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.
Skip to content
Skip to content
Connect is A program of NAMI NH
Get Help Now: call 988
Contact US
Image: Connect - Training Professionals & Communities in Suicide Prevention & Response
Who We AreConnect PrinciplesMeet the Connect TeamWho We TrainOrganizations & BusinessesFederal/State Agencies & CommunitiesK-12 SchoolsIndividuals & Small Groups
eLEARNING PLATFORM
Is Your Community Ready? Introducing the Connect Postvention Readiness Assessment
The rest of the page is in full screen.
# Is Your Community Ready? Introducing the Connect Postvention Readiness Assessment / [Newsletter](https://theconnectprogram.org/category/newsletter/) / By [NAMI NH](https://theconnectprogram.org/author/admin/) **When Tragedy Strikes, Readiness Can’t Wait Until Then** When a community loses someone to suicide or another sudden death, the ripple effects reach far beyond the immediate circle of grief — coworkers, classmates, neighbors, and entire organizations can feel the impact for months or years. The communities that respond best aren’t the ones scrambling to figure out what to do in the moment. They’re the ones who took an honest look at where they stood before a crisis ever occurred. That’s exactly what NAMI New Hampshire’s Connect™ Postvention Program helps communities do — and we’re excited to share a new tool that makes that first step easier than ever. **Introducing the Postvention Readiness Assessment** Today we’re releasing the Postvention Readiness Assessment — Community Edition, a free, self-guided toolkit that helps any organization or community gauge how prepared it is to respond to a suicide, a drug poisoning (overdose) death, or another sudden loss. The toolkit has two parts. The Readiness Assessment walks you through seven sections and seventeen questions covering motivation, awareness, infrastructure, coordination, capacity, readiness for action, and existing strengths — plus a simple scoring guide to total your results. The Decision Tree then translates that score, along with a few real-time considerations, into a clear, recommended next step for your community. [](https://theconnectprogram.org/wp-content/uploads/2026/09/Connect_Postvention_Readiness_Assessment-Community_Edition-FILLABLE.pdf) Click to download [](https://theconnectprogram.org/wp-content/uploads/2026/09/Connect_Postvention_Readiness_Assessment-AIAN_Edition-FILLABLE.pdf) Click to download **Built for Two Audiences, One Goal** We designed this edition with two groups in mind. If your community is about to reach out to NAMI NH for support, this assessment is the natural first step — our Connect team members may ask you to complete it before your first conversation, so we can meet you exactly where you are. We’re also making it available to everyone who attends our conference sessions and workshops. Take it back to your own community, work through it with your team, and see what your results suggest. If they point toward reaching out, we’d welcome that conversation — but there’s no obligation either way. **What’s Inside** Each of the seven sections opens with a short description of what an actually ready community or organization looks like, so you’re not just answering questions in the abstract — you have something concrete to measure yourselves against. From there, a simple numeric scale, along with a few multiple-choice questions, builds toward a total readiness score between 6 and 25. That score sorts into three bands — Low, Moderate, and High Readiness — each paired with a realistic recommended approach, from an introductory conversation and leadership engagement work, up through full Connect training and cross-sector planning. A red-flag checklist also flags situations, like severe staffing shortages or active conflict between partners, that should pause any plan regardless of score. **One Tool for Suicide and Drug Poisoning (Overdose) Death** NAMI NH’s Connect Postvention Program has long supported communities preparing for the aftermath of suicide. As we expand into supporting communities affected by drug poisoning (overdose) death as well, we built this assessment to work for either — the process of building readiness looks the same, whatever form the loss takes. There’s no wrong answer anywhere in this toolkit. A low score isn’t a failing grade — it just tells you, and us, exactly where to start. A high score doesn’t mean the work is finished. Your total is a starting point for an honest conversation, not a verdict on your community. **Get Started** The Postvention Readiness Assessment — Community Edition is available now. Print it, fill it out digitally, or work through it as a team at your next staff meeting. If your results suggest it’s time to talk, or if you just want to think it through with someone, reach out to our Connect team — we’re always glad to help a community take its next step, whatever that turns out to be. **Amy Cook, Director of Training Email:** [[email protected]](mailto:[email protected])
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
28 pages, set against the 167,893 sites with figures.
- Readablehigher is better
- 100%28 of 28 pages
- All 167,893 sitesBetter than 47%
Pages whose own text is in the HTML the server sends, enough of it for their kind.
- Cleanhigher is better
- 77%middle page
- All 167,893 sitesBetter than 60%
Of the words before script, the share that are the page and not menus, footer and forms. 2 pages are not measured, with no <main> or no words.
- Costshown, never scored
- 146,888tokens
- About 5,246 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
26 pages measured. Not measured: 2 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.
No site near it by what it does has figures yet.
AI crawler access
What robots.txt says to each, as read on October 23, 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.
17 pages of 28 lose something. Pick a loss to see what to do about it.Open the action plan
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/theconnectprogram.org"><img src="https://mttr.si/agent-view/theconnectprogram.org/badge.svg" alt="Agent View: 100% readable, 77% clean" height="20"></a>
The figures in one line
theconnectprogram.org in Agent View: 100% of pages readable, better than 47% of sites; 77% clean; 146,888 tokens to read all 28 pages. mttr.si/agent-view/theconnectprogram.org
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 17 pages a main headingClearer
- Wrap 2 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 23, 2026, not a screenshot, and only from the 28 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.