Release Notes

Multi-Agent Orchestrator

Chain multiple specialized agents together to create complex, intent-driven workflows. A "Supervisor" agent evaluates the user's request and intelligently routes it to the most appropriate subagent. Subagents execute their task and return the result — the supervisor can then refine the response before delivering it to the user.

Keyword-Based Routing

Configure specific keywords on each subagent to enable deterministic routing. When a user's message contains a configured keyword, the message is routed directly to the matched subagent — bypassing the main agent's LLM entirely for faster, more predictable responses.

Direct Subagent Selection in Copilot

End-users can now manually select which subagent should handle their message using a selection interface in the Copilot input area. This gives users explicit control when they already know which specialist they need.

Subagent Response Attribution

Messages handled by a subagent are now clearly marked in the conversation UI with a distinct icon and the subagent's name, making it immediately clear which agent generated each response.

AI-Optimized Subagent Descriptions

An integrated "Optimize with AI" button rewrites your subagent descriptions into 75–150 word prompts specifically formatted for optimal LLM tool selection accuracy.

Visual Orchestrator Graph

A built-in React Flow visualizer displays the hierarchical relationship between your agents. Active subagents are outlined in green, archived ones in red. Click any node to navigate directly to that agent's configuration.

MCP Integrations (Client Mode)

Connect your agent to external MCP (Model Context Protocol) servers and use their tools natively. Your agent can now call tools hosted on any MCP-compatible server — CRMs, databases, internal APIs, or third-party platforms — directly within conversations.

Tool Discovery & Selection

When adding an MCP integration, click "Get Available Tools" to probe the remote server and browse all available tools. Select which tools to expose to your agent — only selected tools are passed to the LLM, keeping context lean and routing accurate.

Streamable HTTP & SSE Transport

MCP integrations support both Streamable HTTP (default) and Server-Sent Events (SSE) transport protocols, ensuring compatibility with a wide range of MCP server implementations.

RAIA MCP Server (Server Mode)

Expose your raia agent as a tool that other AI platforms can query. External systems can send prompts to your agent via a standardized MCP endpoint, and your agent responds using its full AI pipeline — instructions, vector store, and linked packs included.

OAuth & Bearer Token Authentication

Secure your MCP connections with either Bearer token or OAuth authentication. Authorization tokens are masked in API responses for security.

Configurable Retention Periods

Control how long conversations are stored before they are anonymized. Set a retention period between 1 and 3,650 days (up to 10 years). Conversations older than the configured period are automatically processed.

Conversation Anonymization

When the retention period expires, conversation data is permanently overwritten — message content is replaced with [ANONYMIZED], and associated metadata (user names, emails, phone numbers, IP addresses) is cleared. This is a destructive operation designed for compliance — data is truly gone, not soft-deleted.

User Anonymization

Optionally anonymize the conversation users associated with expired conversations. User names, emails, phone numbers, and external IDs are cleared independently from message content, giving you granular control over what gets retained.

Audit Logging

Every anonymization run is logged to the Action Logger with counts of conversations and users processed, providing a full compliance audit trail.

Smart Cutoff Logic

The retention period is calculated from the most recent message in a conversation, not the conversation creation date. This ensures active conversations are never anonymized prematurely.

Daily Inbound Message Limits

Set a daily message limit per user to prevent abuse and control costs. Messages from email, SMS, live chat, copilot, and other channels all count toward one shared daily limit.

Cross-Channel Tracking

Usage is tracked per-channel (email, SMS, live chat, etc.) with a unified total. Admins can see exactly how many messages a user sent on each channel within the current day.

Per-User Custom Limits

Override the global default for specific users. Grant VIP customers a higher allowance, or restrict problematic users to a lower cap — all without affecting other users.

Temporary Unlimited Access

Temporarily grant a user unlimited messages (e.g., during onboarding or escalation resolution) without permanently changing their configured limit.

Automatic Daily Reset

All counters automatically reset at the end of each UTC day. No manual intervention required.

Quota Exceeded Alerts

When a user hits their daily limit, the system generates an alert visible in the Message Quota Skill's Alerts tab. Admins can review, adjust limits, or grant temporary unlimited access directly from the alert.

Zero-Token Blocking

Quota checks run before the message reaches the LLM. Blocked messages consume zero tokens, ensuring costs are fully controlled.

Organization Default Limits

Set baseline monthly caps for tokens, SMS, emails, and call minutes at the organization level. These defaults apply automatically to any agent or user that does not have a custom limit configured.

Agent-Level Usage Limits

Override organization defaults with per-agent monthly caps. Each agent can have its own token, SMS, email, and call minute budget — preventing any single agent from consuming disproportionate resources.

User-Level Usage Limits

Control resource consumption per end-user. Set monthly caps on how many tokens, SMS messages, emails, and call minutes each user can consume across all their conversations.

Real-Time Usage Dashboard

Monitor consumption with live progress bars on the Agent Usage tab. The dashboard auto-refreshes every 60 seconds, showing current usage against configured limits for all four resource types.

Subscription Ceiling Enforcement

Agent and user limits cannot exceed the organization's subscription maximum. The UI displays the maximum allowed value below each input field and warns admins if a subscription downgrade makes existing limits invalid.

Graceful Fallback Chain

Limits resolve in order: Custom Agent/User Limit → Organization Default → Subscription Limit. Deleting a custom limit immediately reverts to the next level in the chain.

Zero-Cost Enforcement

All quota checks occur before the action is executed. If a limit is exceeded, the action is blocked before reaching the LLM or external service — no resources are wasted on blocked requests.

Teams Channel & DM Support

Your raia agent can now respond to direct messages and channel mentions in Microsoft Teams. Users can interact with the agent naturally within their existing Teams workspace.

Scope-Based Access Control

Choose who can message your agent: allow all users in the tenant, or restrict access to specific users and channels using Microsoft Graph IDs.

Multi-Agent Picker

When multiple agents are configured for the same Teams tenant, the bot presents an Adaptive Card allowing the user to select which agent they want to interact with.

Pause vs. Disconnect

Pause an account to temporarily disable a specific agent's Teams connection without affecting other agents. Disconnect to fully remove the Microsoft OAuth connection for your entire organization.

File Upload Support

Users can attach up to 5 files (20MB each) directly in Teams messages. Supported formats include documents, images, and spreadsheets.

File Attachments on the Prompt API

The Prompt API now supports file attachments in addition to plain text. The workflow mirrors message attachments in conversations: (1) call the API to obtain a signed upload URL, (2) upload the document to Google Cloud Storage using the signed URL, and (3) attach the uploaded file to the prompt when creating or sending it by passing the returned storagePath in body.files.

Improved Country Selection

The country dropdown in Live Chat → Geographic Restrictions is now sorted A–Z with keyboard jump support, making regional blocking easier to configure.

Geographic Restrictions Behavior Fixes

Live Chat now shows a clear warning when a restricted user tries to send a message, and the chat no longer appears active while blocked. Copilot is unaffected — internal conversations are created normally regardless of region.

Auto-Assignment for Escalation

The Escalation Skill supports a default assignee — escalated conversations can be automatically assigned to a specific admin instead of left unassigned.

Escalation Webhook Payload

Escalation webhooks now include the full conversation payload, not just the form submission, so SIEM and downstream security systems receive complete context.

New Alerts Tab for Escalation

An Alerts tab has been added to the Escalation Skill to improve visibility into triggered events, aligning the UI with the Auditor Skill.

Notification Metadata Fix

Metadata collected from the Live Chat form is now properly passed in admin notifications, ensuring admins receive complete context on every alert.

Legacy Notifications Removed

The 'Notify on Auto-Archive' option and legacy email notifications have been removed from the Notification Skill to simplify configuration and reduce alert fatigue.

Auditor Skill Enhancements

Continued refinements to the PII and Hack Auditor engines improve detection accuracy and reduce false positives.

New Live Chat version / migration

A larger Live Chat redesign and migration was discussed as close to release and production deployment.

Live Chat background image customization

Upload and delete background images for the chat widget. Configure background image and background color by light/dark theme. Background image covers and scales within the widget. Color mask/fade uses the configured background color.

Live Chat templates / standard template setting

New template configuration was shown in Live Chat settings.

Live Chat after-hours / unavailable message webhook

Instead of storing deferred messages locally and sending later, after-hours messages are sent to a webhook. Supports sending multiple after-hours messages.

Live Chat limited-date availability

Live Chat availability can now be configured by specific dates, not just times.

Live Chat webhook payload now includes embedded page URL and user IP

Conversation metadata captures where the chat is embedded and the user IP.

Live Chat buttons: improved regex appearance logic

Button visibility conditions can parse assistant responses and manual assistant messages, not just user input.

Escalation / button behavior improvements

Discussion around using escalation logic to trigger buttons. Regex checking both user message and AI response. Proposed improvement: escalation auto-mode should also parse AI answer, not only user question.

Inline / mid-conversation forms

A form can appear inside a conversation based on similar appearance conditions as buttons. Use case: user says they want to register, and a form appears for event registration.

Conversation forms / user information forms

Forms in Live Chat for collecting user or conversation info. Added validation for maximum string length.

500-character validation on custom form fields

Frontend and backend validation added to prevent very long input strings in user and conversation forms.

Live Chat CSV/table export

Tables can be copied or downloaded as CSV in Live Chat.

Widget fixes

Issues found in widgets have been fixed.

Chat SDK async command support

SDK commands such as opening/closing chat, setting users/context, and sending messages can now be awaited using native JavaScript promises.

Prompting / enhanced prompting skill

New Prompting skill. Clients can activate the skill and override default prompts at the agent level. User message is transformed and enhanced before being sent.

Prompting toggle in Copilot

Copilot input includes a toggle/control for enhanced prompting.

Force prompting setting

Admins can force prompting to always be used.

Hide prompting toggle setting

Admins can hide the prompting control from users while still using prompting behind the scenes.

View enhanced/transformed prompt

Users and admins can inspect the transformed prompt that was actually sent. Discussed UI options: icon, modal, status pill, dropdown, or subtle prompt-enhanced indicator.

Prompting state persistence via OpenAI background processing

Prompt API improved to use OpenAI background processing and response IDs, storing state in Redis so Kubernetes pod restarts do not lose long-running prompt state.

GPT-5.5 model added

Latest GPT-5.5 model was added to the application.

GPT-5.4 Nano for Optimize with AI

Optimize with AI and completion API updated to GPT-5.4 Nano.

Formatted Copilot message downloads

Downloaded Copilot messages can render Markdown as formatted documents rather than raw Markdown.

Word/PDF/other document export improvements

Markdown now exports into cleaner Word/PDF-style documents.

Copy/download tables as CSV

Tables in Copilot can be copied and downloaded as CSV.

Increase Copilot attachment limit

Copilot file attachments increased from 4 files to 20 files.

Sticky save button for dirty forms

UI improvement so save button remains visible when a form has unsaved changes.

Copilot reskin / Launchpad core product reskin

Ongoing work to reskin Copilot and Launchpad.

New skill type: Prompting

Prompting appears as a skill in the skill list.

Frontend handling for new skill mappings

Fix for cached frontend versions failing to render newly added backend skills.

Regex generation / Optimize with AI for regex fields

Proposed ability to type a natural-language description and have AI generate the regex for button appearance conditions.

Computer skill

New computer skill. Configuration was mostly built; Manus API integration into message processing was still needed.

MCP skill OAuth

Pull request for MCP skill OAuth created; under review.

Custom Twilio API key logic

Custom Twilio API key logic implemented; still in review.

Function skill now receives conversation ID

Conversation ID added into function skill metadata/payload.

Function/API file attachment support discussion

Proposed support for passing file IDs and multiple files into prompts through external API, especially for code interpreter-style workflows.

Agent-to-agent communication

Agents can delegate questions to other agents, likely implemented as function-call-style orchestration. Streaming and proxying events between agents was called out as the hard part.

Task agent / deep-research style workflow

Prototype direction: prompt expansion, query multiple raia agents, query MCPs, optionally send to Manus/computer/code interpreter, then deliver output through Slack/email.

Scheduled task-style Copilot workflow

Concept where a user can schedule or run a background task through Copilot-like UI.

Agent-level usage tab

Owners and admins can see a Usage tab on an agent.

Agent-level usage limits

Admins can set limits for tokens, SMS, emails, and WhatsApp/WAPI minutes at the agent level.

Usage enforcement in Copilot and Live Chat

If an agent hits its configured limit, Copilot and Live Chat block further sends for that agent while other agents still work.

Delete/reset agent limits

Admins can remove the configured agent-level limits.

Future org/user-level limits

Next step discussed: organization-level and user-level token limits, especially for Copilot.

Updated quota/resource management

Database and quota recalculation improvements were discussed, including daily cron behavior and reduced resource issues.

License key registration fix

Users can register via license key again after a Supabase/wrong-ID issue was fixed.

Assigned user contact info in Escalation and Conversation APIs

API responses include assigned user information such as ID, name, avatar and later contact details.

Conversation assignee metadata

Conversation metadata includes assigned user information.

Agent statistics API filters

Agent statistics endpoints can fetch/filter by user ID, foreign key ID, conversation user ID, etc.

External API batch/vector-store improvements discussed

Proposed API to upload a group of file IDs to an agent/vector store instead of one-by-one processing.

Batch file/vector-store handling for OpenAI rate limits

OpenAI 429s were observed during bulk file uploads; timeouts and batch processing were discussed.

Vector store upload status tracking

File upload status stored in the database to prevent duplicate vector-store uploads.

Support for OpenAI file IDs vs vector-store files

Discussion around uploading files first, then using file IDs for vector stores or attaching files directly to prompts/code interpreter.

Document security permission update

Organization owners can manage document security settings, not just agent owners.

Super Admin users table improvements

Delete users or change roles directly from Super Admin user table without impersonating.

System prompt library in Super Admin

Prompts for things like agent descriptions, disclaimers, and optimization are managed in the Super Admin prompt library.

Custom prompt for background-image generation

Discussion around having a Super Admin-configured prompt used when generating background images.

Private agent permission update

Copilot users can be invited into private agents.

Impersonation used for org owner/admin security management

Related to managing document security settings as an org owner.

Region selector on login/sign-up

Login and sign-up screen has a region dropdown for US Central, US West, EU, etc.

EU OpenAI project / regional OpenAI routing

Plan to route EU server/projects to EU OpenAI project. Legacy customers may stay on existing project until vector stores are recreated/moved.

Organization-level API key approach for OpenAI region migration

Current API key can be saved as org-level key for existing orgs; new orgs use EU project key.

Microsoft Entra / Active Directory login

Client-specific Microsoft Entra / AD login discussed. Open question: separate login page, slug-based routing, or separate frontend deployment.

Apple / Google / Microsoft login already supported

Mentioned as existing common login providers while discussing Entra.

Cloud storage abstraction

Common storage interface with different implementations because Google Cloud/Azure do not fully support all S3 methods.

Support for Google Cloud Storage, S3, and MinIO

Cloud storage migration supports Google Cloud, S3, and MinIO, including Azure/self-hosted style deployments.

Queue/message broker abstraction

Planned common queue interface/connectors for different message brokers/systems.

RabbitMQ to replace/reduce Google Pub/Sub dependency

Discussed as part of making the platform distributable as Docker images without cloud-provider dependency.

Docker/self-hosted distribution foundation

Storage and queue abstraction work supports deployability outside Google Cloud.

Supabase/Lovable portability discussion

Discussed how to move Lovable/Supabase apps into a more internal/self-hosted stack.

Sentry profiling / request tracing

Added and improved Sentry profiling to collect request statistics and performance traces.

Sentry noise reduction

Scanner and scraper 404s filtered out to reduce Sentry usage/limit impact.

Grafana health-check log cleanup

Kubernetes health-check logs removed from Grafana noise.

Database query/index improvements

SQL queries and indexes updated to reduce CPU/memory pressure.

Quota recalculation performance improvements

Quota and resource management improved; daily midnight recalculation spike discussed.

Scoring batch-processing fix

Incorrect promise-based batching fixed with map_limit, intended to reduce Kubernetes SIGTERM, memory, and connection problems.

Database replication/copy process concerns

Large copy commands were causing memory/database load; batching and read-replica usage discussed.

Increase database connections

Discussed as possible mitigation for database spikes.

SMS emoji / empty OpenAI response handling

Fix for cases where OpenAI returns empty response, especially SMS messages containing emoji.

Backend/frontend dependency upgrades

Libraries and packages updated across backend. Security-related package updates completed.

Node.js LTS migration

Frontend and backend migrated to latest LTS Node.js version.

Sentry frontend/backend configuration improvements

Better handling of frontend and backend Sentry logs.

Button can load a form

Suggested as a preferred approach for showing forms from conversation interactions.

Prompt-based button appearance condition

Discussed but not clearly approved; concern was cost/overhead and over-triggering.

Function action to trigger button appearance

Discussed as an alternative to regex/prompt-based appearance logic.

Escalation without changing conversation state

Discussed because escalation-like logic may be used to show options/buttons without truly escalating.

Support-options buttons in Live Chat

Example: user asks what are my support options and multiple buttons appear.

Image crop modal for Live Chat backgrounds

Suggested as a nice future improvement so users can crop background images.

Batch upload UX for folders

Suggested UI where users drop a folder and get prompted to automatically upload documents to vector store.

OpenAI file-batch API usage

Discussed using OpenAI file batches to improve handling of hundreds of files.

Code interpreter file passthrough

Support for attaching one or multiple files to a prompt without vector-storing them.

MCP/connectors in Copilot tasks

Future Copilot workflows may connect to Slack, Gmail, and other MCP servers for actions and data retrieval.

Post output to Slack / email output

Prototype included generating a document/PDF and posting to Slack or emailing it.

TOTP MFA Enforcement

Fixed an issue where users could bypass enforced TOTP multi-factor authentication by switching back to SMS-based 2FA. Organization-level MFA policies are now consistently enforced.

Enhanced API Key Management for External APIs

Refactored API key management to support multiple keys at both the organization and API skill levels. Added expiration options (TTL or fixed date), key status handling (Active, Expired, Revoked), and improved overall security. Existing keys remain fully supported to ensure backward compatibility.

Training Documents Access Restriction

Introduced a new security setting allowing restriction of training document downloads to the agent owner only. This enhances control over sensitive data stored in the Vector Store.

GPT-5.4 Model Integration

The GPT-5.4 model has been integrated into the platform. Analytical capabilities have been expanded, allowing the model to be selected and utilized within AI agents for complex reasoning and improved response accuracy.

Manual Vector Store ID Configuration

The ability to edit the Vector Store ID for individual agents has been implemented. This feature allows multiple agents to be pointed to the same knowledge base, enabling shared data access while streamlining the management of vector storage across different agent configurations.

Expanded File Format Support

Support for the most commonly used file formats, including PDF, DOCX, XLSX, and CSV, has been implemented across Copilot, Live Chat, and Email Skill. A new conversion pipeline has been introduced to process these documents into AI-friendly formats before they are stored in the Vector Store.

Archived Conversations Visibility and Notifications Cleanup

A Show Archived filter has been added to the Copilot conversation list, allowing archived sessions to be viewed alongside active ones.

Expanded System Event Messages in Conversation UI

Support for muted system messages has been extended within conversation transcripts for both Live Chat and Copilot. By incorporating a broader range of system events into the interface, the tracking of user actions and the restoration of activity logs have been made more transparent and efficient for administrative monitoring.

Optimize UI of Live Chat Settings Panel

The Live Chat settings interface has been redesigned to improve navigation and clarity. Existing configurations have been reorganized into clearly defined tabs and application-specific sections, complemented by the introduction of accordion UI components to manage high-density settings and reduce visual clutter.

Security Vulnerability Mitigation for Image Uploads

A critical Cross-Site Scripting (XSS) vulnerability related to SVG file uploads for Agent logos has been resolved. Sanitization and validation measures have been implemented to prevent the execution of malicious scripts within the platform.

Added Auto-Assignment Configuration for Escalation Skill

Escalation Skill now supports configuring a default assignee for each escalation type. When an escalation is triggered, the conversation can automatically be assigned to the specified admin instead of remaining unassigned.

Added Option to Disable Live Chat Access

A new configuration option allows Live Chat access to be disabled while keeping the agent available through Copilot. This helps prevent direct access via the Live Chat link when agents are intended to be used only within Copilot, improving access control and reducing potential security risks.

Added Control for File Links in Copilot Annotations

A new Copilot setting allows administrators to enable or disable file links (hyperlinks) in document annotations. This provides greater control over document access, helping organizations prevent users from downloading or accessing underlying training files when annotations are displayed.

Improved Refresh Token Handling

Refresh token logic has been reviewed and updated to ensure more reliable session renewal and authentication stability. This improvement helps prevent unexpected authentication interruptions and ensures tokens are refreshed correctly during active user sessions.

Standardized Email Templates for Consistent Branding

Introduced a unified structure and styling standard for all system-generated email templates to ensure a consistent user experience and alignment with organization branding. This update standardizes elements such as headers, footers, greetings, layout spacing, and the use of organization logos or names. It also ensures that email templates properly reflect organization branding settings where applicable.

Fixed Validation Logic for Optional Fields in Live Chat Pre-Chat Form

Corrected validation behavior in the Live Chat pre-chat form where fields configured as Not Required still prevented users from starting a chat if left empty. The Start Chat button is now enabled as long as all required fields are completed, ensuring the form behavior correctly matches the admin configuration for optional fields.

Fixed Inconsistent Authors in Copilot Activity Log

Resolved an issue where activity entries in the Copilot Activity Log could display inconsistent or incorrect authors for certain actions. The log now consistently records and displays the correct author for each activity, improving traceability and audit accuracy.

Fixed Security Vulnerability in Signup Flow

Addressed a security vulnerability in the signup process related to email hyperlink injection, which could potentially lead to unauthorized account access. Input validation and sanitization mechanisms have been strengthened to prevent malicious link execution and protect user accounts from potential takeover attempts.