ActionTavilyUpdated September 2026
How do I search the web from an AI agent?
Short answer: You can web search in Tavily by hand from its own interface, but it won’t repeat itself. On TinyCommand, add the Tavily Web Search action to a workflow, map its 5 inputs from any upstream app, and it runs automatically every time the trigger fires. No code, and a free tier to start.
Inputs
The fields this action accepts.
Every field can be mapped from an upstream trigger, AI step, table row, or hard-coded literal.
| Field | Type | Required | Description |
|---|---|---|---|
Query query | string | Required | Search query |
Depth search_depth | options | Optional | Depth. Options: Basic (fast), Advanced (thorough) |
Max Results max_results | string | Optional | 5 |
Topic topic | options | Optional | Topic. Options: General, News, Finance |
Include Answer Summary include_answer | options | Optional | Include Answer Summary. Options: Yes, No |
Sample request
{"query": "e.g. latest news on quantum computing","search_depth": "{{trigger.search_depth}}","max_results": "5","topic": "{{trigger.topic}}","include_answer": "{{trigger.include_answer}}"}
Returns
{"query": "quantum computing","answer": "Recent advances in quantum computing include...","results": [{"url": "https://example.com","score": 0.95,"title": "Title","content": "..."}]}
Use these fields in downstream nodes for routing, logging, or error handling.
Triggered by
Apps that pair well as the trigger for Web Search.
Any of these apps can fire this action as part of a workflow.
FAQ
Questions about Web Search.
What does the Web Search action do in Tavily?
Runs a web search through Tavily and returns fresh, AI-optimized results tuned for LLM agents and RAG. Returns ranked snippets with URLs so the model can cite sources.
What inputs does Web Search require?
Required: Query. Every input accepts a static value or a variable from any upstream node in your workflow.
Can I use dynamic inputs from earlier workflow nodes?
Yes. Any field on this action can pull values from upstream nodes, whether that's a form response, a trigger payload, an AI output, or a lookup result.
What happens if Tavily returns an error?
The run history shows the failed step with its input and the error message Tavily returned, so you can fix the input and run the workflow again. Automatic retries are built into HTTP steps only, where you can also set your own retry count and delay.
Does Web Search support batch operations?
Run Web Search inside a loop to process each item in an array. TinyCommand does not throttle calls for you, so for large arrays add a Delay step if you need to stay within Tavily's rate limits.
More actions
Other Tavily actions.
Action
Crawl Site
Crawls a website starting from the given URL and returns clean Markdown for every reachable page. Best for RAG ingestion, knowledge-base imports, or competitive content scrapes.
ActionExtract URLs
Fetches a list of URLs and returns clean, structured Markdown for each, stripping nav, ads, and boilerplate. Use this in RAG pipelines or when you need to feed pages into an LLM context.
ActionMap Site
Discovers URLs on a site without downloading or parsing page content. Much faster than Crawl when you only need the URL graph (sitemaps, audits, route inventories).