🎉 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 widget is fully customizable, check Chat Widget for detailed explanations.

Requires Chat Widget 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 widget 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