Google Gemini integrationIn development
Diagnose issues with Google Gemini, on your own key
The Google Gemini integration is in development. It is designed for teams that prefer Google's models: connect a Gemini API key, choose a model and let ROOKON send each issue's evidence to Gemini for analysis.
The problem
Your model choice shouldn't decide your tooling
Teams standardize on an AI provider for reasons of cost, policy or existing cloud relationships. A product that only works with one provider forces a trade-off that has nothing to do with the problem you are trying to solve.
- Tools hard-wired to a single model vendor
- Separate approvals for every new AI provider
- Recommendations that become unreadable after switching
- No record of which model produced which advice
Live demo 1 of 3
Connect your Gemini key safely
Save a sample Gemini key and see it encrypted, wrapped and reduced to a masked hint. Runs in your browser and sends nothing.
- Use the sample key
- Test the connection
rookon · settings · AI provider · Google Gemini
Simulated dataConnect Google GeminiIn development
Don’t paste a real key. This demo runs only in your browser and sends nothing. Use the sample key instead.
Envelope encryption
When you save a key:
- a fresh data key encrypts it (AES-256-GCM),
- a master key that never touches the database wraps the data key,
- only ciphertext and a masked hint are stored,
- the worker decrypts it for a single analysis request, then forgets it.
The API returns only maskedKey after saving, never the key itself, to anyone.
How ROOKON helps
What you get
Gemini API keys
The first version is designed for Gemini API keys. Support for Vertex AI credentials is under consideration based on customer demand.
Model selection
Pick the Gemini model available to your key; ROOKON confirms it works with a small validation request when you connect.
Provider-neutral history
Every recommendation records which provider and model produced it, and stays readable if you later switch providers.
Background processing
Analyses run in queued jobs, separate from your product's traffic and from ROOKON's own request handling.
Protected credentials
Your key is envelope-encrypted at rest, decrypted only in the worker during a request and never shown again after you save it.
Live demo 2 of 3
Pick a Gemini model per task
After connecting, choose which of your models diagnoses issues and which writes the code. Model names are examples: ROOKON lists the models your own key can use.
- Change the code generation model
- Set review revisions back to “Same as fallback”
rookon · workspace settings · AI models
Simulated dataConnected providers
Model names below are examples. In ROOKON the list is fetched from your provider account with your key.
| Task | Model | Est. per run |
|---|---|---|
Diagnosis A fast, inexpensive model is usually enough. | ~$0.022 | |
Code generation Pick your strongest coding model. This is where quality matters most. | ~$0.87 | |
Review revisions Defaults to your code generation model. | Uses Code generation: your-strongest-coding-model | ~$0.36 |
Marketing copy Defaults to your diagnosis model. | Uses Diagnosis: your-fast-model | ~$0.006 |
Support replies Defaults to your diagnosis model. | Uses Diagnosis: your-fast-model | ~$0.004 |
Content writing Defaults to your marketing copy model. | Uses Diagnosis: your-fast-model | ~$0.007 |
The model you pick for code generation writes every proposed change. Model routing is in development with the rest of ROOKON.
Setting up Gemini in ROOKON
- 01
Create a key
Generate a Gemini API key in your Google account for ROOKON's use.
- 02
Add it to ROOKON
An owner or admin saves the key and chooses a default model.
- 03
Pick your projects
Set Gemini as the provider for all projects or only some of them.
- 04
Review results
Recommendations appear on issues, labeled with the model that produced them.
Live demo 3 of 3
Cap what Gemini costs you
Set a monthly budget for analyses on your Gemini key and decide what runs automatically. Prices from the model picker above feed the estimate. Simulated.
rookon · workspace settings · AI budget
Simulated dataBilled by your AI provider, on your key. ROOKON stops before the cap.
Your model’s price per 1M tokens
Example prices. Check your provider’s current pricing for your model.
Simulated day 1 of 30
Live$0.00 of $15 this month
on trackprojected month-end $0.000 tokens0 automatic · 2 waiting
Detected issues (newest first)
- infoRarely used setting causes console warningday 1This issue is below the severity your autopilot mode analyzes automatically.
- infoImage without dimensions on /blogday 1This issue is below the severity your autopilot mode analyzes automatically.
Simulated month. Most impactful issues are analyzed first; ROOKON reserves the worst case before each call so a single analysis can’t push you over the cap.
Try: Pick a pricier diagnosis model above · Raise the cap
FAQ
Common questions
Is the Gemini integration available?
Not yet. It is in development, and this page will be updated when it is available.
Do you support Vertex AI?
The first version targets Gemini API keys. Vertex AI support is being evaluated; tell us if you need it.
Who is billed for Gemini usage?
Usage is billed by Google to the account that owns the key. ROOKON does not charge for model usage.
How do I rotate or remove my key?
Replace the key in ROOKON's AI settings at any time; the previous encrypted key is deleted. Revoking the key in your Google account stops all use immediately.
Use Gemini where it helps most
Sign up and connect your Gemini key in the setup journey.