AI Agent · Gemini
A Gemini-powered agent for large knowledge bases
Run your ChatFlo agent on Google's Gemini models. Gemini's large context window suits businesses whose answers live across long manuals, sprawling help centres, and dense product catalogues.
Can ChatFlo run my support agent on Gemini?
ChatFlo can run your support agent on Google's Gemini 2.5 Pro or Flash, grounded in your own website and documents. No Google Cloud account or API key is required; usage is included in your plan. Gemini's large context window makes it the usual pick when answers are spread across long manuals or large product catalogues.
Why Gemini
The one for very large knowledge bases.
Handles long source documents
Gemini's large context window means a lengthy manual or specification sheet can be reasoned over in one pass, rather than sliced into fragments that lose the thread.
Good on catalogue-shaped questions
Comparisons across many similar products — sizes, specs, compatibility — hold together well, which suits retailers with deep catalogues.
Flash for cost-sensitive volume
Gemini 2.5 Flash is the cheap, fast option for routine traffic, with Pro reserved for the conversations that actually need it.
Available models
The Google models you can select
Pick one in AI settings. Switching is a setting, not a migration — your training content, guardrails, and history stay where they are.
Gemini 2.5 Pro
Most capable, large context
Gemini 2.5 Flash
Fast and cheap for high volume
When another model is the better call
For strict adherence to a short, precisely-worded policy, Claude is usually the safer choice. For general-purpose support with no special document demands, GPT-4o remains the simpler default.
Point Gemini at your knowledge base
Upload your manuals and catalogue, pick Gemini in AI settings, and the agent starts answering from them.
Frequently asked questions
It is the same family of models, used differently. Google's app is a general assistant answering from the open web. ChatFlo runs Gemini against your content only, on your own channels, with citations and escalation rules — so it answers as your business rather than as a general assistant.
ChatFlo indexes your content and retrieves the relevant parts per question, so the size of your knowledge base is not capped by the model's context window. Gemini's larger window helps most when a single answer genuinely depends on a long stretch of one document, such as a technical manual.
No. ChatFlo runs the model for you on every paid plan — there is no separate Google account, billing relationship, or key to manage. Model usage is included in your plan.
Yes, from the AI settings screen, at any time. The model is a setting on your agent, not a plan tier — your training content, guardrails, tone, and conversation history are untouched by the switch, so you can A/B two models on the same setup.
No. Training is the same regardless of model: you point ChatFlo at your website, docs, and files, and it indexes them. The model only affects how answers are composed from that material — it never changes what the agent is allowed to draw on.
Other models
ChatFlo is not locked to one model vendor
Your agent runs on whichever of these you select, and you can change your mind without rebuilding anything.