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.
\nAgent 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.
\nTasks can use supported Azure OpenAI deployments, and Claude Fable 5 is available for demanding reasoning and agentic workloads.
\nEvals · Observability · Model governance · Run agents with files
", "url": "https://docs.rightbrain.ai/changelog/2026/9/1", "title": "Evals and Run Operations", "summary": "Replay file-backed evals, inspect agent run activity and costs, and use Azure OpenAI deployments.", "date_modified": "2026-09-01T00:00:00.000Z" }, { "content_html": "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.
\nApproval-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.
\nXero 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.
\nTask 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.
\nConnections · Approvals · Observability
", "url": "https://docs.rightbrain.ai/changelog/2026/8/16", "title": "Connections, Approvals, and Xero", "summary": "Choose personal or shared connections, sample tool calls for human review, and trace the identity behind a run.", "date_modified": "2026-08-16T00:00:00.000Z" }, { "content_html": "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.
\nAgent 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.
\nA unified Shares view brings Task and agent shares into one searchable, filterable list. Share tags can be managed from the same Project-level workflow.
\nThe 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.
\nModel governance · Evals · CLI · Sharing and cloning
", "url": "https://docs.rightbrain.ai/changelog/2026/8/1", "title": "Model Governance and Evaluations", "summary": "Control model availability, customize agent eval rubrics, and automate API access through named CLI environments.", "date_modified": "2026-08-01T00:00:00.000Z" }, { "content_html": "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.
\nTest 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.
\nIntegration 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.
\nAudit 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.
\nApprovals · Chaos testing · Connections · Observability
", "url": "https://docs.rightbrain.ai/changelog/2026/7/16", "title": "Approvals, Chaos Mode, and Audit Integrity", "summary": "Review approvals, test recovery with Chaos Mode, attach integrations to tasks, and verify audit-log integrity.", "date_modified": "2026-07-16T00:00:00.000Z" }, { "content_html": "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.
\nMistral's models are now available for your tasks and agents, widening the range of providers you can build on and fall back to.
\nUpload 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.
\nConnections · Model governance · Run agents with files
", "url": "https://docs.rightbrain.ai/changelog/2026/7/1", "title": "Slack, Mistral, and File Attachments", "summary": "Connect agents to Slack, use Mistral models, and inspect uploaded or generated files in agent runs.", "date_modified": "2026-07-01T00:00:00.000Z" }, { "content_html": "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.
\nTools 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.
\nStart 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.
\nTasks now have a Schedule tab for running them on a recurring schedule directly from the dashboard, with no external scheduler required.
\nApprovals · Run agents with files · Triggers and runs
", "url": "https://docs.rightbrain.ai/changelog/2026/6/16", "title": "Approvals, Runtime Files, and Gmail Triggers", "summary": "Pause tool calls for approval, pass files between tools, and start runs from Gmail or schedules.", "date_modified": "2026-06-16T00:00:00.000Z" }, { "content_html": "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 for details.
\nA new audit log page records activity across your project, with filters by resource type and identifier so you can trace exactly what changed and when.
\nDrag and drop multiple files straight into an agent run, 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.
\nObservability · Memory and context · Run agents with files
", "url": "https://docs.rightbrain.ai/changelog/2026/6/1", "title": "Context Usage, Audit Log, and File Attachments", "summary": "Inspect agent context usage, trace project changes in audit logs, and attach files to agent conversations.", "date_modified": "2026-06-01T00:00:00.000Z" }, { "content_html": "Test changes before you ship them with 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.
\nShare 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.
\nKeep long-running agent conversations within the model's context window using memory compaction. 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.
\nAgents 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.
\nEvals · Sharing and cloning · Memory and context
", "url": "https://docs.rightbrain.ai/changelog/2026/5/16", "title": "Evals, Agent Sharing, and Memory Compaction", "summary": "Evaluate task and agent revisions, share and clone agents, and compact conversation history within context limits.", "date_modified": "2026-05-16T00:00:00.000Z" }, { "content_html": "Give your agents reusable, focused abilities with 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.
\nConnections 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.
\nChanges to an agent’s execution configuration now create a new revision 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.
\nChoose 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.
\nurl_fetcher input processor added a direct fetch modeSkills · Connections · Revisions · Fallbacks
", "url": "https://docs.rightbrain.ai/changelog/2026/5/1", "title": "Skills, Connections, and Agent Versioning", "summary": "Manage versioned skills and connections, select active agent revisions, and configure agent fallback models.", "date_modified": "2026-05-01T00:00:00.000Z" }, { "content_html": "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.
\nConnect 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.
\nA 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.
\nAudit 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.
\nConnections · Authentication · Agents · Observability
", "url": "https://docs.rightbrain.ai/changelog/2026/4/16", "title": "Integrations and Agent Experience", "summary": "Connect Google Workspace tools, authenticate MCP servers with API keys, and inspect agent runs and audit logs.", "date_modified": "2026-04-16T00:00:00.000Z" }, { "content_html": "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.
\nGroup 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.
\nA 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.
\nConnect 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.
Skills · Collections · Input processors · Connections
", "url": "https://docs.rightbrain.ai/changelog/2026/4/1", "title": "Skills and Knowledge Bases", "summary": "Equip agents with skills, ground tasks in document collections, transcribe audio, and interact through Slack.", "date_modified": "2026-04-01T00:00:00.000Z" }, { "content_html": "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.
\nAgents 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.
\nAttach 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.
\nNew 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.
\nAgents · Triggers and runs · MCP · Observability
", "url": "https://docs.rightbrain.ai/changelog/2026/3/16", "title": "Agent Triggers and Execution Modes", "summary": "Schedule agents, choose agentic or sequential execution, attach MCP tools, and inspect run performance.", "date_modified": "2026-03-16T00:00:00.000Z" }, { "content_html": "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.
\nConnect 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 and MCP.
\nThe triggers system now has a home in the dashboard. Configure webhook triggers on a task from a redesigned task layout, without touching the API.
\nAgents · Connections · TypeScript SDK
", "url": "https://docs.rightbrain.ai/changelog/2026/3/1", "title": "Agents and MCP Connections", "summary": "Build agents that call task tools, connect external MCP servers, and manage webhook deliveries and CLI automation.", "date_modified": "2026-03-01T00:00:00.000Z" }, { "content_html": "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.
\nShared 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.
\nCreate 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.
\nConnect 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.
\nClean 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.
\nShared task pages now render full GitHub Flavored Markdown, making shared results look polished and professional.
\nModel governance · Tasks · A2A interoperability
", "url": "https://docs.rightbrain.ai/changelog/2026/1/16", "title": "Image Generation and Agent Protocol", "summary": "Generate images with OpenAI, expose tasks through A2A, and manage project deletion and shared-page formatting.", "date_modified": "2026-01-16T00:00:00.000Z" }, { "content_html": "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.
\nImport 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.
\nThe Rightbrain API client is now available on npm as @rightbrainai/brain-api-client, making it easier to integrate Rightbrain into JavaScript and TypeScript projects.
Task forwarders · Tasks · TypeScript SDK
", "url": "https://docs.rightbrain.ai/changelog/2026/1/2", "title": "Email Forwarding and JSON Schemas", "summary": "Forward task results by email, import JSON output schemas, and use the published JavaScript API client.", "date_modified": "2026-01-02T00:00:00.000Z" }, { "content_html": "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.
\nExport structured data as CSV files with table displays in the interface. Great for data processing, analytics, and spreadsheet-ready outputs.
\nA plain text output option provides clean, unformatted results when that's what you need.
\nTask responses now render Markdown with full GitHub Flavored Markdown support including tables, code blocks, and task lists.
\nDownload task run attachments directly inline without navigating away - streamlined access to all generated files.
\nWhen 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.
\nTeam members now receive notifications when invited to join an organization. The invitation interface shows clear actions and better plan-based project creation options.
\nDownload files generated by your tasks directly from the interface. Documents, images, and other outputs are one click away.
\nChoose image or audio output for supported task configurations.
\nSharing and cloning · Run tasks · Projects and organizations
", "url": "https://docs.rightbrain.ai/changelog/2025/12/2", "title": "Share Examples and Download Results", "summary": "Attach example runs to shared tasks, download generated files, and receive organization invitations.", "date_modified": "2025-12-02T00:00:00.000Z" }, { "content_html": "Tasks can now search the web using Perplexity AI, bringing real-time information into your workflows. Configure search context and result limits to get exactly the data you need for research, fact-checking, and content enrichment.
\nShare task results with team members or external stakeholders. Enable public sharing on tasks to collaborate more effectively and showcase your AI workflows.
\nModel governance · Sharing and cloning
", "url": "https://docs.rightbrain.ai/changelog/2025/11/1", "title": "Web Search and Task Sharing", "summary": "Search the web with Perplexity-backed tasks and share run results with teammates or external readers.", "date_modified": "2025-11-01T00:00:00.000Z" }, { "content_html": "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.
\nNew 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.
\nGet help exactly when you need it with context-aware Intercom support that understands where you are in the application.
\nSharing and cloning · Authentication
", "url": "https://docs.rightbrain.ai/changelog/2025/11/16", "title": "Task Cloning and Sharing Controls", "summary": "Clone tasks across projects, set run visibility, and access contextual support from the dashboard.", "date_modified": "2025-11-16T00:00:00.000Z" }, { "content_html": "Text extraction has improved for PDFs, images, scanned documents and complex layouts.
\nRedesigned interface makes it easier to integrate tasks into your applications with clearer code examples, better testing tools, and improved documentation.
\nImproved validation helps catch malformed structured outputs.
\nFile inputs · Tasks · Getting started
", "url": "https://docs.rightbrain.ai/changelog/2025/10/16", "title": "Enhanced Document Processing and Integration", "summary": "Extract content from uploaded documents and use clearer integration examples, validation and task-building tools.", "date_modified": "2025-10-16T00:00:00.000Z" }, { "content_html": "Control which AI models are available at the organization or project level. Set defaults, restrict access to specific models, and ensure consistency across teams.
\nChoose your own fallback model for each task. The fallback can run when the primary model encounters a supported failure.
\nEnhanced JSON handling for supported models ensures more reliable data extraction from AI responses with fewer formatting issues.
\nModel governance · Fallbacks · Tasks
", "url": "https://docs.rightbrain.ai/changelog/2025/10/2", "title": "Flexible Model Configuration", "summary": "Control model availability, choose task fallback models, and improve structured output handling.", "date_modified": "2025-10-02T00:00:00.000Z" }, { "content_html": "Open live support chat directly within the platform. Ask questions, report issues, and get guidance without leaving your workflow.
\nThe login page and onboarding flow have been redesigned.
\nStep-by-step guidance helps new users create and run their first task.
\nConnect your Rightbrain tasks to AI assistants like Claude, Cursor, and other MCP-compatible tools. Expose tasks to compatible clients through MCP.
\nOrganize and track task usage by team, project, or use case with reporting groups, useful for understanding costs and performance across your organization.
\nGenerate voice responses and audio content directly from your tasks, opening up new possibilities for voice-enabled applications.
\nMCP interoperability · Observability · Tasks
", "url": "https://docs.rightbrain.ai/changelog/2025/8/16", "title": "MCP Protocol and Real-Time Capabilities", "summary": "Expose tasks through MCP, segment usage with reporting groups, and generate audio output.", "date_modified": "2025-08-16T00:00:00.000Z" }, { "content_html": "Upload and process CSV files as task inputs, perfect for data enrichment, batch processing, and analysis workflows. Transform spreadsheet data at scale.
\nMore flexible trial periods ensure new users get the full experience to evaluate the platform's capabilities before committing.
\nClearer error messages help you understand and fix issues faster when tasks fail, with specific guidance on what went wrong and how to resolve it.
\nFile inputs · Tasks · Usage and credits
", "url": "https://docs.rightbrain.ai/changelog/2025/8/2", "title": "CSV Support and Enhanced Trials", "summary": "Process CSV inputs, inspect clearer task errors, and manage trial periods and team permissions.", "date_modified": "2025-08-02T00:00:00.000Z" }, { "content_html": "Manage retired models and migrate affected tasks to replacement models.
\nBetter control over who can access task execution results with granular permissions, perfect for multi-tenant applications and team collaboration.
\nAdd performance insights and notes to models, helping your team share knowledge about which models work best for specific use cases.
\nModel governance · Authentication
", "url": "https://docs.rightbrain.ai/changelog/2025/7/16", "title": "Model Management and Access Control", "summary": "Manage model retirements, document model behavior, and control access to task run results.", "date_modified": "2025-07-16T00:00:00.000Z" }, { "content_html": "Create and manage MCP servers with easy-to-remember short IDs. Track server health, monitor usage, and get detailed logging for all MCP connections.
\nEvery MCP interaction is now recorded with detailed timestamps and metadata, giving you complete visibility into how your tasks are being used through external tools.
\nOrganization and project data loads more quickly in the dashboard.
\nMCP interoperability · Observability
", "url": "https://docs.rightbrain.ai/changelog/2025/7/2", "title": "MCP Server Management and Performance", "summary": "Manage MCP servers, inspect recorded MCP calls, and navigate organization and project data more quickly.", "date_modified": "2025-07-02T00:00:00.000Z" }, { "content_html": "Configure custom parameters for your AI models including temperature, top-p, and other advanced settings to fine-tune task behavior for your specific needs.
\nEnhanced security for mobile and single-page app integrations. Use PKCE for public OAuth clients that cannot safely hold a client secret.
\nAutomatic OAuth discovery makes it easier for applications to configure authentication with Rightbrain without manual configuration.
\nModel governance · Authentication
", "url": "https://docs.rightbrain.ai/changelog/2025/6/2", "title": "Custom Model Parameters and Secure Authentication", "summary": "Configure model parameters and integrate mobile or browser applications using OAuth with PKCE and discovery.", "date_modified": "2025-06-02T00:00:00.000Z" }, { "content_html": "Tasks can now generate images using Vertex AI's Imagen models. Create visual content, diagrams, product mockups, and more through the same task interface.
\nRun Meta's Llama 3.3 models through Groq.
\nNew URL fetcher and document content extractor processors make it easier to work with web content and file uploads in your tasks.
\nTasks · Model governance · File inputs
", "url": "https://docs.rightbrain.ai/changelog/2025/5/16", "title": "Image Generation and Llama 3.3", "summary": "Generate images with Imagen, run Llama 3.3 through Groq, and extract task inputs from documents and URLs.", "date_modified": "2025-05-16T00:00:00.000Z" }, { "content_html": "Full billing integration with Stripe including subscriptions, usage-based pricing, invoices, and automatic credit top-ups.
\nManage plan upgrades, downgrades, cancellations and subscription credit allocation.
\nMigrated ad-hoc payments to proper invoice system with better tracking, tax handling, and payment reconciliation.
\nTasks 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.
\nA 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.
\nA 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.
\nTriggers and runs · CLI · Observability
", "url": "https://docs.rightbrain.ai/changelog/2026/2/16", "title": "Triggers and Automation", "summary": "Trigger tasks from signed webhooks, automate task management with the CLI, and inspect project-wide run history.", "date_modified": "2026-02-16T00:00:00.000Z" }, { "content_html": "New @rightbrain/sdk package provides type-safe access to the Rightbrain API with full TypeScript support and IntelliSense for better developer experience.
Better tools for testing tasks before deployment, including enhanced preview capabilities and clearer output visualization.
\nTypeScript SDK · Tasks · File inputs
", "url": "https://docs.rightbrain.ai/changelog/2025/2/16", "title": "TypeScript SDK and Enhanced Testing", "summary": "Use the TypeScript SDK for typed API calls and inspect task outputs with improved testing and file handling.", "date_modified": "2025-02-16T00:00:00.000Z" }, { "content_html": "Support for string enums, number types (float/decimal), and additional type constraints gives you more control over exactly what data your tasks return.
\nOrganization, project, and task names are validated when resources are created or updated.
\nClearer error responses with actionable context make it easier to understand and fix issues when creating or updating tasks.
\nCreate task test revisions for testing without affecting production. Experiment with new prompts, models, or configurations safely before deploying changes.
\nComplete revision management with easy comparison between versions. Track what changed, when, and see performance differences across revisions.
\nBetter handling of PDFs, images, and document uploads with improved text extraction and support for more file types.
\nAutomatic validation ensures your prompts fit within model limits. Get clear errors before execution instead of runtime failures.
\nDetailed credit usage reports by task, user, and time period help you understand and optimize AI costs across your organization.
\nSee detailed input and output token counts for every task execution, making it easy to forecast expenses and optimize model selection.
\nObservability · Model governance
", "url": "https://docs.rightbrain.ai/changelog/2025/3/16", "title": "Cost Tracking and Model Insights", "summary": "Inspect credit and token usage by task and validate prompt sizes against model context limits.", "date_modified": "2025-03-16T00:00:00.000Z" }, { "content_html": "Access your tasks via REST API, TypeScript SDK, or Model Context Protocol. Choose the integration method that works best for your tech stack.
\nCreate and manage OAuth applications directly from the dashboard. Support for multiple authentication flows makes integration straightforward.
\nProcess images, documents, and URLs automatically before they reach your AI model. Extract text, optimize images, and fetch web content seamlessly.
\nTypeScript SDK · MCP interoperability · File inputs · Authentication
", "url": "https://docs.rightbrain.ai/changelog/2025/1/16", "title": "Flexible Integration and Smart Input Processing", "summary": "Connect through REST, TypeScript or MCP, configure OAuth clients, and prepare documents and URLs for task input.", "date_modified": "2025-01-16T00:00:00.000Z" }, { "content_html": "Execute specific task revisions using tags. Perfect for blue-green deployments, A/B testing, and managing multiple task versions in production environments.
\nFilter task runs by success or error state, track performance metrics, and get better insights into which executions succeed or fail.
\nCreate shareable links for your tasks, making it easy to demo capabilities or allow limited external access without full authentication.
\nTask revisions · Observability · Sharing and cloning
", "url": "https://docs.rightbrain.ai/changelog/2025/6/16", "title": "Advanced Task Execution and Sharing", "summary": "Select task revisions by tag, filter run outcomes, and share tasks with external users.", "date_modified": "2025-06-16T00:00:00.000Z" }, { "content_html": "Transparent credit balance tracking with complete transaction history. See exactly how credits are earned, spent, and allocated across your organization.
\nCredit allocation covers trial accounts and subscription renewals, with transaction records for reviewing balance changes.
\nImproved user onboarding experience with automatic initial credit allocation and clearer guidance for new teams.
\nCreate AI tasks through the dashboard or API, with prompts and structured outputs that can be reused in applications.
\nBuild reusable AI tools with structured inputs and outputs. Each task is versioned, observable, and ready to integrate into your applications.
\nAuthenticate API requests and control access to organization and project resources.
\nTasks · Authentication · Observability
", "url": "https://docs.rightbrain.ai/changelog/2025/1/2", "title": "Welcome to Rightbrain", "summary": "Create reusable AI tasks with structured inputs and outputs, version history, access controls and usage tracking.", "date_modified": "2025-01-02T00:00:00.000Z" }, { "content_html": "Test your MCP server integrations directly from the dashboard. Verify connectivity, validate configurations, and debug issues before deploying to production.
\nUpload files directly in assistant conversations to get better suggestions and more context-aware help when building tasks.
\nInteractive buttons in assistant responses make it easier to take action on suggestions without switching contexts.
\nMCP interoperability · File inputs · Getting started
", "url": "https://docs.rightbrain.ai/changelog/2025/9/16", "title": "MCP Server Testing and File Attachments", "summary": "Test MCP connections, attach files to assistant conversations, and inspect task run attachments.", "date_modified": "2025-09-16T00:00:00.000Z" }, { "content_html": "Add notes and context to specific task revisions. Document changes, performance observations, and important decisions directly on each version for better team collaboration.
\nOrganize tasks, collections, and other entities with tags. Build hierarchies, filter by tags, and manage large task libraries more effectively.
\nGenerate and manage your own API keys with automatic usage tracking. See when each key was last used and maintain better security hygiene.
\n