Agent shifts use an AI model to analyze code and generate changes. Before your team can
run agent shifts, you need to connect an AI provider and enable the models you want to
use.
Prerequisites
- Fleetshift setup
complete (webhooks connected)
- An Anthropic or OpenAI API key, an AWS account with access to Amazon Bedrock, or a
GCP project with access to Vertex AI
- Permission to update Portal settings (app settings or plugin settings, depending on the provider)
Fleetshift supports Anthropic, Amazon Bedrock, Google Vertex AI, and OpenAI as AI
providers. You can configure one or more — Anthropic, Bedrock, and Vertex AI power
Claude models, while OpenAI unlocks GPT and o-series models.
Anthropic
Amazon Bedrock
Google Vertex AI
OpenAI
Anthropic is configured through the AI Gateway in app settings.
- Go to
App Settings > AI Models.
- Under
Anthropic, enter your API key.
- Click
Save.
Once your Anthropic key is configured, the shift creation wizard enables
Claude Code and makes the Claude models available on your Anthropic account
selectable for agent shifts.The API key needs access to the models you plan to use. See the
Anthropic integration guide
for additional configuration details. Bedrock is configured as a Portal-wide AI provider in app settings.
- Go to
App Settings > AI Models.
- Under
Amazon Bedrock, select your credential source:
Default credentials uses the AWS credentials already configured in
App Settings > Integrations > AWS.Custom uses Bedrock-specific credentials. Enter the access key, secret key,
and region.
- Click
Save.
If you choose Default credentials, make sure your AWS integration already has an
access key and secret key configured under App Settings > Integrations > AWS.The AWS credentials need the following IAM permission: Vertex AI is configured in the Fleetshift plugin settings.
- Go to
Plugin Settings > Fleetshift.
- Under the AI section, enter your GCP project ID and region.
- Create a GCP service account in your project and provide its key JSON.
Fleetshift uses this identity when running AI shifts.
- Click
Save.
The GCP service account needs the following IAM role: OpenAI is configured through the AI Gateway in app settings.
- Go to
App Settings > AI Models.
- Under
OpenAI, enter your API key.
- Click
Save.
Once your OpenAI key is configured, the shift creation wizard enables
opencode — a multi-model agent harness that runs GPT and o-series models.
When you create a new shift, you’ll see opencode as a harness option alongside
Claude Code. Select opencode and pick a GPT model (GPT-5.5, GPT-4.1, etc.)
from the model dropdown.Both harness options are always visible in the wizard, but you can only select
a harness if its provider is configured. Without an OpenAI key, opencode is
visible but disabled — and vice versa for Claude Code without Anthropic, Bedrock,
or Vertex AI.The API key needs access to the models you plan to use. Check your
OpenAI account to confirm model
availability. Enable Claude models
Fleetshift agents are powered by Claude when using Anthropic, Amazon Bedrock, or Google
Vertex AI. For direct Anthropic access, models available to your API key are fetched
automatically. For Bedrock or Vertex AI, enable the Claude models you plan to use with
your chosen provider.
Amazon Bedrock
Google Vertex AI
- In the AWS Console, go to
Amazon Bedrock > Model access.
- Request access to the Claude models you want to make available.
- In the GCP Console, go to
Vertex AI > Model Garden.
- Enable the Claude models you want to make available.
Available models
You choose which model to use when creating each shift — this is not a global setting.
Claude models (Anthropic / Bedrock / Vertex AI)
OpenAI models (via opencode)
OpenAI models are available through the opencode harness. When you configure an
OpenAI API key in the AI Gateway, the shift creation wizard shows opencode as a harness
option. Select it and pick from the GPT models below.
If you have both OpenAI and Claude providers configured, you can switch
between them on an existing shift. Edit the shift’s model in the shift
configuration page, then re-run targets — useful for iterating on a prompt or
building on top of previous work with a different model.
Next step
You’re ready to create and run your first shift. 
