You can create Celigo AI agents that utilize AI models to process each record within your flow. For every record, the Celigo platform sends the mapped input data to the Celigo AI agent, which then provides a standardized response that can be mapped for subsequent steps in the flow.
You can add Celigo AI agents to your flows as an import, and preview and validate the agent before using it in Production. Your Celigo AI agent can:
-
Execute tasks by providing it instructions
-
Integrate with MCP tools for action enablement
-
Return a consistent response envelope that downstream steps can map as:
-
Text
-
Structured JSON
-
Blob
-
-
Execute the following import components:
-
preMap and postMap hooks
-
Standard error handling and run behavior
When your flow runs, the Celigo AI agent has the same order of operations as an import step. The platform reads the incoming records and processes them one at a time. For each record, any configured preMap hooks run first, followed by Mapper 2.0 mappings that prepare the input for the agent. The agent then runs using the selected model and settings. After the agent completes, any postMap hook is invoked, and the step produces a standard response that you can map to downstream steps. All activity is captured through the platform’s existing logs, metrics, and audit trails.
Add a new import model type named Celigo AI agent that executes per record with standard import semantics, delegating AI execution to the agent runtime, and returning a standard response envelope suitable for downstream mapping.
-
To create your own Celigo AI agent as an import model type, navigate to AI studio → AI agent → Create AI agent.
If you have previously created an agent, click + Create AI agent at the upper right of the page.
-
Alternatively, you can add an AI agent while working in Flow builder. From the left navigation menu, click Build → Flow Builder → click the + icon and select Add AI agent.
Go to AI studio → AI agents to create or manage your agents and review activity.
The main dashboard provides a comprehensive overview and management interface for your agent. This central hub allows you to quickly assess the status and key properties of all configured agents.
-
Name/Description – Displays the agent name
-
Last updated – Sort by newest or oldest
-
Actions – Click the overflow (...) menu for context-sensitive choices
Model selection controls which AI models your agent or guardrail can use and how those models run in a flow or API. It ensures that executions run under the correct account, respect model capabilities, and remain governable as models evolve or are retired.
You can select models from a Celigo-provided OpenAI list or from a bring-your-own-key (BYOK) OpenAI connection. The platform enforces all capability, policy, and lifecycle rules automatically so you don’t have to manage them manually.
When you add an AI agent to a flow, the model determines output quality, performance, cost, and supported features. By controlling model selection centrally, you ensure:
-
Only approved and supported models are used
-
Inputs, outputs, and advanced settings stay compatible
-
Runs draw from the correct quota and concurrency limits
-
Retired or disabled models cannot be used accidentally
When you configure an AI agent or guardrail, you choose the model source first.
-
Celigo AI: You can select from a curated list of models managed by Celigo: These models run under a Celigo-provided enterprise-level account.
-
OpenAI – gpt-5, gpt-5-pro, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4.1-mini (default), and gpt-4.1-nano
-
Gemini – gemini-2.5-pro, gemini-2.5-flash-lite, gemini-2.5-flash, and gemini-2.5-flash-image
-
-
BYOK: You attach your own OpenAI or Gemini connector. Celigo automatically lists all models compatible and accessible on that connection.
Service tier options (auto, default, priority) are available and control how requests consume capacity on your connection.
Important
Only OpenAI connections are allowed for BYOK.
When selecting a model, balance quality, speed, and cost based on your integration needs:
-
Pro: Highest quality and accuracy, though typically slower and more expensive. Choose for complex or high-risk tasks where correctness is critical.
-
Standard: Recommended default. Balanced quality, performance, and cost for most integration scenarios.
-
Mini: Faster and lower cost. Suitable for routine or high-volume tasks; may be less reliable for complex reasoning.
-
Nano: Fastest and lowest cost. Best for simple tasks such as classification or extraction. Not recommended for reasoning-heavy workloads.
If a model becomes unavailable due to provider or policy changes, the platform prevents further saves that reference it and fails fast at runtime with a precise message and guidance.
Warning
If you attempt to access a feature the selected model does not support, the platform blocks the configuration or runs to protect your flows from unpredictable AI behavior in production.