Exa
Exa neural search for AI agents
Exa is the neural search API built for AI agents and RAG pipelines — designed around the observation that LLMs need search results that pre-filter for content (not just URLs), are scoped semantically (not just keyword), and are returned with rich text snippets ready to drop into a prompt. Tiny Command exposes four actions, no triggers: Search (neural search across the web; results include URL, title, summary, optionally the full text), Get Contents (fetch the full text and summary for any URL — useful when you have URLs from elsewhere and want Exa's cleaned-text extraction), Find Similar (find pages semantically similar to a reference URL — "show me more like this article"), Answer (Exa's RAG-as-a-service — returns a synthesised answer plus citations, the right shape for "give the LLM a grounded answer in one call"). The connection uses an Exa API key from dashboard.exa.ai. Exa's neural search uses an embedding-based index — the search is for meaning, not keywords, which is the right model for "find me articles like X" agent workflows.
Do anything Exa can do, from a workflow.
Every action accepts dynamic inputs from upstream nodes, whether that's an AI output, a form field, or a search result.
| Action | What it does |
|---|---|
| Exa Answer | Exa's RAG-as-a-service — pass a question, get back a synthesised answer with source citations. Saves the search + retrieve + LLM-summarise chain by bundling all three server-side. For "agent needs to look something up" workflows. |
| Exa Find Similar | Pass a reference URL, get back semantically similar pages. Useful for content discovery ("find articles like this one"), competitive intel ("find similar blog posts to our hero piece"), and LLM grounding ("find related sources before answering"). |
| Exa Get Contents | Fetches and cleans the full text of one or more specific URLs. The right path when you already have the URLs (from elsewhere or from Search) and want Exa's text extraction for downstream LLM consumption. |
| Exa Neural Search | Semantic web search — favours content depth and topical relevance over keyword exactness. Returns URLs with titles and summaries. Use include_answer to bundle LLM synthesis, include_raw_content to fetch the cleaned text inline. |
Pre-built Exa workflows.
Clone any recipe and customize it in one click. Every recipe is fully editable.
Three things worth knowing.
Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.
Connect Exa once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every Exa field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.
Questions about the Exa integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect Exa to Tiny Command?
What Exa triggers does Tiny Command support?
What Exa actions can I run from a workflow?
Is the Exa integration real-time?
Do I need to write code to use Exa with Tiny Command?
How much does the Exa integration cost?
More other apps people connect.
Same category as Exa, ordered by how often teams pair them. Hover the carousel to pause.
Do more with Exa.
Wire it to Slack, Notion, HubSpot, Stripe, or any of the other 438 apps in our catalog. Setup takes roughly two minutes. Free to try, no credit card.
