Agent View
The site as an AI agent gets it, beside the site as a person sees it. What it can read, what it has to cut away, and what it never sees.
AskYourDatabaseDocumentation DocumentationDiscord (opens in a new tab)
- Tutorial
- Getting Started
- Get better answer
- Train to get better answer
- Prepare Database Connection String
- Sample Databases
- Webhook
- Privacy, Data Protection, and Security
The rest of the page is in full screen.
Documentation v1.1.124 ## Support for GPT-4.1 & GPT-4.1-mini We have upgraded our model lineup to OpenAI’s newly-released **GPT-4.1** and **GPT-4.1-mini**, replacing the previous GPT-4o and GPT-4o-mini across the entire application. What this means for you: - **Blazing-fast responses** – average latency is reduced by ~30 %. - **Smarter code generation** – the new models produce cleaner, more reliable code snippets and SQL queries. - **Improved context handling** – better at following long or complex instructions without losing track. If you were previously using GPT-4o or GPT-4o-mini, no action is required—your existing settings now automatically point to GPT-4.1 equivalents. ## Unlimited DeepSeek V3 **for** Professional Plan We’ve also added first-class support for the flagship open-source model **DeepSeek V3**. **** All users on the **Professional** plan can now invoke DeepSeek V3 without any quota limits. Why you’ll love DeepSeek V3: - Competitive performance on reasoning and coding tasks - Open-source transparency—inspect the weights and behavior - No usage caps for Professional subscribers To start using DeepSeek V3, simply select it from the model dropdown in the chat or code interpreter panel. [v1.1.121](https://www.askyourdatabase.com/docs/v1.1.121)[v1.1.135](https://www.askyourdatabase.com/docs/v1.1.135)
No h1: Give each one h1 that says what the page is.
The figures
90 pages, set against the 167,946 sites with figures.
- Readablehigher is better
- 100%90 of 90 pages
- All 167,946 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 93%middle page
- All 167,946 sitesBetter than 91%
Of the words before script, the share that are the page and not menus, footer and forms. 11 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 244,794tokens
- About 2,720 a page
To read every page once. A long page that answers well is not worse for it. Tokens are estimated at about 4 characters each.
How its pages spread on Clean
70 pages measured. Not measured: 11 with no <main> or no words.
Against its rivals
The sites nearest it by what they do, with figures. Close means similar work, not better.
| Readinghigher is better | Costnot scored | ||
|---|---|---|---|
| Site | Readable | Clean | Tokens a page |
| askyourdatabase.comThis site, 90 pages | 100% | 93% | 2,720 |
| forem.com100 pages | 98% | 75% | 1,966 |
| dqc.ai100 pages | 96% | 44% | 876 |
| itpathsolutions.com100 pages | 98% | 96% | 6,200 |
First of 4 on Readable, second on Clean.
AI crawler access
What robots.txt says to each, as read on October 24, 2026. 8 of 8 may read the site.
| Crawler | robots.txt says | Used for | The line that decides |
|---|---|---|---|
| GPTBotOpenAI | Not named | Training models | Falls to User-agent: * |
| OAI-SearchBotOpenAI | Not named | ChatGPT search | Falls to User-agent: * |
| ChatGPT-UserOpenAI | Not named | A page a person asks about | Falls to User-agent: * |
| ClaudeBotAnthropic | Not named | Training models | Falls to User-agent: * |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Not named | Perplexity search | Falls to User-agent: * |
| Google-ExtendedGoogle | Not named | Training Gemini | Falls to User-agent: * |
| bingbotMicrosoft | Not named | Bing and Copilot | Falls to User-agent: * |
Every AI crawler mttr checks may read it. Not named means the rules for every crawler apply.
Every page
Worst first. Each opens in Agent View at the top.
19 pages have no main heading. Give each one h1 that says what the page is.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /resources/sql-server-latest-status-example.sql | 142 | No <main> | Yes | None | 291 | No <main> and 1 more |
| /seo/ai-database-query/reference.sql | 243 | No <main> | Yes | None | 581 | No <main> and 1 more |
| /seo/crm-pipeline/reference.sql | 189 | No <main> | Yes | None | 349 | No <main> and 1 more |
| /seo/mysql-gui/session-timezone.sql | 115 | No <main> | Yes | None | 214 | No <main> and 1 more |
| /seo/natural-language-rollout/reference.sql | 144 | No <main> | Yes | None | 353 | No <main> and 1 more |
| /seo/postgresql-report/reference.sql | 142 | No <main> | Yes | None | 380 | No <main> and 1 more |
| /seo/sql-dashboard/reference.sql | 248 | No <main> | Yes | None | 670 | No <main> and 1 more |
| /seo/sql-query-generator/join-aggregation.sql | 143 | No <main> | Yes | None | 264 | No <main> and 1 more |
| /seo/text-to-sql-evaluation/fixture.sql | 95 | No <main> | Yes | None | 285 | No <main> and 1 more |
| /seo/text-to-sql/reference.sql | 95 | No <main> | Yes | None | 245 | No <main> and 1 more |
| /seo/warehouse-sql-routing/definition-change.sql | 145 | No <main> | Yes | None | 256 | No <main> and 1 more |
| /chatbot-pricing | 141 | 53% | Yes | None | 280 | No h1 |
| /desktop-pricing | 79 | 53% | Yes | None | 127 | No h1 |
| /docs/v1.1.136 | 110 | 63% | Yes | None | 281 | No h1 |
| /docs/v1.1.135 | 107 | 64% | Yes | None | 265 | No h1 |
| /docs/v1.1.121 | 166 | 71% | Yes | None | 304 | No h1 |
| /docs/v1.1.124 | 166 | 72% | Yes | None | 337 | No h1 |
| /docs/v1.1.13 | 204 | 73% | Yes | None | 446 | No h1 |
| /docs/connect | 583 | 89% | Yes | None | 1,370 | No h1 |
Show where it stands
A card, a badge and a line, each with the figures.
A badge for the site
<a href="https://mttr.si/agent-view/askyourdatabase.com"><img src="https://mttr.si/agent-view/askyourdatabase.com/badge.svg" alt="Agent View: 100% readable, 93% clean" height="20"></a>
The figures in one line
askyourdatabase.com in Agent View: 100% of pages readable, better than 47% of sites; 93% clean; 244,794 tokens to read all 90 pages. mttr.si/agent-view/askyourdatabase.com
What to do next
Fix the pages, let an agent do it, and read the site again to see the figures move.
Fix what agents miss
- Give 19 pages a main headingClearer
- Wrap 11 pages in <main>Clean measured
Connect your agent
Claude Code, Codex or Cursor reads the site’s fixes over MCP, fixes a page in your code, has mttr read it again, and checks the fix landed.
https://mttr.si/mcpSet up an agent
Claim the site
Prove it is yours with a DNS record or a file. Your agent can then reach its reads and jobs, and set each change to wait for your approval.
Claim the siteDrawn from the HTML mttr fetched on its read of October 24, 2026, not a screenshot, and only from the 90 pages read. An assistant’s own reader may differ. Tokens are estimated at about 4 characters each. A site an agent reads well is not a site an assistant cites.