# How to use a Righthand with FireCrawl

Use Righthand to review Firecrawl page-extraction output against the underlying page response.

By Righthand Team · 2026-10-12

Source: https://www.righthand.ai/blog/how-to-use-righthand-with-firecrawl

## Quick answer

Use Righthand to review Firecrawl page-extraction output against the underlying page response. A successful extraction request does not necessarily mean the target page was valid.

Start with a reviewable deliverable, keeping FireCrawl as the accepted home for its records. This guide uses an explicitly approved snapshot or browser read; it does not assume that every provider API action is exposed by your Righthand connection.

## Evidence and access

Firecrawl documents separate API-request status and target-page status in scrape responses. See the [official FireCrawl reference](https://docs.firecrawl.dev/features/scrape). Provider capabilities and Righthand's available tools are separate checks.

Use the owner's permitted crawl or scrape output with source URLs, retrieval timestamps, page boundaries, and extraction requirements. No new crawl is needed for the review. Verify the required tools and owner-approved scope through [Righthand integrations](/integrations); use the supplied packet when a native read is unavailable.

## Define the objects and authority

Include these fields in the working input: requested URL, final URL, extraction status, target status, content format, fetched time, selected text. These are the requested review columns, not a promise that every provider endpoint returns them under those exact names.

Extracted text may omit interactive or protected content. The first run reviews provided outputs and does not authorize crawling extra sites.

| Responsibility | Owner |
| --- | --- |
| Prepare source scope and access | Account owner |
| Organize evidence and proposed next steps | Righthand |
| Approve consequential changes | the documentation reviewer |

## Illustrative first-run brief

> Use the owner-provided FireCrawl snapshot or approved read-only view. Review ten supplied page extracts for the approved documentation set. Flag target errors, empty sections, and redirected identities. Prepare an evidence checklist without new crawls. Run once for the agreed sample, using America/Los_Angeles for the review deadline and preserving source timestamps separately. Return the draft in this conversation by Friday at 3 PM Pacific for the documentation reviewer to review. Include source references and missing fields. Do not write records, spend money, change permissions, or send external messages. Stop and report an unavailable source rather than substituting another account.

## Expected result and verification

An API success with a target-page error stays an invalid source for the requested claim. It is not marked successfully verified.

Compare final URL and target status with the original page and inspect one quoted section. Record the source cutoff, applied filters, and items excluded from the sample. The reviewer should be able to follow each consequential finding back to an original object. A well-written summary is not evidence that a proposed action happened. If a later write is authorized, verify its specific result separately before changing the task's status.


### Illustrative input and draft output

These synthetic entries show the requested review, not live account results or a provider field schema.

| Source item | Supplied observation | Draft conclusion |
| --- | --- | --- |
| Page A | Required section preserved | Review extraction |
| Page B | Dynamic field absent | Request authoritative copy |
| Page C | Source time missing | Hold freshness conclusion |

## Common failure and recovery

A redirect or login page can be extracted cleanly while providing the wrong content. Correct the source identity before using the text.

If extracted content omits a required section, flag the missing text and request an approved source copy; do not fill the gap from assumptions.

## FAQ

### What should the reviewer verify first?

Verify URL, retrieval time, page scope, and extracted fields against the original source where permitted. Extracted text can lose context or omit dynamic content.

### How should a repeat run be scoped?

Retain URL and extraction-version references on repeat reviews. Recheck changed pages and preserve absent fields as unknown rather than converting them into empty values.

For connection and permission details, use [Righthand Docs](https://docs.righthand.ai). Review [Pricing](/pricing) alongside any separate provider charges before expanding the workflow.