githubEdit

brain-circuitAI

Flashback's AI layer combines AI LLM management with a flexible AI Policy system. You can securely configure multiple AI providers (OpenAI, Google Cloud's Gemini, Anthropic) per workspace, then govern their usage with natural-language policies scoped at organization, workspace, or repository level. Together, they give you centralized control over credentials, usage, compliance, and real-time enforcement of responsible AI behavior across your apps and repositories.

Reference Table

Category
Description

Configure and manage connections to external AI providers (e.g., OpenAI-compatible, cloud LLMs), validate credentials, and make these models available to workspaces and repositories under a unified interface.

Define and enforce natural-language governance rules (e.g., PII handling, security, content boundaries) with risk levels and actions (log, alert, block), scoped at organization, workspace, or repository level.

Create and manage scoped API keys that applications use to call AI endpoints via Flashback, controlling which LLM configurations and repositories they can access and how much usage they are allowed.

AI API Calls

The table below consolidates all AI-related endpoints across the three sub-categories.

AI LLM Management

Method
API Reference
Description

POST/ai/llm

Create a new AI LLM configuration.

GET/ai/llm

List all AI LLM configurations (with optional workspace filter).

GET/ai/llm/available

Get available configurations ready for use.

PUT/ai/llm/{id}

Update an existing AI LLM configuration.

DELETE/ai/llm/{id}

Delete an AI LLM configuration.

POST/ai/llm/{id}/validate

Validate an AI LLM configuration.

GET/ai/llm/stats

Get usage statistics for AI LLM configurations.

AI Policy

Method
API Reference
Description

POST/policy

Create a new AI policy.

PUT/policy/{policyId}

Update an existing policy.

GET/policy

List policies with optional filtering.

GET/policy/{policyId}

Get detailed information about a specific policy.

GET/policy/violations

Retrieve policy violations across AI operations.

GET/policy/{policyId}/violations

Retrieve all violations for a specific policy.

GET/policy/alerts

Retrieve all policy alerts with optional filtering.

GET/policy/{policyId}/alerts

Retrieve all alerts for a specific policy.

DELETE/policy/{policyId}

Permanently delete an AI governance policy.

AI API Keys

Method
API Reference
Description

POST/repo/{repoId}/ai/apikey

Create a new AI API key for a repository.

PUT/repo/{repoId}/ai/apikey

Update an AI API key's properties.

GET/repo/{repoId}/ai/apikey

List all AI API keys for a repository.

DELETE/repo/{repoId}/ai/apikey/{apikeyId}

Delete an AI API key.

Last updated

Was this helpful?