🎉 New features​

Serenity Chat as side panel​

Two new modes for the side panel have been added that can be customized through the Serenity* Chat Channel.

Integrated UI Side Panel: Use the chat component directly embedded in the UI of your webpage. By setting this property, the chat will be visible on the right side of the page, providing an expanded view for conversations.

Floating Side Panel: A floating chat that occupies the full height of the screen without compressing your own UI.

Integrated Side Panel

Model Catalogue​

See a full list of all the available AI Models in Serenity* AI Hub.

Email Skills​

AI Agents can send emails by adding the Email Skill. This allows for the creation of scenarios in which the agent can automate the sending of emails to different recipients.

The agent can determine whether it is applicable to send the email and can complete both the body and subject of the email. You can choose between using the default sender or integrating your own email provider.

Plugin configuration

Setting up agent behavior for sending emails

Interacting with the agent

Email sent to the specified recipients

Prompt Skill​

Enhance AI Agents with extra prompting capabilities. Prompt skills provide an additional prompt that can be executed by the agent if certain conditions are met within the conversation.

Defining the custom skill

Agent response based on the users requirement

---

🛠 Enhancements​

Advanced Knowledge Chunking​

A new knowledge strategy has been implemented to improve agents' knowledge retrieval.

Knowledge sections now contain an overlap between the previous and next sections, allowing for greater specificity and more contextual information. This provides additional context to enhance the agents' responses.

Both the main section and the overlapping sections can be edited for further refinement of knowledge searches.

---

🐛 Bug fixing​

• Improved internal and external links in the Serenity* Chat Component.
• Enhanced visualization of sections and page numbers in knowledge edits.
• Performance improvements on the Knowledge tab in the agent designer to avoid excessive calls for updated status.
• Meta tags are now set on demo pages when scraping external websites.
• The Serenity* Chat component now displays message timestamps as "time ago."
• Fixed the visualization of special characters in the Serenity Chat header.
• Agent logos can now be included in the Serenity Chat channel.
• Improved visualization of the chat component when no title is provided.
• Fixed the password recovery process for users registered with social login.

🎉 New features​

Create Agent from website​

This new feature allows for creating an expert assistant for your website just by providing the URL address.

Serena will train the AI Agent with information from your site and create a demo page for trying it out. The agent can be further customized by using the agent designer.

Channels​

Agents now support channels customizations. You can activate/inactivate a channel but maintain the configuration to re-enable it later.

Serenity* Chat​

This new channel allow you to fully customize the Serenity* Chat from the agent designer. Customizations defined in the agent designer can still be overwritten locally from the Serenity* Chat code snippet.

You can use the demo page to quickly see the changes applied using this channel.

Nexus​

When this channel is active, the agent will be available to use in Nexus.

Requires Nexus feature in suscription plan

WhatsApp integration [Beta]:​

Phone numbers can be whitelisted for chatting with the agent via WhatsApp. A same number can be registered in more than one agent. Users can close conversations and start new ones sending "EndConversation" to Serena.

Discord channel [coming soon]!​

🛠 Enhancements​

Demo page improvements​

Improved control of your demo page with direct access to useful features:

• Edit Agent
• Edit demo directly
• Export code snippets
• Share

Serena integration with behaviour​

The Serena Agent Creator has been enhanced to better integrate with user requirements. The behaviors specified by the user while using Serena are now mapped to the Personality Traits in the Agent Designer view.

Additionally, the Personality Traits and System Definition within the "Behavior" tab of the Agent Designer have been improved. The "Generate with AI" feature now makes a better use of the Personality Traits to create the System Definition.

Finally, manual changes made to the System Definition using the "Advanced Mode" can now be synced with the Personality Traits, ensuring coherence between both options.

🤖 New Embedding Models​

Open AI Text Embedding Small 3​

Highly efficient embedding model and provides a significant upgrade over its predecessor ada 002 at a lower price.

Open AI Text Embedding Large 3​

Open AI new next generation larger embedding model and creates embeddings with up to 3072 dimensions.

Mistral Embed​

State-of-the-art semantic for extracting representation of text extracts.

🐛 Bugs & minor improvements​

• Resolved issue with multiple customers for same tenant in stripe.
• Corrected generation of automatic invoices from auto balance recharge.
• Tenant currency defaults to Euro by default.
• Fixed localizations and unified texts formats.
• Changed color of badges in agent version grid for better contrast.
• Validation of exceeded agents now appears before entering a template avoiding the need to complete the form for the error to appear.
• OCR support for images as knowledge files
• Tenant currency is now required
• Automatic agent creator now maintains url when redirecting to Agent designer

🎉 New features​

Enhanced Onboarding Experience​

A new integrated onboarding feature has been introduced to facilitate users in navigating the platform effectively. This feature provides step-by-step guidance on how to utilize the platform and create the first agent with ease.

This enhancement aims to streamline the initial user experience, ensuring a smoother and more intuitive journey from the very start.

Agent Activation/Inactivation​

A new functionality has been introduced that allows for the activation and deactivation of agents directly from the agent grid. This feature provides enhanced flexibility in managing agents, enabling users to temporarily limit or restrict access as needed.

• Inactive Agents: Agents that are deactivated will not be editable or accessible via API calls until they are reactivated.
• Active Agents: Agents that remain active can be utilized normally through the agent designer, chat component, or API calls. It is important to note that agents can be activated up to the limit set by the subscription plan. This enhancement aims to provide better control over agent management and access, ensuring a more tailored experience for users.

Billing management​

A new section has been added under Settings, allowing users to access comprehensive billing information with ease.

Key functionalities include:

• Remaining Balance: View the current balance at a glance.
• Payment Method Management: Add credit cards, manage existing payment methods, and set a preferred payment method as default.
• Manual Credit Charging: Recharge the account balance manually as needed.
• Automatic Payments: Set up automatic payments to occur when the balance reaches a specified threshold.

All payment methods are securely managed through Stripe, ensuring a safe and reliable payment experience.

API Status​

A dedicated site has been introduced for users to check the status of the API. This feature provides real-time updates on API performance and availability, ensuring that users can stay informed about the operational status of the services. Access can be done directly through the nav bar

🛠 Enhancements​

Liquid expression on Agent Designer​

The functionality of liquid expressions in the Initial Bot Message, Personality, and System Description has been significantly updated. This enhancement introduces improved performance, a more intuitive user interface, and enhanced suggestions for users.

Key improvements include:

• Dynamic Suggestions: Users can now type '/' to open a suggestions menu, allowing for the direct creation or use of existing variables.
• Conditionals for Control Flow: The ability to insert conditionals has been added, enabling more sophisticated control flow within liquid expressions. These upgrades are designed to streamline the creation and management of bot messages, providing users with greater flexibility and efficiency.

Improved scroll in Serenity* Chat​

Several improvements have been made to the chat component to enhance user experience and usability:

• Improved Scroll to Bottom Feature: The automatic scrolling functionality has been refined. Scrolling will now stop just above the first lines of the agent's response, providing a more comfortable reading experience.

• New Scroll to Bottom Button: A dedicated scroll to bottom button has been introduced, facilitating easier navigation within the chat interface.

These updates are designed to ensure smoother interactions and a more enjoyable user experience within the chat environment.

Reprocess Knowledge​

A new capability has been introduced that allows for the reprocessing of knowledge. This feature enables users to revert knowledge back to its original state after modifications have been made, ensuring greater flexibility in knowledge management.

Additionally, websites can now be reprocessed to update their content based on newly scraped data. This enhancement ensures that users have access to the most current information, improving the overall accuracy and relevance of the knowledge base.

Credit on newly registered tenants​

Enjoy a 5 EUR credit when registering a new tenant in the platform. This credit can be used to execute agents.

Serenity* Chat theme customization​

The customization options for the Serenity* Chat have been significantly expanded. Users can now personalize the chat experience by setting a theme that includes:

• Color Customization: Change the colors of the header, user messages, conversation starters, and bot messages to match branding or personal preferences.
• Custom Icons: Add unique icons to further enhance the visual appeal of the chat interface.

🐛 Bug fixes​

• Resolved an issue with AI Proxy calls when the userIdentifier is null or undefined.
• Ensured that input parameter values are stored in the Agent Designer when an agent is saved.
• Fixed issues related to dates and subscription assignments in tenants when new users are added.
• Enabled access to agents for users registering through Google using an enterprise email.
• Addressed various general fixes and typos throughout the platform.
• Improved informational messages on the agent grid when no agents are displayed.
• Added the userIdentifier parameter in CURL export when required in agent definitions.
• Included code snippets in the AI Proxy Agent for enhanced usability.
• Enhanced styling and responsiveness in the AI Agents Grid and Sidebar.
• Introduced an agent type tag to templates for better organization.
• Improved Serena's interpretation of templates for more accurate responses.
• Enhanced live updates on conversation starters in the preview mode.
• Made improvements to the demo page for better performance on mobile devices.
• Organizations can now correctly change their preferred currency.
• Fixed an issue where line breaks in personality settings were ignored.
• Improved support for code blocks in Serenity Chat.

🎉 New features​

Introducing Serena​

Serena is an expert companion for creating AI Agents. It has the capabilities of generating a custom AI Agent based on user inputs in a chat, describing your application or need. Serena has the ability to decide which type of agent is best for the use cased described and creates all necesary configurations needed

Agent personality powered by AI​

Your agents personality is now simplified and powered by AI. Inside the agent designer go to the "Behaviour" tab to edit the agents personality. You can select from a variety of fields including Role, Tone of the conversation, Complexity. Upon confirmation an enhanced personality will be generated based on the atributes and additional information available on the agent. You can turn advanced mode to modify and taylor the generated personality for your specific needs.

Serenity* Star Home​

A new design of your home page provides easy access to usefull information in just one screen. From here you can:

• Start creating a new agent with an integrated chat with Serena
• See at a glance your most recently edited agents
• Quickly create an agent from a template
• Access useful resources and complementary information with direct links

Unified agent view​

Access all of your agents within a new view. This new view provides access to easy filtering for each type of agents, a search bar and a sorting filter by name, recently edited, newest and oldest.

---

🛠 Enhancements​

• Agent designer system description can now be used with up to 20000 characters
• When creating a new agent, Chat GPT 4o Mini is set by default so that you can quickly set up an start using a fast, inexpensive model out of the box without any additional configuration.

---

🤖 New Models​

Mistral Large 2​

Mistral Large 2 has a 128k context window and supports dozens of languages including French, German, Spanish, Italian, Portuguese, Arabic, Hindi, Russian, Chinese, Japanese, and Korean, along with 80+ coding languages including Python, Java, C, C++, JavaScript, and Bash.

Mistral NeMo​

A state-of-the-art 12B model with 128k context length, built in collaboration by Mistran and NVIDIA. Mistral NeMo offers a large context window of up to 128k tokens. Its reasoning, world knowledge, and coding accuracy are state-of-the-art in its size category.

Mistral Mamba​

Mamba2 language model specialised in code generation. Mamba models offer the advantage of linear time inference and the theoretical ability to model sequences of infinite length. It allows users to engage with the model extensively with quick responses, irrespective of the input length. This efficiency is especially relevant for code productivity use cases

---

🐛 Bug fixes​

• Improved handling of knowledge files with string chains in the format {{}}
• Added a default background image on assistant demo page if none is provided
• Added display icon and corrected localizations on knowledge editor.
• Fixed bug in cost manager dashboard that didn't reflected monthly percentage change
• When Requires user identifier is activated on agent designer execution on preview uses the current user avoiding validation error.

🎉 New features​

Conversation Starters​

Agent designer now supports Conversation starters for Conversational Agents. This will be used in the Serenity* Chat for providing suggestions to the end user. Within the Behaviour Tab, you can define a set of conversation starters and they will be automatically added to the agent as soon as you publish.

You can quickly test them using the preview.

Requires Serenity* Chat v. 2.6.0

Pop up Welcome Message​

Enhance user engagement in the Serenity* Chat by providing a customizable popup that will be displayed after a certain amount of time if no initial interaction was made with the agent. By default, the initial message of the agent is shown but the component is fully customizable, check Serenity* Chat for detailed explanations.

Requires Serenity* Chat v. 2.6.0

Knowledge Editor​

Added support for editing knowledge directly on the Agent Designer. You can edit or delete specific sections of your file for correcting or removing unnecesary information that is present in your files or webpages. Click the "Show sections" button on the knowledge file and you will be taken to the knowledge editor. All sections of the file will be listed and you can view or modify them. Each section that is modified will be flagged so as to track changes.

---

🛠 Enhancements​

Preview improvements on Agent Designer​

The preview component has an improved view and new fuctionalities.

• A refreshing look on the empty state provides conversation starters, Assistant name, and initial assistant message with live Updates.
• Improved support for different screen resolutions
• Improvements on message and parameter pane
• Restart conversation on conversational agents

Download volatile Knowledge from Serenity* Chat​

Files uploaded in the chat component for use by the assistant as volatile knowledge can now be seen and downloaded from the conversation to see the contents of the files or from the conversation instance

Plugins / Skills​

• Plugin tab is now renamed as Skills
• Added wizard for Agent Executor Plugin. This allows any agent to invoke an action from another agent. Just specify the agent you want to invoke.

• Better HTTP Request Plugin wizard with variable body capabilities

---

🤖 New Models​

Open AI's Chat GPT 4o-Mini​

GPT-4o mini enables a broad range of tasks with its low cost and latency, such as applications that chain or parallelize multiple model calls (e.g., calling multiple APIs), pass a large volume of context to the model (e.g., full code base or conversation history), or interact with customers through fast, real-time text responses (e.g., customer support chatbots). The model has a context window of 128K tokens, supports up to 16K output tokens per request, and has knowledge up to October 2023. Thanks to the improved tokenizer shared with GPT-4o, handling non-English text is now even more cost effective.

---

🐛 Bug fixes​

• Improved error message when message field is not completed on Agents Designer Preview.
• Now conversations start and end with the same version providing a consistency in the agents anwers.
• Improved tooltip hover/blur appearance on screens
• Fixed a bug that if you deleted a knowledge file and then uploaded the same one a validation error was shown.
• Localized texts in user roles
• Improved liquid rendering in initial bot message.
• Corrected bug in AI Proxy Agent that didn't allow for a change in the agent.
• Allow for non logged users to see the background image in the Demo page
• Improved error message feedback on Serenity* Chat