What does this automation do?
An agent decides this flow should run, the web is searched, and an agent that knows your market turns the findings into a project you can work from.
What can you do with it?
- Let the agent run the workflow, rather than only sit inside one
- Turn a search into a structured project instead of a wall of links
- Build a research record that carries from one run to the next
The Steps
This automation runs in 4 steps:
- When Agent Tool
- Then Media — Search the web
- Then Taskade AI — Ask an agent ("Research Runner")
- Then Taskade — Create Project
What makes this different from a Zapier-style flow?
The "Research Runner" step is not a one-off model call. It is a Taskade AI agent that knows your market, competitors and past research, remembers what it has already looked into, so every run builds on the last one instead of starting from an empty prompt.
A stateless "ask the model" step forgets everything the moment it returns. An agent keeps its knowledge and its memory between runs, carries its own tools, and can be handed work by other automations.
Who is this automation for?
Built for researchers who want the agent to start the job itself. An agent decides this flow should run, the web is searched, and an agent that knows your market turns the findings into a project you can work from.
How do you set it up?
- Open the "Automations" tab in your workspace.
- Click ➕ Add automation, then start from scratch.
- Add the "Agent Tool" trigger.
- Add the action "Search the web" from Media.
- Add the action "Ask an agent" from Taskade AI. Point it at an agent called "Research Runner".
- Add the action "Create Project" from Taskade.
- Enable the toggle in the top-right corner to activate the automation.
Prefer to describe it instead? Click Build this flow with AI above and Taskade wires the trigger, the steps, and the agent for you.