Output control determines how an AI agent returns data to your flow. Configure the output type to ensure the agent’s response is predictable, validated, and easy to map in downstream steps. You se...
Prerequisite: In Shopify, verify if the order status is fulfilled. When you run the NetSuite Fulfillment to Shopify Fulfillment Add flow, if the retry data has empty fulfillment_orders array and yo...
MCP prompts are reusable, server-defined message templates that resolve into a sequence of chat messages. You can use prompts to standardize how the model receives instructions and reuse that patt...
After configuring your tool input and output, you can incorporate lookups and imports into your tool. Lookups allow your tool to dynamically reference and retrieve critical data from connected sys...
MCP resources are read-only files from Celigo file storage that an MCP server exposes to your agent. When you add resources to an agent, the agent can read those files at runtime to ground its dec...
In Tool Builder, you can add branching to your tools to simplify condition-based routing and reduce complexity when working with multiple applications or endpoints. Branching decreases your effort...
A Celigo guardrail is an import-type flow step that evaluates each record against safety, compliance, or governance policies. For every record, it returns a structured JSON result with a determini...
Celigo provides powerful error-handling features to help you manage and remediate issues efficiently in your Tools. With automated error logging and detailed error messages, you can quickly diagno...
Tools participate in ILM the same way flows and integrations do. Use ILM to move tool changes safely between environments, such as sandbox, staging, and production. Tool definitions, dependencies,...
Guardrails help you protect your flow by checking each record for safety and compliance as it runs. It works in real time and can be placed before or after an AI agent, or anywhere in the flow. Cr...