Claid.ai connects to a Nagent workspace with an API key. Once it is connected, agents can call 14 Claid.ai actions, such as "Get Storage Details", "Update Connected Storage" and "List Connected Storages". Nothing is enabled on connect: each action is allowed one at a time, and an action with side effects runs or waits for a person according to the agent's level.
Every operation an agent can call against Claid.ai, with input parameters and output schema.
CLAID_AI_BACKGROUND_GENERATEGenerate AI-powered backgrounds for product images. Creates professional scenes with customizable backgrounds, lighting, and composition. Use cases: - E-commerce product photography enhancement - Creating lifestyle scenes for product marketing - Generating consistent backgrounds across product catalogs - Adding realistic shadows and reflections Supports three generation modes: 1. Prompt-based: Describe the background in text (e.g., "minimalist white studio") 2. Template-based: Use a reference image to guide the style 3. Shadow/effect mode: Add shadows to transparent product images Returns temporary URLs (valid 24 hours) or saves to connected storage.
Input parameters
Scene generation settings including model, prompt, aspect ratio, and quality preferences.
Source product image URL and placement configuration (position, scale, rotation).
Optional output settings. If omitted, returns 4 PNG images with temporary URLs (valid 24h).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_BACKGROUND_REMOVERemove the background from images using Claid.ai's AI-powered background removal. Supports category hints (general, products, cars) for optimized removal, selective removal to keep specific objects, and optional clipping to crop to subject bounds. Returns a temporary URL to download the processed image with transparent or colored background.
Input parameters
URL or storage URI of the input image. Supported schemes: http(s):// or storage://.
Optional output destination or format settings. String endpoint or object with format.
Background removal operation settings.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_CLAID_STORAGE_DETAILSTool to retrieve details of a connected storage resource. Use when you have a storage ID and need to inspect its configuration before performing further operations.
Input parameters
ID of the storage resource to fetch
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_CREATE_STORAGETool to connect a storage resource. Use after you have bucket/folder details and credentials. E.g., to add a new AWS S3, GCS bucket, or public web folder for your image assets.
Input parameters
The storage name inside Claid
Type of storage connector
Connector-specific configuration
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_GENERATIVE_RESIZEExpand image canvas using AI-powered generative outpainting. This tool adjusts image aspect ratios by generating coherent background content to fill new canvas areas. Use it when you need to: - Change image aspect ratio for different platforms (e.g., square to landscape) - Extend an image's borders while maintaining visual consistency - Create zoom-out effects by expanding the scene in all directions The AI generates photorealistic content that matches the original image's style, lighting, and composition. Maximum output size is 16.78 MP.
Input parameters
URL of the source image. Accepts public HTTPS URLs or Claid storage URIs (e.g., 'storage://bucket/path/image.jpg').
Output destination as a storage URI string (e.g., 'storage://bucket/out.jpg') or OutputOptions object for detailed format settings. If omitted, a temporary URL valid for 24 hours is returned.
Pipeline describing the generative resize operation with target dimensions and outpaint fit mode.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_IMAGE_AI_EDITTool to submit an asynchronous AI-based image editing task. Use when you need text-driven edits on existing images and will poll for completion.
Input parameters
Publicly accessible URL of the source image (HTTP/HTTPS) or storage URI (storage://storage-name/path/image.jpg). Supported formats: JPEG, PNG, WEBP, AVIF, HEIC.
Output destination URI string or configuration object. If omitted, a temporary URL is returned.
AI editing options including prompt and generation parameters.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_IMAGE_EDIT_BATCHTool to process multiple images in batch asynchronously. Use when applying the same edits (resize, enhance, background removal, etc.) to many images at once. Accepts input from: - Cloud storage folders (with optional recursive processing) - Lists of public image URLs - Single public image URL Returns a batch job ID and result_url to poll for completion status and processed images. Requires billing capabilities on the Claid.ai account.
Input parameters
Image source(s) to process. Accepts: (1) ImageInputOptions object with 'source' (storage URL) and optional 'recursive' flag; (2) A single public image URL string (http/https); (3) A list of public image URLs. Example URLs: 'https://example.com/image.jpg' or 'storage://my_storage/folder/'
Output destination. Accepts: (1) Storage folder URL string like 'storage://my_storage/output/'; (2) Configuration object with 'format' (type: jpeg/png/webp/avif, quality: 1-100) and optional 'destination'. If omitted, processed images are stored temporarily with 24-hour public URLs.
Image editing operations to apply. Use nested dicts for each operation type: 'restorations' (polish, upscale, decompress), 'adjustments' (hdr, exposure, saturation, contrast, sharpness), 'background' (remove, color, blur), 'resizing' (width, height, fit: crop/cover/bounds/canvas/outpaint), 'privacy' (blur_plate). Example: {'restorations': {'polish': true}} or {'resizing': {'width': 800, 'fit': 'bounds'}}
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_IMAGE_GENERATEGenerate AI images from text prompts using Claid.ai. Creates 1024x1024 pixel images. Use when you need to create custom visuals, product mockups, or creative imagery from a description. Supports generating 1-4 images per request. Returns temporary URLs (valid 24h) or saves to connected cloud storage.
Input parameters
Detailed text description of the image to generate (3-1024 chars). Be specific for better results.
Storage URI for output folder (must end with '/'). If omitted, temporary URLs valid for 24 hours are returned.
Controls image generation behavior including count and prompt adherence.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_LICENSE_PLATE_BLURAutomatically detect and blur license plates in images for privacy compliance. Use this tool when you need to obscure vehicle registration plates in photos (e.g., for car marketplaces, real estate listings, or street photography). The AI automatically identifies and blurs all license plates in the image.
Input parameters
URL of the input image. Supported schemes: http(s):// or storage://; length 1–4096.
Optional output configuration. Can specify format settings (type: 'jpeg'\\|'png'\\|'webp'\\|'avif'\\|'tiff', quality: 1-100) and/or destination URI (e.g., 'storage://bucket/path/image.jpg'). If omitted, returns a temporary URL in JPEG format valid for 24 hours.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_PATCH_STORAGETool to update a connected storage's settings. Use when you need to change name, type, or parameters of an existing storage. Use after confirming the storage exists.
Input parameters
New display name for the storage
New type for the storage connector (web_folder, s3, or gcs)
Storage-type-specific parameters to update
Identifier of the storage to update
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_POLISH_IMAGEApplies AI-powered polish restoration to an image, sharpening and cleaning up while preserving the original structure. Ideal for enhancing upscaled images or removing AI artifacts. Note: Target image must not exceed 16 MP (megapixels).
Input parameters
URL or storage URI of the input image. Supported schemes: http(s):// or storage://; length must be between 1 and 4096 characters.
Optional output destination or format settings. Provide a storage URI string or an object with format settings. Defaults to JPEG if omitted.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_SMART_FRAMEPlace images on a canvas with specified dimensions and padding for consistent product photography framing. Ideal for e-commerce: standardizes product photos with uniform spacing and background colors. Use this when you need to add white space or colored borders around product images for marketplace listings.
Input parameters
URL of the input image. Supports publicly accessible http(s):// URLs or Claid storage URIs (storage://bucket/path).
Framing configuration including target canvas dimensions, padding around the subject, and optional background color.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_STORAGE_LISTTool to list connected storage resources. Use when you need to retrieve all storage connectors for your account.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
CLAID_AI_STORAGE_TYPESTool to retrieve available storage types. Use when you need to list supported storage connectors before uploading files.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
Agents can call 14 Claid.ai actions on Nagent, including "Get Storage Details", "Update Connected Storage" and "List Connected Storages". Get Storage Details: Retrieve details of a connected storage resource. Each action is listed on this page with its input parameters and its output.
Claid.ai connects with an API key, under your workspace's own connection. Nothing is enabled on connect: each action is allowed one at a time and can be scoped to the agents that need it.
Get Storage Details takes 1 required input: storage_id. It returns data, error and successful.