Eric Ciarla
Retell uses Firecrawl to keep AI phone agents answering from live, LLM-ready documentation, turning each customer's docs and help center into a knowledge base, without writing a single scraper.
What is Retell? Retell is the leading voice agent platform powering fully autonomous phone calls for modern businesses, built to sound like real conversations, not touch-tone phone menus.
When a borrower checks application status or a lead answers an outbound call, AI phone agents have seconds to apply the latest rules. Sounding human is not enough. These agents sit inside revenue and ops workflows, where answering from stale or incomplete content is a failure in a business-critical moment.
Zexia Zhang, Co-Founder of Retell, and their team understand this well. Retell ships with a built-in Knowledge Base that ingests URLs, files, and custom text so agents use the same sources human teams trust.
As larger customers came on with multi-product documentation and JavaScript-heavy portals, each new account meant another fragile scraper and another round of "did we miss this page?" debugging.
What was the old, traditional approach costing Retell?
Keeping knowledge bases current meant maintaining a mix of one-off Puppeteer/Playwright scripts, sitemap crawls, and manual copy-paste from docs sites. They could wire bespoke scrapers for each account, rely on occasional exports and sitemaps, or accept that some calls would route through outdated answers.
These setups shipped, but they did not meet the bar Retell sets for call containment and cost per call.
What they wanted instead was a straightforward pipeline from documentation to LLM-ready content. A knowledge base they could treat as configuration, not a new engineering project every time a customer signed. Firecrawl's web scraping API, already powering more than 40,000 knowledge bases, fills that gap.
How does Firecrawl fit into the knowledge base pipeline of Retell?
Retell now standardizes on Firecrawl's /scrape endpoint as the ingestion primitive behind these knowledge bases.
Firecrawl takes a docs URL, an API reference, changelog, status page, or support center, and turns it into LLM-ready markdown or JSON. Navigation, boilerplate, and ad-like clutter are stripped out.
Backed by Firecrawl's Fire-Engine browser layer, it handles JavaScript-heavy docs and PDFs without Retell running its own headless browser fleet or proxy rotation.
Instead of writing a new scraper for every customer, the team defines small, focused scrape jobs around the URLs that actually matter. Firecrawl handles pagination, navigation, and rendering. The output drops into the embedding and retrieval stack that already powers their agents.
Extending coverage is a matter of adding a URL to a Firecrawl job, not re-architecting ingestion.
As they rolled Firecrawl into production, the team experimented with different endpoints. They used /map to understand docs structures and /scrape to hydrate the content itself. Leading with targeted scrape jobs on a short list of each customer's docs and help center links gave them the predictable coverage they needed for voice agents.
Together with the Firecrawl team, they documented a clear pattern, with guidance on where /batch-scrape, /crawl, and /map make sense for larger, multi-domain documentation sets.
What does the production pattern look like for Retell?
For each new customer, Retell keeps a short list of docs and help center links as configuration for Firecrawl jobs, instead of hard-coding them into bespoke scripts.
When a job works well for one account, for example scraping a multi-language API reference plus changelog, it becomes a template Retell can reuse across that vertical.
Refreshing a knowledge base means rerunning Firecrawl jobs or adjusting their config, not touching scraping infrastructure. Today, Retell's production phone agents run on top of Firecrawl-powered knowledge bases that stay aligned with each customer's docs, without a scraping team in the loop.
Firecrawl's search API powers voice experiences beyond enterprise platforms too — developers can build their own real-time voice assistant that searches the web and handles email through natural spoken conversation.
Ready to power your AI application with reliable web data? Try Firecrawl and ship faster.
Frequently Asked Questions
How does Firecrawl help Retell?
Firecrawl reads each customer's docs and help center pages and keeps an up-to-date knowledge base that Retell's phone agents answer from.
Which Firecrawl endpoints matter most for Retell?
Retell leans on the /scrape endpoint for day-to-day ingestion, uses /batch-scrape and /crawl to cover larger or multi-domain docs footprints, and reaches for /map when they need a high-level inventory of a docs surface.
What does success with Firecrawl look like for Retell?
New customers hand Retell a short list of docs and help center links and, without writing new scrapers, get an up-to-date, LLM-ready knowledge base powering phone agents that answer from the same pages their users see.
data from the web