Since the move to Amazon Bedrock, an administrator can choose, team by team, which AI models members can use in the Assistant, as well as the default model.
🛠️ Choosing a team's models
In the Admin tab, select the team you want to choose the models for.
Open the Features tab, then click Manage models in the MasterAgent section.
Check the models team members will be able to use.
Click Set as default next to the model to offer first.
Click Save.
🤖 Available models
Choose your model according to your needs: the more powerful it is, the better it handles complex tasks.
Model | Provider | Cost | Best for | Reasoning levels |
Claude Haiku 5.5 | Anthropic | € | The fastest and most cost-effective, for everyday tasks. | ✅ Yes |
Claude Sonnet 5.5 | Anthropic | €€ | The balance between performance, speed and cost. | ✅ Yes |
Claude Opus 5.5 | Anthropic | €€€ | Complex reasoning and long analyses across several documents. | ✅ Yes |
🧠 Enabling reasoning
Reasoning lets the Assistant analyze a request in more depth before answering. To make it available to a team:
In the Admin tab, select the team.
Open the Features tab.
Enable reasoning.
Once reasoning is enabled, team members can adjust its level (from "Faster" to "Smarter") in the Assistant, for all the models in the table above.
👉 What's next?
Team members will find the checked models directly in the Assistant. If reasoning is enabled, they can also adjust its level there to suit their request.
🔗 Learn more: Choosing your AI model and reasoning level
⚡ Key points
Models are chosen from the Admin tab, team by team.
A default model is offered to users, who can choose from the other checked models.
Reasoning is enabled in each team's Features tab.


