying task. See [Observability](/docs/production/observability). ## Improvements * A new versioning interface for reviewing agent revisions and rolling back to an earlier one. See [Versioning and revisions](/docs/production/revisions). * Improved retrieval-augmented generation for tasks backed by a knowledge base. * Filter the tool list when configuring an agent, making large tool sets easier to work with. * Redesigned agent pages. * Hardened handling of webhook credentials. > **Note** > > Combine schedule triggers with an agent to run recurring work unattended, such as a daily report or a periodic data sync, with no code to maintain. ## Current documentation [Agents](/docs/concepts/agents) · [Triggers and runs](/docs/concepts/triggers-and-runs) · [MCP](/docs/interop/mcp) · [Observability](/docs/production/observability) ## Agents and MCP Connections > Build agents that call task tools, connect external MCP servers, and manage webhook deliveries and CLI automation. ## What's New ### Introducing Agents Agents are AI orchestrators that reason over natural language and call your existing tasks to get work done. An agent can select and run multiple tasks in sequence, hold a multi-turn conversation, and stream its responses as it works. Build one in the dashboard and give it the tasks it needs. See [Agents](/docs/concepts/agents). ### MCP Server Connections Connect external Model Context Protocol (MCP) servers to bring third-party tools into Rightbrain. Authenticate with OAuth or an API key, discover the tools a server offers, and register the ones you want to use. Connections stay healthy over time with automatic token refresh and clear status when re-authentication is needed. See [Connections](/docs/concepts/connections) and [MCP](/docs/interop/mcp). ### Task Triggers in the Dashboard The triggers system now has a home in the dashboard. Configure webhook triggers on a task from a redesigned task layout, without touching the API. ## Improvements * New CLI commands to list, get, update, and export tasks, enabling a Cursor plugin to manage tasks directly from your editor * Non-interactive CLI login for use in CI and automation * Typed SDK generation so your task inputs and outputs are checked in code * Task run status badges and clearer revision handling in the task view * Inspect individual webhook deliveries with a new event lookup > **Note** > > MCP connections let an agent use tools from services you already rely on. Authenticate once, register the tools, and your agents can call them as part of a run. ## Current documentation [Agents](/docs/concepts/agents) · [Connections](/docs/concepts/connections) · [TypeScript SDK](/docs/api/sdk) ## Triggers and Automation > Trigger tasks from signed webhooks, automate task management with the CLI, and inspect project-wide run history. ## What's New ### Triggers and Webhooks Tasks can now run automatically in response to external events. Create a webhook endpoint that runs a task whenever an outside service calls it, map the incoming payload to your task inputs, and secure it with HMAC or bearer token authentication. Connect GitHub, Stripe, Slack, or any service that can send an HTTP request. See [Triggers and Runs](/docs/concepts/triggers-and-runs). ### Rightbrain CLI v2 A rebuilt command-line interface for working with Rightbrain from your terminal. Log in with OAuth, initialize a project, run tasks with file and image inputs, list available models, and generate typed task runners for use in your code. ### Project-Wide Run History A new view lists every task run across a project in one place, with filtering by task and by success or failure. Run visibility settings are respected throughout, so people see the runs they are permitted to see while always seeing their own. See [Observability](/docs/production/observability). ## Improvements * Task shares are now taggable, and you can list every share across a project * Clone a shared task directly from the CLI * Model lists can be filtered so you only see models that fit your task's requirements > **Note** > > Webhook triggers turn a task into an endpoint that other systems can call, so a new pull request, a payment event, or a form submission can kick off a task run without any manual step. ## Current documentation [Triggers and runs](/docs/concepts/triggers-and-runs) · [CLI](/docs/api/cli) · [Observability](/docs/production/observability) ## Visual Inputs for Tasks > Send images and PDFs directly to vision-capable tasks and show file requirements on shared pages. ## What's New ### Image and PDF Inputs Tasks can now accept images or PDF documents as visual input for the model to read and reason over. Set how a task handles files with the new file input mode, choosing between images only, PDFs only, or both. This makes it straightforward to build tasks that check text against a screenshot, extract fields from a scanned document, or validate visual content. See [Tasks](/docs/concepts/tasks). ### Vision-Aware Shared Pages Shared task pages now show exactly which file types a task accepts, with a clear "Prompt Variables" section for text inputs and a "Valid File Attachments" section for images and PDFs. Anyone you share a task with can see its input requirements before running it. ## Improvements * Clearer separation between prompt variables and file attachments when configuring a task * Stronger validation when creating and updating tasks, with more useful error messages * Fixed duplicate images appearing when selecting an image for a task run > **Note** > > File input mode lets you require a specific file type for a task. A document-review task can insist on a PDF, while an image-analysis task can accept either an image or a PDF. ## Current documentation [Tasks](/docs/concepts/tasks) · [Run tasks with files](/docs/api/run-tasks) ## Image Generation and Agent Protocol > Generate images with OpenAI, expose tasks through A2A, and manage project deletion and shared-page formatting. ## What's New ### OpenAI Image Generation Create images directly in your tasks using OpenAI's GPT Image model. Configure size, quality, and output format. The AI generates images from your prompts with support for various aspect ratios and quality levels. ### A2A Protocol Support Connect your Rightbrain tasks to other AI agents using the Agent-to-Agent (A2A) protocol. Your tasks appear as agents that external systems can discover and call via standard JSON-RPC endpoints. Perfect for building multi-agent workflows. ### Project Deletion Clean up your workspace by deleting projects you no longer need. Deleted projects are soft-deleted, preserving history while freeing up the project name for reuse. ### Rich Markdown on Shared Pages Shared task pages now render full GitHub Flavored Markdown, making shared results look polished and professional. ## Improvements * Better loading states when waiting for AI responses * Clearer error messages for duplicate project names * Updated team seat limits for trial and pro plans * More accurate credit tracking for task runs > **Note** > > A2A protocol support means your Rightbrain tasks can be called by AI assistants, orchestration frameworks, and other agent systems - turning your tasks into reusable AI capabilities. ## Current documentation [Model governance](/docs/production/model-governance) · [Tasks](/docs/concepts/tasks) · [A2A interoperability](/docs/interop/a2a) ## Email Forwarding and JSON Schemas > Forward task results by email, import JSON output schemas, and use the published JavaScript API client. ## What's New ### Email Task Forwarding Forward task results directly to email addresses. Configure one or more recipient email addresses and the task output will be sent automatically when the task completes. Uses a template editor with variable suggestions to customize the email content. ### JSON Schema Import Import JSON schemas to define your output formats with validation. Paste or upload a schema and the system validates and applies it to ensure your task outputs match exactly the structure you need. ### NPM Package The Rightbrain API client is now available on npm as `@rightbrainai/brain-api-client`, making it easier to integrate Rightbrain into JavaScript and TypeScript projects. ## Improvements * Better template notation handling with autocomplete * Updated API documentation * Improved modal dialog interactions > **Note** > > Email forwarding is perfect for automated reports - run a task and have the results delivered straight to your inbox or your team's. ## Current documentation [Task forwarders](/docs/api/task-forwarders) · [Tasks](/docs/concepts/tasks) · [TypeScript SDK](/docs/api/sdk) ## New Output Formats > Generate PDF, CSV and text output, render Markdown results, and download attachments inline. ## What's New ### PDF Output Tasks can now generate PDF documents directly. The AI creates HTML content that's automatically converted to PDF files. Perfect for reports, invoices, and formatted documents. ### CSV Output Export structured data as CSV files with table displays in the interface. Great for data processing, analytics, and spreadsheet-ready outputs. ### Text Output A plain text output option provides clean, unformatted results when that's what you need. ### Markdown Rendering Task responses now render Markdown with full GitHub Flavored Markdown support including tables, code blocks, and task lists. ### Inline Attachment Downloads Download task run attachments directly inline without navigating away - streamlined access to all generated files. ## Improvements * Enhanced share page design and functionality * Faster task execution with optimized queries * Better handling of client disconnections * Security patches for React and Next.js ## Current documentation [Tasks](/docs/concepts/tasks) · [Run tasks](/docs/api/run-tasks) ## Share Examples and Download Results > Attach example runs to shared tasks, download generated files, and receive organization invitations. ## What's New ### Share Tasks with Example Runs When sharing tasks publicly, you can now attach an example run to show exactly what the task produces. Viewers see the example inputs and outputs, and when they clone the task, those inputs are pre-filled automatically. ### Organization Invite Notifications Team members now receive notifications when invited to join an organization. The invitation interface shows clear actions and better plan-based project creation options. ### Task File Downloads Download files generated by your tasks directly from the interface. Documents, images, and other outputs are one click away. ### Image and Audio Output Support Choose image or audio output for supported task configurations. ## Improvements * Redesigned share pages optimized for mobile * Updated task card and usage record designs * Better Perplexity search validation with query context * Animated workspace creation experience ## Current documentation [Sharing and cloning](/docs/production/sharing) · [Run tasks](/docs/api/run-tasks) · [Projects and organizations](/docs/concepts/projects-and-orgs) ## Task Cloning and Sharing Controls > Clone tasks across projects, set run visibility, and access contextual support from the dashboard. ## What's New ### Task Cloning Duplicate any task with a single click. Clone tasks across projects - works for logged-in users, registered users who need to sign in, and new signups. Perfect for creating variations or sharing templates. ### Task Run Visibility Controls New sharing dialog lets you control who can see task run results. Choose from owner only, editors and owners, or all viewers. Share buttons and visibility indicators now appear on task cards and lists. ### Contextual Help Get help exactly when you need it with context-aware Intercom support that understands where you are in the application. ## Improvements * Updated pricing plan card designs for clearer comparisons * Better project validation and session handling * Improved document type support for sharing ## Current documentation [Sharing and cloning](/docs/production/sharing) · [Authentication](/docs/api/authentication) _Showing the 20 most recent of 41 entries. Append `/llms.txt` to the changelog URL for the complete index._