Install

Create a new AI tool definition in a project. The schema should be a raw JSON Schema object with type, properties, and required fields (e.g. {"type": "object", "properties": {...}}). Do NOT use the OpenAI function calling wrapper format. After creation, attach the tool to a variation using update-ai-config-variation.

Get a single AI tool definition including its full schema. Use to inspect a tool's parameters before attaching it to an AI Config variation.

List AI tool definitions in a project. Returns each tool's key, description, and schema. Tools are attached to AI Config variations to give models function-calling capabilities.

Add or remove specific contexts from individual AI Config targeting in an environment. Individual targets are the highest priority and override all rules. Supported kinds: addTargets, removeTargets, clearTargets, replaceTargets. Each instruction takes a 'variationKey' set to either the variation key (from get-ai-config) or the variation name (from get-ai-config-targeting); the tool resolves either to the internal variation _id before patching.

Update the default (fallthrough) rule for an AI Config in an environment. Set a percentage rollout across variations, or serve a single variation to all unmatched contexts. Weights must sum to 100. Use human-friendly percentages (e.g., 80 for 80%). Accepts a variation key (from get-ai-config) or variation name (from get-ai-config-targeting); the tool resolves either to the internal variation _id (UUID) before patching.

Add, remove, or modify custom targeting rules for an AI Config in an environment. Rules are evaluated top-to-bottom; first matching rule wins. Supported kinds: addRule, removeRule, addClauses, removeClauses, reorderRules, replaceRules, updateRuleDescription, addValuesToClause, removeValuesFromClause, updateClause. Use get-ai-config-targeting first to obtain ruleId, clauseId, and variationId values referenced by these instructions. If the environment requires approval, the response includes requiresApproval: true and an approvalUrl instead of executing.

Read the targeting configuration for an AI Config in a specific environment. Returns variations (with their _id UUIDs and names), individual targets, custom rules, fallthrough (default rule), and off variation. The variation name returned here can be passed as 'variationKey' to update-ai-config-targeting-rules, update-ai-config-rollout, and update-ai-config-individual-targets. Alternatively, use get-ai-config to obtain the variation's slug key.

Clone an existing AI Config variation with selective overrides. Reads the source variation, applies any provided overrides (model, instructions, messages, parameters, tools), and creates a new variation. Returns both the source and created variation so you can compare the diff. Use this for A/B experimentation: change one thing at a time while keeping everything else constant.

Permanently delete an AI Config variation. THIS IS IRREVERSIBLE. Requires confirm=true to execute.

Update an AI Config variation's model, instructions/messages, parameters, or attached tools. All fields are optional: only provided fields are updated. To attach tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool). Pass an empty tools array to detach all tools.

Create a variation for an AI Config. A variation defines the model, prompts, parameters, and tools. modelConfigKey must be in Provider.model-id format (e.g. OpenAI.gpt-4o, Anthropic.claude-sonnet-4-5) for models to display correctly in the UI. Agent-mode configs use 'instructions' (a string); completion-mode configs use 'messages' (an array of {role, content} objects). To attach AI tools, pass the 'tools' array with {key, version} entries (create tools first with create-ai-tool).

Health check for an AI Config. Detects common issues: missing models (NO MODEL in UI), missing prompts, orphaned tool references, and empty configs with no variations. Returns a health verdict (healthy, warning, unhealthy) with specific issues and per-variation summaries. Run before updating or experimenting with a config.

Check an AI Config's lifecycle status across all environments. Returns per-environment state (active, inactive, new, launched) and whether targeting is on, plus a summary of which environments the config is active, inactive, or launched in. Useful for understanding where a config is currently being served before making changes.

Create an AI Config with its first variation in one step. This is the recommended way to set up a new AI Config: it creates the config, adds a variation with model and prompts, and verifies everything is configured correctly. Returns the full config detail with variation. To attach AI tools, pass the 'tools' array with {key, version} entries. Use create-ai-config + create-ai-config-variation separately only when you need more control.

Permanently delete an AI Config. THIS IS IRREVERSIBLE. Requires confirm=true to execute. Prefer archiving (update-ai-config with archived: true) when possible.

Update an AI Config's metadata: name, description, tags, or archive status. Does NOT modify variations: use update-ai-config-variation for model, prompt, or parameter changes. Set archived: true to archive (reversible).

Create a new AI Config in a project. This creates the config shell: use create-ai-config-variation next to add a model, prompts, and parameters. Mode determines whether variations use 'instructions' (agent) or 'messages' (completion).

Get detailed configuration for a single AI Config including all its variations. Each variation includes its model, instructions or messages, parameters, and attached tools.

Search and browse AI Configs in a project. Returns a paginated list with key, name, mode (agent or completion), tags, and variation count. Use query to search by name or key.