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.
Donate Make giving easy, seamless, and m…Grants Management Maximize your communit…Challenges Engage your workforce with fu…Enterprise Impact Platform Purpose, impa…Volunteer Empower employees to make a di…Employee Groups Foster a rich culture of…Reporting Suite Unify your social impact…Services & Add-Ons Expand your impact wi…
Resources
Videos
Benevity Enterprise Impact Platform Overview
Discover how the Benevity Enterprise Impact Platform unifies giving, volunteering and grants to scale corporate purpose.
Learn more about the platform
Related resources
Image: A woman looking at a laptop screen.
Blog posts
The rest of the page is in full screen.
[Resources](https://benevity.com/resources) Videos # Benevity Enterprise Impact Platform Overview Discover how the Benevity Enterprise Impact Platform unifies giving, volunteering and grants to scale corporate purpose. [Learn more about the platform](https://benevity.com/enterprise-impact-platform) ## Related resources [](https://benevity.com/blog/best-csr-software) [Blog posts The 15+ best CSR software options This guide compares the best CSR software options, what each platform does well and who it suits.](https://benevity.com/blog/best-csr-software) [Read more](https://benevity.com/blog/best-csr-software) [](https://benevity.com/blog/yourcause-alternatives) [Blog posts Is YourCause the best corporate giving platform for you? An honest review This YourCause review examines how the platform performs in each area and where another option may make more sense.](https://benevity.com/blog/yourcause-alternatives) [Read more](https://benevity.com/blog/yourcause-alternatives) [](https://benevity.com/blog/giving-tuesday-2026-ideas) [Blog posts Giving Tuesday 2026: Ideas to grow employee participation Read about five ideas to grow employee engagement for Giving Tuesday.](https://benevity.com/blog/giving-tuesday-2026-ideas) [Read more](https://benevity.com/blog/giving-tuesday-2026-ideas)
Thin: Too few words of their own are in the HTML for a page of their kind. Render the rest on the server.
The figures
100 pages, set against the 169,244 sites with figures and 539 in nonprofits.
- Readablehigher is better
- 98%98 of 100 pages
- All 169,244 sitesBetter than 41%539 nonprofits sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 55%middle page
- All 169,244 sitesBetter than 31%539 nonprofits sitesBetter than 43%
Of the words before script, the share that are the page and not menus, footer and forms. 9 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 269,545tokens
- About 2,695 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
91 pages measured. Not measured: 9 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 |
| benevity.comThis site, 100 pages | 98% | 55% | 2,695 |
| yourcause.com77 pages | 100% | 85% | 2,531 |
| groundswell.io100 pages | 94% | None | 2,765 |
| blog.blackbaud.com100 pages | 100% | None | 2,418 |
Third 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 | Allowed | Training models | User-agent: GPTBot / Allow: / |
| 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 | Allowed | Training models | User-agent: ClaudeBot / Allow: / |
| Claude-SearchBotAnthropic | Not named | Claude’s search | Falls to User-agent: * |
| PerplexityBotPerplexity | Allowed | Perplexity search | User-agent: PerplexityBot / Allow: / |
| Google-ExtendedGoogle | Allowed | Training Gemini | User-agent: Google-Extended / Allow: / |
| 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.
11 pages of 100 lose something. Pick a loss to see what to do about it.Open the action plan
| What an agent getshigher is better | Signals | Costnot scored | ||||
|---|---|---|---|---|---|---|
| Page | Words | Clean | Readable | Main heading | Tokens | What it loses |
| /resources/enterprise-impact-platform-overview-video | 139 | 26% | No | Yes | 456 | Thin |
| /resources/benevity-for-teams-conversation-chris-battles | 159 | 30% | No | Yes | 489 | Thin |
| /careers | 46 | No <main> | Yes | None | 458 | No <main> and 1 more |
| /annual-impact-report/2024 | 4,356 | No <main> | Yes | Yes | 9,093 | No <main> |
| /annual-impact-report/2025 | 4,528 | No <main> | Yes | Yes | 9,957 | No <main> |
| /community | 166 | No <main> | Yes | Yes | 471 | No <main> |
| /events | 386 | No <main> | Yes | Yes | 918 | No <main> |
| /grants-hub | 1,631 | No <main> | Yes | Yes | 5,189 | No <main> |
| /pages/corporate-volunteering-impact-playbook | 461 | No <main> | Yes | Yes | 839 | No <main> |
| /pages/global-donation-disbursement | 1,098 | No <main> | Yes | Yes | 2,242 | No <main> |
| /tools/calculator | 116 | No <main> | Yes | Yes | 571 | No <main> |
| /support | 196 | 17% | Yes | Yes | 379 | Nothing |
| /tools/ai-purpose-program-quiz | 216 | 20% | Yes | Yes | 430 | Nothing |
| /tools/deskless-worker-impact-program-quiz | 114 | 23% | Yes | Yes | 309 | Nothing |
| /articles-archive | 121 | 25% | Yes | Yes | 484 | Nothing |
| /benevity-photography-notice | 108 | 28% | Yes | Yes | 190 | Nothing |
| /social-impact-platform-upgrade | 366 | 29% | Yes | Yes | 800 | Nothing |
| /nonprofit-stories | 179 | 29% | Yes | Yes | 455 | Nothing |
| /resources/embed-corporate-giving-into-workplace-tools | 169 | 31% | Yes | Yes | 507 | Nothing |
| /resources/spark-employee-engagement | 174 | 32% | Yes | Yes | 550 | Nothing |
| /resources/security-gdpr | 185 | 34% | Yes | Yes | 552 | Nothing |
| /resources/donation-matching-drive-impact | 187 | 34% | Yes | Yes | 550 | Nothing |
| /resources/virtual-volunteering-guide | 198 | 35% | Yes | Yes | 642 | Nothing |
| /resources/drive-big-change-missions | 201 | 35% | Yes | Yes | 601 | Nothing |
| /scale-with-confidence | 537 | 35% | Yes | Yes | 1,151 | Nothing |
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/benevity.com"><img src="https://mttr.si/agent-view/benevity.com/badge.svg" alt="Agent View: 98% readable, 55% clean" height="20"></a>
The figures in one line
benevity.com in Agent View: 98% of pages readable, better than 47% of nonprofits sites; 55% clean; 269,545 tokens to read all 100 pages. mttr.si/agent-view/benevity.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
- Wrap 9 pages in <main>Clean measured
- Render the rest of 2 pages on the serverReadable
- Give 1 page a main headingClearer
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 100 pages read, where the read stopped at its page limit. 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.