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 main content.
RatesRefinancingHome Refinance LoansCash-out RefinancingHome Equity LoansHELOCLoan OptionsHome Purchase Loans
Manage my existing loan
Log in to my account
New to Pennymac?
Register to create an account
Image: or
Image: or
Apply for a new loan
The rest of the page is in full screen.
reCAPTCHA # PennyMac Financial Services, Inc. to Present at the 2025 Barclays Global Financial Services Conference Press Releases August 29, 2025 min read Share Multimedia Files WESTLAKE VILLAGE, Calif.—(BUSINESS WIRE)—PennyMac Financial Services, Inc. (NYSE: PFSI) announced today that it will present jointly with PennyMac Mortgage Investment Trust (NYSE: PMT) at the 2025 Barclays Global Financial Services Conference. Chairman and Chief Executive Officer David Spector and Senior Managing Director and Chief Financial Officer Daniel Perotti will participate in a fireside chat at 2:45 p.m. Eastern Time on Monday, September 8, 2025. A link to the live audio webcast will be available on PennyMac Financial Services, Inc.’s Investor Relations website at pfsi.pennymac.com. A replay of the webcast will be archived for a limited time. ##### About PennyMac Financial Services, Inc. PennyMac Financial Services, Inc. is a specialty financial services firm focused on the production and servicing of U.S. mortgage loans and the management of investments related to the U.S. mortgage market. Founded in 2008, the company is recognized as a leader in the U.S. residential mortgage industry and employs approximately 5,300 people across the country. For the twelve months ended March 31, 2026, PFSI's production of newly originated loans totaled $154 billion in UPB, making it a top lender in the nation. As of March 31, 2026, PFSI serviced loans totaling $720 billion in UPB, making it a top mortgage servicer in the nation. Additional information about PFSI is available at [pfsi.pennymac.com](https://pfsi.pennymac.com/). ##### Contacts ###### Media Kristyn Clark [[email protected]](mailto:[email protected]) [805.395.9943](tel:8053959943) ###### Investors Kevin Chamberlain Isaac Garden [[email protected]](mailto:[email protected]) [818.264.4907](tel:8182644907) Share Connect with us [LinkedIn](https://www.linkedin.com/company/pennymac/) [Instagram](https://www.instagram.com/pennymacusa/) [ YouTube](https://www.youtube.com/@Pennymacusa) #### Want to stay in the know about today's interest rates? Sign up for emails and get updates directly in your inbox! #### Your info has been received! Thanks for signing up for Pennymac updates! If you have any questions about our rates, mortgages, etc., you can always call us at [866.549.3583](tel:1-866-549-3583) . #### Sorry, but something went wrong Please refresh the page and try again. Or if you have any questions about our rates, mortgages, etc., you can always call us at [866.549.3583](tel:1-866-549-3583) .
An agent gets this page whole: its own text is in the HTML the server sends.
The figures
100 pages, set against the 167,893 sites with figures.
- Readablehigher is better
- 100%100 of 100 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
- 67%middle page
- All 167,893 sitesBetter than 45%
Of the words before script, the share that are the page and not menus, footer and forms.
- Costshown, never scored
- 344,496tokens
- About 3,445 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
100 pages measured.
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 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.
No page loses anything an agent needs.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/pennymac.com"><img src="https://mttr.si/agent-view/pennymac.com/badge.svg" alt="Agent View: 100% readable, 67% clean" height="20"></a>
The figures in one line
pennymac.com in Agent View: 100% of pages readable, better than 47% of sites; 67% clean; 344,496 tokens to read all 100 pages. mttr.si/agent-view/pennymac.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
No page loses anything an agent needs. The action plan has the site’s other fixes.
Open the action planConnect 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.