30. May 2025

Evoya AI Update: May 2025

A lot has happened, a lot has improved: from exciting workshops to new AI agents and more power for your data. Here are the highlights at a glance:

  • AI workshop with tarifsuisse: From theory to your own AI agent
  • Agent library: Preconfigured specialists for your workspace
  • Hybrid search: Find relevant answers even faster
  • Active Directory and LDAP: Central user administration
  • AI models: New Claude 4 models, Google Gemini 2.5 Flash, Qwen 3 and Perplexity Sonar – our Model Hub is now even more versatile

AI workshop with tarifsuisse - From theory to your own agent

Workshop with Tarifsuisse
tarifsuisse logo

30+ employees, two hours, one goal: understanding and directly applying AI.

After a compact introduction to the world of AI, all participants built their first AI agent – hands-on and without detours. To be continued – the next workshop will focus on specific business use cases.

Thanks to the tarifsuisse team for their trust and openness.

Do you want your team to understand and be able to use AI? Talk to us

Agent library - specialists at the touch of a button

library agents

Don’t fancy spending hours tinkering with agents? Our new library provides preconfigured AI agents for various applications. From diagram creation and build generators to a researcher that searches the web with Perplexity – everything is ready to use with just one click.

The best thing is that behind every agent is the language model that is best suited to the task at hand. Some models excel at research and web searches, others excel at logical thinking, precise translations, coding skills or mathematical expertise. Our platform combines these strengths specifically for each use case – so you always benefit from the optimal AI agent without having to deal with technical details.

Test our library and the agents yourself – experience how uncomplicated and powerful AI solutions are today! And if you have an agent idea of your own: Simply submit it in the top right-hand corner of the library – we look forward to your suggestions!

Hybrid search - find data instead of searching

hybrid search

We’ve all been there: the most important information is somewhere in documents, presentations or old reports. Searching is time-consuming and often tedious. New employees in particular often don’t even know that certain information exists.

To solve precisely this problem in an even more targeted way, we have further developed our search: We now combine classic full-text search with AI search – your agents will now find relevant answers even faster, more precisely and directly from your own sources. Whether PDF, Word, website or database.

Curious to see what this looks like in practice? We’ll show you live. Book a demo now

Active Directory & LDAP - Simple user management for companies

LDAP Ad

Thanks to the LDAP and Active Directory connection, you can integrate our platform seamlessly into your IT environment. You control access and users centrally – without additional effort.

AI model updates

AI Models

New language models are now available in the Model Hub – for even more flexibility and application options.

Newly added:

  • The latest Claude models from Anthropic: Opus 4 and Sonnet 4
  • Google Gemini 2.5 Flash – for fast, up-to-date answers
  • Open source power with Qwen 3 (235B and 32B) – which can run on your own servers
  • Perplexity Sonar – the compact model for efficient web research

Replaced or removed:

  • Gemma 2 27B is replaced by Gemma 3 27B
  • Qwen 2.5 70B is replaced by the faster Qwen 3 32B
  • No longer available: Gemini 1.5 Flash-8B, Gemini Flash 2.0, Llama 3.1 405B Instruct

As always, you can find all information on the available AI models in the Model Hub directly on the Evoya platform.

Curious to see what this looks like in practice? Start a free trial or book a demo – we will be happy to show you the feature!

Share:
Facebook
Pinterest
WhatsApp