The AI tab in a Bloom’s configuration controls which underlying model answers student messages. You have two options: Smart Selection, which automatically uses the latest, best-performing models we have evaluated, and Manual Selection, which pins your Bloom to a specific provider and model. Smart Selection is the right choice for almost every Bloom. Manual Selection exists for advanced users with a specific reason to deviate, like a research project, a regulatory constraint, or a subject where you have tested and prefer one model’s style.
Who can change this
Two things gate the AI tab:
- Plan: your Teaching Space must be on the Growth or Enterprise plan. On Free and Educator Plus, Manual Selection is disabled for everyone and you will see this banner:
- Role: on a qualifying plan, the controls are still read-only for students and educators. You need to be a Bloom Manager, Super Admin, or Space Owner. Otherwise you will see this banner:
If you need to switch a model and do not have access, either upgrade the plan (Space Owners only) or ask a Space Owner or Bloom manager to make the change for you.
Step 1: Open the AI tab
From Manage Blooms, click into the Bloom you want to configure. In the configuration tab strip, click the AI tab. You will see two large cards stacked vertically: Smart Selection on top, marked with a green Recommended pill, and Manual Selection below.
Step 2: Use Smart Selection (recommended)
Smart Selection is the default for new Blooms. When it is active, Bloom routes chat messages through the strongest model we have validated for general teaching tasks. The card names the models currently in rotation, in a line that begins:
The benefits listed on the card:
- Auto-updated to newest models: when we promote a new frontier model, every Bloom on Smart Selection moves with us. You do not need to revisit this page.
- Optimized for safety and performance: the rotation is paired with our content moderation stack and tuned for educational dialogue.
If you change nothing else on this tab, you will get a good experience. Most Blooms (including the ones on our paid pilot programs) leave this on.
Step 3: Switch to Manual Selection
Click the Manual Selection card to expand it. Two dropdowns appear: AI Provider and AI Model. Once you switch off Smart Selection, your Bloom will not change models until you come back here and update them.
AI Provider
The provider list is grouped by the underlying API:
- Azure: Microsoft’s Azure OpenAI deployments. This is the default for new manual configurations and offers the broadest model range.
- OpenAI: direct OpenAI API. Same model family as Azure but routed through OpenAI’s own endpoints.
- Google: Gemini models, spanning the Pro and Flash tiers.
Switching providers resets the model dropdown, so pick a provider first, then a model.
AI Model
Each provider exposes a curated list, with the current default pre-selected at the top. Alongside it you will usually find one or two previous generations of the same family, kept available so a Bloom that was tuned against an older model can stay on it. Models that are not intended for student chat, such as the small models behind classification and titling, are filtered out of the menu, so the list you see is the list you can safely pick.
We do not list the exact model names here, because they change whenever we promote a newer model. The dropdown in your Bloom is the authoritative list.
Step 4: Choosing a model
There is no universally best model, and the specific names shift over time. What stays stable is the tier a model sits in, so choose by tier:
- The default Azure chat model suits general subjects. It is whatever sits at the top of the Azure list, handles long context, follows instructions tightly, and is the same model Smart Selection uses for chat.
- A Gemini Pro tier model suits STEM Blooms with heavy mathematical or code-heavy content. The Pro tier is also what Deep Think reaches for on Google when reasoning mode is invoked.
- A Gemini Flash tier model suits cases where latency matters more than depth, for example a busy intro course where students want quick clarifications.
- Avoid older or preview-tagged models for live student traffic. They are kept available for evaluation and migration but are not what we recommend for production.
Click Save at the bottom of the configuration page once you are happy. The change applies to the next message. Conversations already in progress continue on whatever model their in-flight request was already using.
Common issues
The whole tab is locked with a Lock icon
Either your Teaching Space is on Free or Educator Plus (Manual Selection requires Growth or Enterprise), or your role does not allow editing AI settings. Read the banner above the cards to see which one applies. To unlock it, upgrade the plan or ask a manager, super admin, or Space Owner to make the change.
The Save button does nothing or shows a validation error
If you toggled to Manual Selection but never picked a provider or model, the form will fail validation. Either pick a provider and model, or switch back to Smart Selection.
Manual Selection picked, but answers feel different to what I tested
Two things to check. First, Deep Think (when enabled by the student or educator on a message) swaps the chat model for a stronger reasoning model for that message only. Second, some background tasks, such as conversation titles, use small purpose-built models regardless of your chat model choice. Your chat model only governs the main conversational reply.
I want a model that is not in the dropdown
The list reflects what we have validated, deployed, and deemed safe for student traffic. If a model you want is missing, send us a request through the in-app feedback. We add new models to the rotation on a regular cadence.
What’s next
- Understand how the per-message reasoning model works → How Deep Think works
- See the full configuration tour → Configuration overview
- Open Bloom and tune a model now → Manage Blooms