AI Providers

codev can use an AI model you connect to power its AI features. You bring your own provider and key — configure a provider once and every AI feature can use it.

You configure AI providers under Settings > Organization > Integrations (the AI Providers category). Only organization owners can manage them.

AI features are exclusive to sfp-pro. There is no flxbl-managed AI — codev only calls the provider you connect, with your own key. If you don't connect one (or set a project to None), AI features are simply skipped.

What AI powers

Connecting a provider enables three AI features. In codev they surface like this:

• AI Insight reports — on-demand code and architecture analysis for a package or domain. Open the Workspace Explorer (or the Packages / Domains views), select a package or domain, and use the AI Insight tab's Generate Insight action. See AI Assisted Insight Report.
• AI architecture analysis — an architectural review of the changes in a pull request, run as the architecture analysis linter (enable it under a project's Analysis Settings). Results appear on the PR check. See AI Assisted Architecture Analysis.
• AI-assisted error analysis — when a pull request validation fails, codev asks your provider to explain it (likely root cause, severity and confidence, suggested fixes, prevention tips) and posts the result into the PR check. It runs automatically on failure and never blocks validation. See AI-Assisted Error Analysis.

In every case codev sends only the relevant context — the code for an insight report, or the failing output for error analysis — to the provider you connected, under your own key.

Supported providers

Provider	Recommended	What you provide
Anthropic (Claude)	⭐ Yes	An API key (sk-ant-…) from the Anthropic Console.
OpenAI	Yes	An API key (sk-…) from the OpenAI Platform.
Amazon Bedrock	Yes	AWS Region, Access Key ID, and Secret Access Key for an IAM user with the AmazonBedrockFullAccess policy.
GitHub Copilot	Yes	A GitHub token, for teams with an active Copilot subscription (model access enabled).

For provider-specific setup, default models, and how to verify a provider with sfp ai test, see Configuring LLM Providers.

Adding a provider

1. Go to Settings > Organization > Integrations and pick the provider under AI Providers.
2. Enter the credential for that provider (each form links to where to create it — the Anthropic Console, OpenAI Platform, GitHub developer settings, or the AWS IAM console).
3. Set Availability to Global (optionally marking it the default for AI) or to a specific project.
4. Click Add Integration.

Choosing which provider codev uses

The provider you connect here is the server-managed credential every AI feature draws from — in codev and in any pipeline connected to the same sfp server. codev resolves the provider for a project in this order:

1. The project's AI provider setting. During project setup you can pick an AI Provider — choose a provider, or None to disable AI for that project.
2. The default AI provider — a registered AI integration marked as the default for the AI category, used when a project hasn't chosen its own.
3. A global AI integration, if no default is set.

Data handling

When an AI feature runs, the relevant code or failing output is sent to the AI provider you connected, under your own account and key. Pick a provider that fits your organization's data policy, and set a project's AI provider to None to opt it out entirely.

Self-hosting

AI providers are connected the same way on a self-hosted instance — you supply your own keys. Credential resolution and configuration details (environment variables, config/ai-assist.yaml, and server-managed credentials) are covered in Configuring LLM Providers and the sfp server documentation.