How to Use Exa web page content in Instinct
Exa returns clean page text, relevant excerpts, or generated summaries from URLs, with available page metadata. Use it to read known documentation, articles, and reports when your agent needs evidence from the page.
Prompts to try with Exa web page content in Instinct
Copy an example into Instinct, or ask in your own words.
Every Monday, use Exa web page content to read https://docs.stripe.com/changelog and report entries added since the previous check, with supporting excerpts.
Each weekday, use Exa web page content to read https://github.blog/changelog/ and summarize newly observed announcements about GitHub Actions.
Every Friday, use Exa web page content to read https://www.postgresql.org/docs/current/release.html and report changes in the extracted page text since the previous reading.
Every Monday, use Exa web page content to read https://www.mozilla.org/en-US/firefox/privacy/ and flag changes to the page's privacy statements.
Each morning, use Exa web page content to read https://www.nasa.gov/missions/artemis/ and report changes in the mission information compared with the previous reading.
How to set up Exa web page content in Instinct
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send Instinct this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Create an API key
In the console, open API keys and create a key for Instinct. Copy it.
- Send Instinct this message
Instinct reads Spiral's skill and asks for your API key.
set up https://spiral.ai/SKILL.md
- Give Instinct the key
When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Exa web page content
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "exa", "model": "exa/contents", "input": { "ids": [ "<ids>" ] } }'
Then paste one of the prompts above: Instinct finds Exa web page content on Spiral, shows the price and runs it.
Exa web page content providers and prices
Spiral runs Exa web page content through Exa. Open a card for today's price, with every fee included.
$0.0013 per page for each content type (text, highlights, summary), subpages included.
Settings you can ask for
Ask Instinct for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Subpages | 0 to 100 | 0 | The number of subpages to crawl. The actual number crawled may be limited by system constraints. |
| Livecrawl | never, always, fallback, or preferred | Deprecated. Use | |
| Compliance | hipaa | Enterprise-only compliance mode. Set to | |
| Max age hours | -1 to 720 | Maximum age of cached content, in hours, up to 720. Cached content younger than this is used, and older pages are fetched fresh. | |
| Livecrawl timeout | a whole number up to 90000 | 10000 | The timeout for livecrawling in milliseconds. |
Every API field of Exa Contents · Web Page Content is on its tool page: open its card above.
What can you do with Exa web page content in Instinct?
Produce a recurring change brief from selected documentation and company pages with Exa. Compare successive page readings and include the passages behind each reported change.
Check an implementation against official documentation
Read the relevant documentation URLs and compare their requirements with the code under review.
Build a brief with supporting passages
Read a selected article list and attach relevant excerpts and source URLs to each conclusion.
Review research papers
Extract passages about methods, findings, and limitations from known paper URLs, including PDFs.
Compare public product documentation
Read vendors' documentation pages and compare the capabilities and restrictions they describe.
Monitor documentation changes
Retrieve selected documentation pages on a schedule and compare their extracted text with previous readings.
Prepare company research
Read public company product and annual report URLs to summarize stated offerings, strategy, and business risks.
Answer support questions from approved sources
Retrieve relevant passages from a selected set of help pages and use them to draft answers with citations.
More on Exa web page content and Instinct
Overview
Exa web page content in other agents
Questions about Exa web page content in Instinct
Can Instinct use Exa web page content?
Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Exa web page content like any built-in tool.
How much does Exa web page content cost in Instinct?
$0.0013 per page for each content type (text, highlights, summary), subpages included. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.
Do I need an Exa account to use Exa web page content in Instinct?
You need no Exa account. Instinct uses one Spiral API key for every tool, and Spiral runs Exa web page content on its own Exa account.
How long does it take to set up Exa web page content in Instinct?
About two minutes: create an API key, then send Instinct this message, then give Instinct the key.
Does Instinct wait while Exa web page content runs?
Exa web page content runs in the background. Instinct starts the run, checks on it and gives you the json when it's ready.
Can Exa read PDFs and pages rendered with JavaScript?
Yes. Exa documents support for PDFs, JavaScript-rendered pages, and complex layouts, with full text returned as a clean Markdown page body.
How many URLs can Exa process in one request?
Exa accepts up to 100 URLs per request. Split larger reading lists into batches of 100 or fewer.
How fresh is a live page retrieval?
Exa defines live content as fetched within the last 60 seconds. Its documentation also warns that a failed fresh fetch may return the latest cached copy.
Does every result include an author and publication date?
No. Exa returns author and publication metadata when the source page has them, so those details are not guaranteed for every URL.
Are highlights and summaries copied from the source?
Highlights are extracted passages selected for relevance to your question. Summaries are generated through a language model call for each page, so use highlights when you need source wording.
Start using Exa web page content in Instinct
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Instinct:
set up https://spiral.ai/SKILL.md


