Skip to content
Good for Bots

Real-time AI assistant that suggests answers during video interviews and sales calls

Click badge to copy

Changed your site? Run a new scan.

Claim to rescan

Claiming is free. Verify ownership to request a rescan after deploying your changes.

Unclaimed listings are checked automatically every 90 days.

Good for Bots report

GeekBye scores 84 of 100: 40 of the 50 base points, 44 of the 50 agent-layer points, no penalties.

Earned

40 of the 50 base points above the line, 44 of the 50 agent-layer points below it.

84

3 prompts away

Copy them below ↓

13

Still open

Behind the checks below, with prompts in Pro.

3
Penalties0
How scoring works · current methodology →

Through a bot’s eyes

“GeekBye is a desktop AI interview assistant that gives real-time answers and suggestions during technical, behavioral and sales interviews and meetings, with free and paid plans.”

Simulated from the response GoodForBotsBot received on , not a live answer from any AI assistant.

What it can read, and what stays hidden →

What a bot can read

The homepage text covers real-time interview assistance: four feature descriptions on answers, invisibility, live suggestions and coding help, a list of supported meeting platforms, a sales coaching and meeting summaries section, and user testimonials that mention job offers at named companies. Some facts a visitor would look for appear as text: the Mac download action, 600+ users, 33 languages and a date stamp. Prices do not appear in the homepage text. The llms.txt file adds a list of further pages with short descriptions, covering pricing, documentation, download requirements for macOS and Windows, comparisons with other interview tools, guides, a blog and a contact page. The JSON-LD blocks add the plan names and prices, the FAQ answers and a link to the contact page. No email address or phone number appears in the text. The homepage excerpt is truncated, so later sections are not visible.

What stays hidden

The homepage text does not give the Pro plan prices or what the paid plans include; those appear only in structured data. It gives no detail on how the undetectability claim works or whether meeting platforms permit the tool. It does not state which Windows versions are supported on the homepage itself, does not give a direct contact address, and does not explain what the free plan's limit on AI responses means in practice. The testimonials are not verified and mostly name no reviewer.

What is GeekBye?

GeekBye is an AI interview assistant delivered as a desktop app, with the homepage offering a Mac download and the structured data listing both Windows and macOS. According to the homepage, it gives real-time answers to coding, behavioral and technical questions during interviews, offers live suggestions and follow-ups as the conversation goes on, and produces meeting summaries with action items.

Read more →

It states that it works with Google Meet, Microsoft Teams, Zoom, Slack and Webex, and claims it is hidden from screen recordings. The site describes it as intended for job seekers in technical interviews, and its FAQ data also names sales professionals, students in oral exams and executives. The Starter plan is listed as free with limited AI responses, and paid Pro plans are listed in the structured data.

3 prompts, 13 points

For Claude Code, Cursor or Codex. The score moves after the next scan.

+5score from 84 to 89

Serve Markdown when asked for it

None of the 4 pages read pass fully; 3 partly. Asking the page at /blog for markdown still returns text/html.

Read prompt

+5score from 89 to 94

Mark up content so a reader can find it

1 of 4 pages read pass; 3 partly. The homepage is partly structured: The outline jumps from h2 to h4, which the standard forbids.

Read prompt

+2.5score from 94 to 97

Give form fields names and recognizable semantics

0 of 1 assessed homepage form fields meet the static naming and field-semantics checks.

Read prompt

Pro

14 more prompts in Pro

Pro shows a prompt for every fix and drafts your llms.txt and robots.txt. It never changes the score.

$9 once, per listingSee Pro

Deployed your fixes? Rescan to update your score →

Select a check to see what we found and how it is graded.

Readable base

40.4 / 50

Passes.

3.3 of 3.3 points.

robots.txt is valid, with 11 user-agent groups.

Passes.

8.3 of 8.3 points.

Sitemap declared in robots.txt, listing at least 200 URLs.

Passes.

8.3 of 8.3 points.

All 4 pages read pass. The homepage describes itself to machines as Organization, ContactPoint, WebSite in valid schema.org JSON-LD.

Half passes.

5 of 10 points.

1 of 4 pages read pass; 3 partly. The homepage is partly structured: The outline jumps from h2 to h4, which the standard forbids.

Passes.

8.3 of 8.3 points.

6 of 6 assessed homepage navigation links expose usable destinations.

Passes.

4.2 of 4.2 points.

165 of 165 assessed homepage links and buttons have a nonempty accessible name.

Fails.

0 of 2.5 points.

0 of 1 assessed homepage form fields meet the static naming and field-semantics checks.

Half passes.

1.3 of 2.5 points.

166 of 170 assessed homepage controls and role declarations meet the static role, state and relationship checks.

Prompt in Pro →
Passes.

1.7 of 1.7 points.

All 4 pages read pass. The homepage declares itself as its canonical URL.

Agent layer

43.8 / 50

Passes.

11.3 of 11.3 points.

/llms.txt is well formed: 125 links across 6 sections.

Passes.

7.5 of 7.5 points.

/llms.txt is descriptive: a summary plus descriptions on 94% of links.

Passes.

12.5 of 12.5 points.

/llms-full.txt serves the site's content as markdown (at least 64 KB).

Half passes.

5 of 10 points.

None of the 4 pages read pass fully; 3 partly. Asking the page at /blog for markdown still returns text/html.

Passes.

5 of 5 points.

States a position on 6 AI crawlers, across 3 purposes (training, user-fetch, search).

Passes.

2.5 of 2.5 points.

Declares AI usage preferences via Content-Signal (robots.txt): ai-train, ai-input, search.

Penalties

− 0

Passes.

Penalty: 0 of 15 points.

Our crawler reaches the page without being challenged.

Passes.

Penalty: 0 of 20 points.

Nothing on the homepage tells a crawler to skip it or to withhold its snippet.

Passes.

Penalty: 0 of 25 points.

The captured homepage HTML contains 2786 content words; completeness is not assessed.

Passes.

Penalty: 0 of 25 points.

robots.txt allows every known search and user-fetch crawler to reach the homepage.

Passes.

Penalty: 0 of 10 points.

The homepage is served over HTTPS and returns HTTP 200.

Passes.

Penalty: 0 of 3 points.

The homepage provides both a non-empty title and meta description.

Passes.

Penalty: 0 of 3 points.

The homepage is reached in 0 redirects.

Passes.

Penalty: 0 of 3 points.

The homepage reached a plain crawler in 77 ms.

Agent capabilities

0 of 11 · no points

Each one found adds +1 to the badge.

Not applicable.

Adds +1 to the badge when found.

No API catalog published.

Not applicable.

Adds +1 to the badge when found.

No /auth.md published.

Not applicable.

Adds +1 to the badge when found.

No AI Catalog published, so no MCP server card can be discovered.

Not applicable.

Adds +1 to the badge when found.

No A2A Agent Card at /.well-known/agent-card.json, and none listed in an AI Catalog.

Not applicable.

Adds +1 to the badge when found.

No usable Agent Skills index was found at either well-known path or in the AI Catalog.

Not applicable.

Adds +1 to the badge when found.

No WebMCP declarations were found in the collected HTML or inline scripts. External scripts were not inspected.

Not applicable.

Adds +1 to the badge when found.

No Web Bot Auth key directory at /.well-known/http-message-signatures-directory.

Not applicable.

Adds +1 to the badge when found.

No HTTP 402 payment challenge on the homepage or robots.txt, and no manifest at /.well-known/x402.

Not applicable.

Adds +1 to the badge when found.

No ACP discovery declaration established at /.well-known/acp.json.

Not applicable.

Adds +1 to the badge when found.

No UCP discovery declaration established at /.well-known/ucp.

Not applicable.

Adds +1 to the badge when found.

No public AMP discovery declaration established. Private or hidden agents may not advertise one to our crawler.

Access & usage policy

Who can read this page, and for what purpose?

GoodForBotsBot received HTTP 200 via a direct request. No indexing restriction was observed in the supported homepage directives.

Sampled URL: https://geekbye.com/

Declared crawling rules

No matching refusal for this URL was found for the listed identities.

Sources and scope: declared crawling rules

Observed access

GoodForBotsBot received HTTP 200 via a direct request.

Sources and scope: observed access
Coverage and interpretation
  • Crawler coverage includes the registered identities and up to 50 user-agent entries from robots.txt. Source excerpts and detail groups are bounded; omissions are labelled.
  • Observed access describes GoodForBotsBot only. Other crawler entries describe declared rules, not tests of those operators' access.
  • Coverage is the sampled homepage response and collected robots.txt files. No indexing or citation is guaranteed. Usage preferences are declarations, not a legal determination of permission.
  • This explanation adds no points or penalties. Any score effects belong to the linked checks.
  • AIPREF and Content Signals keep their own definitions. AIPREF search can include processing used exclusively for search; training preferences are not a blanket ruling on every search process.

In its category

7th of 60 in AI Products & Agents

  1. 1Pixelropepixelrope.com
  2. 2Contents Pilotcontentspilot.com
  3. 7GeekBye · this reportgeekbye.com

The prompts above would take GeekBye to 97, 3rd in its category.

To the prompts ↑

Category average 62. The percentile appears once the catalogue holds a few hundred sites.

Scanned

Site profile

Login
Not established
API
Not established
Commerce
Not established

It decides which conditional checks apply. “Not established” means no proof in what we read, not proof of absence.

Scan details

Every scan is kept. Pro draws the history as a chart →

Scanned
7 Nov 2026
Rubric
0.9.0
Requests
23
Fetched
5.3 MB
Took
16.5 s
Homepage
77 ms · direct
Pages read
4
robots.txt
allowed
Which pages the scan read

The homepage and up to three pages from the sitemap and homepage links. Structured data, page structure, Markdown negotiation and typed links check each page read and take the median page; other checks read the homepage.

  • Homepagealways read
  • /blog/best-cluely-alternativesarticle · linked from the homepage · read
  • /docs/getting-starteddocumentation · linked from the homepage · read
  • /blogcollection · linked from the homepage · read