What Is Agent Automation?
You can connect your favorite apps and services directly to your Custom AI Agents and enjoy a new level of personalized automation. The Agent action lets you embed AI intelligence at any point in your workflow — ask an agent a question, run a predefined command, and use the response in subsequent steps.
This means your automations are no longer limited to simple if-then logic. An AI agent can analyze data, draft content, classify information, or make decisions, and then pass the result to the next action in the chain. Agents can run any of the 15+ frontier models from OpenAI, Anthropic, Google, and leading open-source providers, use custom tools, tap project knowledge, or coordinate with an agent team.
Custom Agent Actions
Here are the actions you can use in your workflows:
| 🏷️ Field | 🔤 Description |
|---|---|
| (ACTION) Ask Agent | Uses a custom AI agent to respond to a query. |
| (ACTION) Run Agent Command | Uses a custom AI agent command. |
Agent Automation Settings
Connector options give you full control over Agent automations:
Action: Ask Agent
| 🏷️ Field | 🔤 Description |
|---|---|
| AGENT | Choose the AI agent that you will be asking a question. This field is required. |
| INPUT | Type in your question or command for the AI agent. You can type "@" or click the ➕ plus button to insert data dynamically. |
Action: Run Agent Command
| 🏷️ Field | 🔤 Description |
|---|---|
| AGENT | Select the AI agent that will execute the command. This field is required. |
| COMMAND | Choose the specific command you want the AI agent to run. This field is required. |
| INPUT | Optionally, provide additional input for the command if needed. You can type "@" or click the ➕ plus button to insert data. |
| OUTPUT (optional) | Add typed output fields the same way Ask Agent with Structured Output does. Each entry becomes a first-class variable downstream. |
💡 Structured output works on Run Agent Command too. Click ➕ Add Output to define typed fields (Text, Number, Boolean, Date, JSON Object, etc.) — the command's reply is parsed into those variables instead of returned as free-form text. Use it when a command needs to feed a Branch, Insert Row, or Update Custom Field downstream.
Example: A /qualify-lead command on a Sales Agent returns score (Number) + tier (Single Select). Wire tier into a Branch and score into an Update Custom Field — no prose parsing required.
Use Cases
Here are a few ways to use the Agent action in your automations:
| 🪄 Use Case | 🔤 Description |
|---|---|
| Email triage | Feed incoming emails to an agent that classifies them by urgency and drafts suggested replies. |
| Content generation | After scraping a webpage, ask an agent to summarize the content or rewrite it for a specific audience. |
| Data enrichment | Pass lead information through an agent that researches the company and appends context before creating a CRM entry. |
| Code review assistance | Send code snippets to an agent that checks for common issues and returns improvement suggestions. |
💡 Tip: The Agent action works best when paired with data-gathering steps like Scrape Webpage or Search Web. Feed real-world data into your agent for more accurate, context-aware responses.
Pick a Model on Every Step
The Ask Agent step exposes the same Model (optional) dropdown that the Taskade AI step does. The picker overrides the agent's default model for this run only, so you can route a single step through a deeper reasoning model without retraining the agent.
- Open the Ask Agent or Run Agent Command step.
- Click Model (optional) in the step settings.
- Pick the model. The live credit cost shows next to each name.
- Leave it on Auto to keep the agent's default.
Use this for one-off hard calls inside an otherwise cheap automation. See AI Models & Credit Costs for which tier fits which job.
Related guides
- Agent Team Action — Call an entire AI Team instead of one agent
- Agent Tool Action — Use a flow as a tool inside an agent
- Agent Knowledge Action — Write results back to agent memory
- Structured Output — Typed agent responses for branching
- Custom AI Agents — Build the agents this action calls
- Branch Action — Route based on agent output