AI Demos Research — the structured-intelligence platform. Every verdict on these pages opens to the execution behind it.
Graded 17 November 2026

Can Firecrawl search only the allowed websites?

Firecrawl kept the search on docs.github.com: all 10 results came from that site, led by GitHub's 'About Copilot' page, and the GitHub Blog post that gives the answer (2021) did not appear. It returned a ranked list of pages rather than a written answer.

1 of 1 test case passed

Every test case in this scenario has a result.

Pass rate100%1 of 1 gradable
Coverage1 of 1test case with a result
1PassDid everything it was expected to do.
0FailNo test case failed.
0Not gradableEvery result here could be graded.
0UntestedEvery test case in this scenario has a result.
The pass rate is a summary. The evidence is the test case below: what we sent, what we checked, what the tool returned, and the proof.

The test case

Each test case is judged on its own: Pass, Fail, Not gradable, or Untested. The scenario result above is based on this test case.

Search only these websitesPassEvidence
What we sent

Input · Search limited to docs.github.com through the native domain filter: “In what year did GitHub first launch a technical preview of GitHub Copilot?”

What the tool returned

Search results export: the request limited to docs.github.com and the ten pages returned

Copied from Output file 1 (JSON), results

10 results
  1. https://docs.github.com/copilot/about-github-copilot/what-is-github-copilot
    description
    GitHub Copilot is an AI assistant that helps you write, understand, and ship software. Copilot is built into GitHub, it works within the development workflow ...
  2. https://docs.github.com/copilot/concepts/agents/code-review
    description
    Copilot reviews your pull requests, identifies issues, and suggests fixes. This article provides an overview of Copilot code review.
  3. https://docs.github.com/enterprise-cloud@latest/copilot/concepts/agents/cloud-agent/about-cloud-agent
    description
    Copilot can research a repository, create an implementation plan, and make code changes on a branch. You can review the diff, iterate, and create a pull request ...
  4. https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models
    description
    GitHub Copilot is evolving rapidly, with new features and models released regularly. Model updates are announced in the Copilot changelog.
  5. https://docs.github.com/en/copilot/responsible-use/agents
    description
    Learn how to use GitHub Copilot agentic features responsibly by understanding their purposes, capabilities, and limitations.
  6. https://docs.github.com/en/copilot/concepts/models/fallback-and-lts-models
    description
    On March 18, 2026, GitHub designated GPT-5.3-Codex as the LTS model. LTS models apply only to Copilot Business and Copilot Enterprise. An LTS model is an AI ...
  7. https://docs.github.com/en/copilot/reference/copilot-billing/request-based-billing-legacy/copilot-requests
    description
    Starting June 1, 2026, Premium requests for Spark and Copilot cloud agent are tracked in dedicated SKUs from November 1, 2025.
  8. https://docs.github.com/copilot
    description
    You can use GitHub Copilot to enhance your productivity and assist as you work on code. Copilot subscription. Learn about Copilot
  9. https://docs.github.com/en/copilot/get-started/quickstart-for-using-github-copilot-in-your-ide
    description Use Copilot in your IDE to explain concepts, complete code, propose edits, and validate files with agent mode.
  10. https://docs.github.com/en/copilot/how-tos/copilot-cli/use-copilot-cli
    description
    Understand the different ways you can use GitHub Copilot in your terminal. Using GitHub Copilot CLI. Learn how to use GitHub Copilot from the command line.
Show as JSON
JSON
[
  {
    "rank": 1,
    "title": "About Copilot - GitHub Docs",
    "url": "https://docs.github.com/copilot/about-github-copilot/what-is-github-copilot",
    "description": "GitHub Copilot is an AI assistant that helps you write, understand, and ship software. Copilot is built into GitHub, it works within the development workflow ..."
  },
  {
    "rank": 2,
    "title": "About GitHub Copilot code review",
    "url": "https://docs.github.com/copilot/concepts/agents/code-review",
    "description": "Copilot reviews your pull requests, identifies issues, and suggests fixes. This article provides an overview of Copilot code review."
  },
  {
    "rank": 3,
    "title": "About GitHub Copilot cloud agent - GitHub Enterprise Cloud Docs",
    "url": "https://docs.github.com/enterprise-cloud@latest/copilot/concepts/agents/cloud-agent/about-cloud-agent",
    "description": "Copilot can research a repository, create an implementation plan, and make code changes on a branch. You can review the diff, iterate, and create a pull request ..."
  },
  {
    "rank": 4,
    "title": "Learning about new features and models - GitHub Docs",
    "url": "https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models",
    "description": "GitHub Copilot is evolving rapidly, with new features and models released regularly. Model updates are announced in the Copilot changelog."
  },
  {
    "rank": 5,
    "title": "Application card: GitHub Copilot Agents",
    "url": "https://docs.github.com/en/copilot/responsible-use/agents",
    "description": "Learn how to use GitHub Copilot agentic features responsibly by understanding their purposes, capabilities, and limitations."
  },
  {
    "rank": 6,
    "title": "Base and long-term support (LTS) models - GitHub Docs",
    "url": "https://docs.github.com/en/copilot/concepts/models/fallback-and-lts-models",
    "description": "On March 18, 2026, GitHub designated GPT-5.3-Codex as the LTS model. LTS models apply only to Copilot Business and Copilot Enterprise. An LTS model is an AI ..."
  },
  {
    "rank": 7,
    "title": "Requests in GitHub Copilot (legacy)",
    "url": "https://docs.github.com/en/copilot/reference/copilot-billing/request-based-billing-legacy/copilot-requests",
    "description": "Starting June 1, 2026, Premium requests for Spark and Copilot cloud agent are tracked in dedicated SKUs from November 1, 2025."
  },
  {
    "rank": 8,
    "title": "GitHub Copilot documentation",
    "url": "https://docs.github.com/copilot",
    "description": "You can use GitHub Copilot to enhance your productivity and assist as you work on code. Copilot subscription. Learn about Copilot"
  },
  {
    "rank": 9,
    "title": "Quickstart for using GitHub Copilot in your IDE",
    "url": "https://docs.github.com/en/copilot/get-started/quickstart-for-using-github-copilot-in-your-ide",
    "description": "Use Copilot in your IDE to explain concepts, complete code, propose edits, and validate files with agent mode."
  },
  {
    "rank": 10,
    "title": "Use GitHub Copilot CLI",
    "url": "https://docs.github.com/en/copilot/how-tos/copilot-cli/use-copilot-cli",
    "description": "Understand the different ways you can use GitHub Copilot in your terminal. Using GitHub Copilot CLI. Learn how to use GitHub Copilot from the command line."
  }
]
Open the whole JSON file ↗

Full run record: the domain restriction, all ten results and the pages checked against

Copied from Output file 2 (JSON), results · an excerpt

10 results
  1. https://docs.github.com/copilot/about-github-copilot/what-is-github-copilot
  2. https://docs.github.com/copilot/concepts/agents/code-review
  3. https://docs.github.com/enterprise-cloud@latest/copilot/concepts/agents/cloud-agent/about-cloud-agent
  4. https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models
  5. https://docs.github.com/en/copilot/responsible-use/agents
  6. https://docs.github.com/en/copilot/concepts/models/fallback-and-lts-models
  7. https://docs.github.com/en/copilot/reference/copilot-billing/request-based-billing-legacy/copilot-requests
  8. https://docs.github.com/copilot
  9. https://docs.github.com/en/copilot/get-started/quickstart-for-using-github-copilot-in-your-ide
  10. https://docs.github.com/en/copilot/how-tos/copilot-cli/use-copilot-cli
Show as JSON
JSON
[
  {
    "rank": 1,
    "url": "https://docs.github.com/copilot/about-github-copilot/what-is-github-copilot",
    "title": "About Copilot - GitHub Docs",
    "content": "[7,614 characters in the file]",
    "content_chars": 7614,
    "published_date": null
  },
  {
    "rank": 2,
    "url": "https://docs.github.com/copilot/concepts/agents/code-review",
    "title": "About GitHub Copilot code review",
    "content": "[24,904 characters in the file]",
    "content_chars": 24904,
    "published_date": null
  },
  {
    "rank": 3,
    "url": "https://docs.github.com/enterprise-cloud@latest/copilot/concepts/agents/cloud-agent/about-cloud-agent",
    "title": "About GitHub Copilot cloud agent - GitHub Enterprise Cloud Docs",
    "content": "[20,773 characters in the file]",
    "content_chars": 20773,
    "published_date": null
  },
  {
    "rank": 4,
    "url": "https://docs.github.com/en/copilot/concepts/learning-about-new-features-and-models",
    "title": "Learning about new features and models - GitHub Docs",
    "content": "[8,569 characters in the file]",
    "content_chars": 8569,
    "published_date": null
  },
  {
    "rank": 5,
    "url": "https://docs.github.com/en/copilot/responsible-use/agents",
    "title": "Application card: GitHub Copilot Agents",
    "content": "[48,797 characters in the file]",
    "content_chars": 48797,
    "published_date": null
  },
  {
    "rank": 6,
    "url": "https://docs.github.com/en/copilot/concepts/models/fallback-and-lts-models",
    "title": "Base and long-term support (LTS) models - GitHub Docs",
    "content": "[2,329 characters in the file]",
    "content_chars": 2329,
    "published_date": null
  },
  {
    "rank": 7,
    "url": "https://docs.github.com/en/copilot/reference/copilot-billing/request-based-billing-legacy/copilot-requests",
    "title": "Requests in GitHub Copilot (legacy)",
    "content": "[7,875 characters in the file]",
    "content_chars": 7875,
    "published_date": null
  },
  {
    "rank": 8,
    "url": "https://docs.github.com/copilot",
    "title": "GitHub Copilot documentation",
    "content": "[2,624 characters in the file]",
    "content_chars": 2624,
    "published_date": null
  },
  {
    "rank": 9,
    "url": "https://docs.github.com/en/copilot/get-started/quickstart-for-using-github-copilot-in-your-ide",
    "title": "Quickstart for using GitHub Copilot in your IDE",
    "content": "[4,703 characters in the file]",
    "content_chars": 4703,
    "published_date": null
  },
  {
    "rank": 10,
    "url": "https://docs.github.com/en/copilot/how-tos/copilot-cli/use-copilot-cli",
    "title": "Use GitHub Copilot CLI",
    "content": "[4,530 characters in the file]",
    "content_chars": 4530,
    "published_date": null
  }
]

Excerpt ends here. Open the source for the complete output.

Open the whole JSON file ↗
Expected vs. Found
✓Expected: The answer page on the other site must not come back, and at least one relevant page from the allowed site must.Found: All ten results were on docs.github.com, led by GitHub Docs' About Copilot page. The GitHub Blog post announcing Copilot's technical preview did not appear at any rank.
Supporting proof
Cited values1 value from this file
timestamp_utc
2026-09-16T08:44:06Z
Why this result

It is a Pass because both halves of the requirement held: the search stayed on the allowed site, with all ten results on docs.github.com, and it still brought back a relevant page from that site, while the blog post that holds the answer was left out.

Tested by Aman · evidence dated 16 September 2026

Configuration and setup

How this tool was set up for the run and what the test needed in place. Each row is a fact from the run's records; a fact the records do not hold is left out, not guessed.

Software that produced the output
Firecrawl
Build or version
Not exposed by the hosted product
Surface
API
Set up before the run
GitHub Blog’s 29 June 2021 Copilot technical-preview announcement gives 2021; GitHub Docs’ About Copilot page gives no launch year. Both pages were checked by hand on 7 September 2026 and again on the morning of 16 September 2026, when the blog post was still live. The question went unchanged to Firecrawl's search API, limited to docs.github.com through its native domain filter.
Search
docs.github.com · 10 results · markdown
Tested
16 September 2026 · Aman

How this scenario is graded

How we decide Pass, Fail and Not gradable. The same rules apply to every tool tested on this scenario.

How results are decided

Each test case gets one result per tool: Pass, Fail or Not gradable. A test case we haven't run yet shows Untested. There are no partial results.

The rules
  • Pass: the tool did everything the test expected, and nothing it said contradicts the correct answer.
  • Fail: at least one expected behaviour clearly didn't happen; the test case's result says which one and quotes the tool.
  • Not gradable: our evidence couldn't settle the outcome (for example a record we needed is missing). It is never counted as a fail, and the test case's result says what's missing.

Where this sits in the benchmark

This page is one cell of a larger study: one tool, one scenario. Only this benchmark's frame appears here.

LevelNameScope
BenchmarkWeb Search for AI →10 scenarios · 12 tools
CapabilityWeb Retrieval →
ScenarioSearch only these websites →
ToolFirecrawl →

History of this result

What has happened to this result since it was first published. Runs and grades are never overwritten: a retest or a re-grade publishes a new result and keeps the earlier one readable.

from the publication record
21 November 2026First publishedWeb Search for AI v1

Act on this result

Nothing filed here edits the run or the grade. A challenge opens a review, and a review can produce a new run or a re-grade — which becomes the current result and leaves this one in the history.

This matches what I see

You run the same kind of test against your own setup and get the same behaviour.

Agree →
This does not match

Yours behaves differently. Tell us what you got, with a screenshot if you have one.

Disagree →
Point out an issue

Something here is wrong — a reference value, a transcription, a grade.

Report an issue →
Request a retest

On a newer build, a larger dataset, or your own setup.

Request a retest →
We have fixed this

Tell us what changed and we schedule a rerun of the failing test case. The old result stays as history.

Vendor notice →
Filed against this evidenceNothing yet. Challenges, counter-evidence and fix notices appear here with their outcome, and stay on the page after they are resolved.
Cite this result
aidemos.com/benchmarks/web-search-for-ai/results/firecrawl/allowlisted-web-search · 1 pass · 0 fail · coverage 1/1 · graded 2026-11-17

The same record is available as structured data through the AI Demos MCP server, with the counts, the coverage and every per-test-case reason carried as fields.

Verify the proof files

These files support this result. Open a file to inspect the original evidence.

Output file 1 (JSON) ↗application/json · 4 KB
Output file 2 (JSON) ↗application/json · 297 KB
File fingerprints (SHA-256)

A fingerprint identifies the exact file used for this result.

Output file 1 (JSON)685406940593b809c17e95bd8c61a863e3e6f58af3fb44fc66e24b870ec92aff
Output file 2 (JSON)78cb7a3636478b6d4b740c4b7d99a316e6409a14215fd2c0568cc1862b1892b7