intercom.io llms.txt
In short
intercom.io serves a 10 KB llms.txt with 16 H2 sections and 67 links, graded B on the llmstxt.org structure (5 of 6 checks). It lacks same-site links. The home page does not link it, so an agent that does not guess paths will not find it. No llms-full.txt was found. Read 4 November 2026.
llms.txt 10 KB, 239 lines
# intercom.com […] llms.txt
> This file helps large language models (LLMs) understand the content structure, canonical sources, and retrieval rules for intercom.com and its sister properties.
Fin (formerly Intercom) is the Customer Agent company delivering perfect customer experiences from support to sales to commerce. The company's primary site is [fin.ai](https://fin.ai/). intercom.com covers the Intercom Helpdesk, the company's human-agent workspace (omnichannel inbox, ticketing, Copilot, knowledge hub, reporting), used by 30,000+ businesses including Anthropic, Amazon, Miro, Linear, Lightspeed, Lovable, Perplexity, and WHOOP. The Helpdesk works alongside Fin, the company's AI Agent, so AI and human teams collaborate […].
For a description of Intercom, the Intercom Helpdesk, and how it works with Fin, see [Facts about Intercom](https://www.intercom.com/ai-instructions).
---
## Site Structure
### Platform
- [Intercom Helpdesk](https://www.intercom.com/): The human-agent workspace that works alongside Fin
- [Pricing](https://www.intercom.com/pricing): Plans for every team size
- [Watch Demos](https://www.intercom.com/view-demos): Product walkthroughs
### Helpdesk (human-agent workspace)
- [Inbox](https://www.intercom.com/helpdesk/inbox): AI-powered inbox for faster, better customer support
- [Copilot](https://www.intercom.com/helpdesk/copilot): Copilot 2, the Agent for support teammates that gathers context, takes action in connected systems and handles the admin on every conversation
- [Tickets](https://www.intercom.com/helpdesk/tickets): Faster resolution with […] ticketing
- [Omnichannel](https://www.intercom.com/helpdesk/omnichannel): Live chat, email, phone, and social in one place
- [Help Center](https://www.intercom.com/helpdesk/help-center): Self-service knowledge base
- [Knowledge Hub](https://www.intercom.com/helpdesk/knowledge-hub): All your support content in one place
- [Outbound](https://www.intercom.com/helpdesk/outbound): Customer messaging and proactive support
- [Reporting](https://www.intercom.com/helpdesk/reporting): AI-powered analytics for support teams
### AI Agent
The company's AI Agent is Fin, served on fin.ai, the company's primary site. Use fin.ai for product depth, pricing, research, demos, and how Fin and the Helpdesk work together as one platform. Use intercom.com for Helpdesk-specific content.
- [Fin (canonical product site)](https://fin.ai/)
- [Fin Pricing](https://fin.ai/pricing)
- [Fin Research](https://fin.ai/research/)
- [Fin Help Center](https://fin.ai/help/en/)
- [Fin llms.txt](https://fin.ai/llms.txt)
---
## Customer Evidence
- [Customer Stories](https://www.intercom.com/customers): Case studies and outcomes across 30,000+ businesses
- Featured customers include: Anthropic, Miro, Gamma, Linear, Vanta, Lovable, Perplexity, Rocket Money, Checkout.com, eToro, Consensys, Culture Amp, Amazon, Lightspeed, Nuuly, Living Spaces, Toast, WHOOP, Stake, and monday.com
---
## Comparisons
- [Intercom vs Zendesk](https://www.intercom.com/compare-intercom-vs-zendesk): Head-to-head comparison
---
## Learning Center
*(Concept explainers and buyer-stage education)*
- [Learning Center](https://www.intercom.com/learning-center): Index of articles
- [AI Customer Service Companies](https://www.intercom.com/learning-center/ai-customer-service-companies)
- [Generative AI in Customer Service](https://www.intercom.com/learning-center/generative-ai-in-customer-service)
- [Customer Service Chat](https://www.intercom.com/learning-center/customer-service-chat)
- [Customer Service Ticketing System](https://www.intercom.com/learning-center/customer-service-ticketing-system)
- [Customer-Centric: Definition](https://www.intercom.com/learning-center/customer-centric-definition)
---
## Blog
*(The company's own articles, podcasts, and videos on customer service and AI agents […] the largest content surface on intercom.com)*
- [Intercom Blog](https://www.intercom.com/blog): Index of all posts, newest first
- Articles: `/blog/<slug>`
- Podcasts: `/blog/podcasts/<slug>`
- Videos: `/blog/videos/<slug>`
First 70 of 239 lines. 5 spans shown as […] because the words or characters in them are rejected by this site's own style rules; the live file has them.
Parse graded B, 5 of 6
file: https://intercom.io/llms.txt
intercom.com […] llms.txt
This file helps large language models (LLMs) understand the content structure, canonical sources, and retrieval rules for intercom.com and its sister properties.
16 sections, 67 links, no Optional section.
Ora's cached score: 55, grade C, scanned 22 August 2026.
The parse
intercom.io lists 67 links: 0 point at intercom.io or a relative path, 67 point elsewhere. The hosts it links most: intercom.com (43), fin.ai (12), trust.intercom.com (6), developers.intercom.com (2).
| H2 section | Links |
|---|---|
| Site Structure | 16 |
| Customer Evidence | 1 |
| Comparisons | 1 |
| Learning Center | 6 |
| Blog | 9 |
| Research & Reports | 1 |
| Programs | 4 |
| Trust, Security & Compliance | 4 |
| Company | 4 |
| Related Properties | 7 |
| Canonical Policy | 0 |
| Technical Guidance for LLMs | 8 |
| Localized Content | 0 |
| Site Metadata | 0 |
| Contact | 4 |
| File Metadata | 0 |
Grade against the llmstxt.org structure
The file passes 5 of 6 checks and fails 1: at least 80 percent of links point at the same site. The grade is the count of passed checks: six is A, five is B, four is C, three is D, fewer is F. It measures structure only. Whether any agent reads the file is a separate question, covered on the llms.txt reference.
| Check | Result | Detail |
|---|---|---|
| Starts with an H1 naming the site or project | Pass | H1: intercom.com […] llms.txt |
| Has a blockquote summary under the H1 | Pass | Blockquote summary found. |
| Has at least one H2 section that lists links | Pass | 16 H2 sections, 12 with links. |
| At least 80 percent of links point at the same site | Fail | 0 of 67 links stay on intercom.io (0 percent). |
| Under 100 KB | Pass | 10321 bytes as served. |
| Plain markdown, no HTML | Pass | No HTML document markers in the body. |
Ora's cached score
Ora's cached report for intercom.io gives it 55 of 100, grade C, scanned on 22 August 2026. Its Access layer, which holds the read-layer checks below, scored 42 of 58 check points. Read from GET ora.ai/api/score/intercom.io on 5 November 2026. The score is Ora's, not this site's, and the structure grade above is a different measure: it grades the llms.txt file against the llmstxt.org proposal, while Ora's score covers the whole site. Ora's report for intercom.io has every layer.
| Ora check (Access layer) | Result | Points |
|---|---|---|
| Sitemap exists | Pass | 2 of 2 |
| Content without JavaScript | Pass | 2 of 3 |
| Not blocked by bot detection | Pass | 2 of 2 |
| Markdown URL fallback | Fail | 0 of 2 |
| llms.txt exists | Pass | 1 of 1 |
| llms.txt formatting | Partial | 1 of 2 |
| JSON-LD structured data | Pass | 4 of 4 |
| Metadata completeness | Pass | 2 of 2 |
| llms.txt links resolve | Pass | 2 of 2 |
| Markdown alternate link | Fail | 0 of 1 |
| Redirect hygiene | Pass | 1 of 1 |
| Page token budget | Pass | 1 of 1 |
| Code fence validity | Pass | 1 of 1 |
| Content behind auth | Not applicable | 0 of 2 |
| OpenAPI spec published | Fail | 0 of 7 |
| Markdown agent docs | Fail | 0 of 1 |
| Markdown negotiation with Vary | Fail | 0 of 1 |
| Markdown for agent user agents | Fail | 0 of 1 |
| Agent crawler reachability | Pass | 2 of 2 |
Linking and the companion file
The home page of intercom.io does not link the file in its HTML. Ora's lab found (2026-10-19) that 86 percent of llms.txt fetches by agents arrived through a link, so an unlinked file is mostly a file nobody opens. No llms-full.txt was found at the same root.
How it compares
At 10 KB the file is larger than 60 percent of the 2,529 plain-text llms.txt files in this edition, and its 67 links put it ahead of 70 percent of them on link count. The home page declares no generator. Size bucket: 10 to 50 KB. Tranco rank 650. Category: Top 10,000, no category.
Live file: https://intercom.io/llms.txt. Read 4 November 2026. If the file has since changed or gone, the live URL is the authority; this page records what the crawl read on that date.
Sources
- intercom.io llms.txt https://intercom.io/llms.txt, read 4 November 2026
- llms.txt proposal (llmstxt.org) https://llmstxt.org/, read 4 November 2026
- Tranco list 746WX (crawl universe) https://tranco-list.eu/list/746WX, read 4 November 2026
- Ora: AgentReady launch post (the 86 percent finding) https://ora.ai/blog/agentready-launch, read 4 November 2026
- Ora llms.txt (GET /api/score/{domain} looks up a cached score) https://ora.ai/llms.txt, read 5 November 2026
Last reviewed 5 November 2026