---
title: "ADM: 56 of 100 on Ora's scan | Am I Ready for Agents?"
description: "ADM scores 56 of 100 on Ora's agent-readiness scan, grade C, read 20 Nov 2026. Open door and clean, readable pages, with nothing an agent can do once inside."
canonical: https://amireadyforagents.com/blog/adm-agent-readiness
site: "Am I Ready for Agents?"
last_updated: 2026-11-20
date: 2026-11-20
section: "360 checks"
---

# ADM: 56 of 100 on Ora's scan | Am I Ready for Agents?

> ADM scores 56 of 100 on Ora's agent-readiness scan, grade C, read 20 Nov 2026. Open door and clean, readable pages, with nothing an agent can do once inside.

Source: https://amireadyforagents.com/blog/adm-agent-readiness
Site: Am I Ready for Agents?
Last reviewed: 2026-11-20

# ADM: 56 of 100 on Ora's agent-readiness scan

## In short

ADM scores 56 of 100 on Ora's agent-readiness scan, grade C, read on 20 November 2026. 60 percent of the 132,085 domains Ora ranks score under 50, and the average score is 44. Open door and clean, readable pages, with nothing an agent can do once inside.

## The score

ADM is an agricultural processor and food ingredient company based in Chicago.

-   56of 100, grade C
    
    Ora's agent-readiness scan of adm.com, read 20 November 2026.
    
-   5Discovery, of 6
    
    Whether assistants find the company: search presence, Wikipedia and Wikidata, catalogues.
    
-   20Access, of 28
    
    Whether they can read it: the door, text without JavaScript, llms.txt, structured data.
    
-   6Usability, of 15
    
    Whether they can act through it: an MCP server, an API with a specification, sign-in for agents.
    
-   0Payments, of 0
    
    No check in this layer applied to the site.
    

60 percent of the 132,085 domains Ora ranks score under 50, and the average score is 44.

## What an assistant meets at the door

Before an assistant can read, compare or buy, it has to get in. These rows are the door: whether the bot shield lets the main agents through, what robots.txt tells the search, training and user-triggered agents, and whether the home page has text without running JavaScript.

| Check | Result | What Ora saw |
| --- | --- | --- |
| Not blocked by bot detection | Pass, 2 of 2 | Site accessible to 4 agent user-agents (ChatGPT-User, OAI-SearchBot, Claude-User, PerplexityBot). |
| Agent crawler reachability | Pass, 1 of 1 | Reachable to every agent we tested - ChatGPT-User: reachable, OAI-SearchBot: reachable, Claude-User: reachable, PerplexityBot: reachable |
| robots.txt AI crawler policy | Pass, 1 of 1 | AI search crawlers: allowed in 3 of 3 checks (3 crawlers on 1 page). AI training crawlers: allowed in 2 of 2 checks (2 crawlers on 1 page), not scored. |
| robots.txt agent-user policy | Pass, 1 of 1 | No applicable crawl or usage restriction found for 3 user-triggered agents (chatgpt-user, claude-user, perplexity-user) on 1 public page: https://adm.com/. Declared policy only; |
| Content without JavaScript | Pass, 5 of 5 | Homepage: 3802 chars, semantic headings (1 H1 + 8 H2s + 9 H3s), 13.0% content ratio. 5 of 5 sampled inner pages have text without JavaScript. |
| Homepage not hidden from search | Pass, 1 of 1 | No noindex on the homepage: no robots, googlebot or bingbot meta tag and no X-Robots-Tag header hides it from search. |

## What it can read, and what it can do

The reading layer is what an assistant takes away from the pages: a text file written for it, markdown on request, structured data about the company, a sitemap. The act layer is whether it can do anything through a published interface rather than by clicking through the site.

| Check | Result | What Ora saw |
| --- | --- | --- |
| llms.txt exists | Pass, 1 of 1 | Found the llms.txt at https://adm.com/llms.txt. |
| llms.txt formatting | Pass, 2 of 2 | The llms.txt is well-formatted: 131 lines with markdown links, 7,408 characters in total. |
| Markdown agent docs | Fail, 0 of 1 | Missing markdown content negotiation. Homepage returned text/html when probed with Accept: text/markdown (expected text/markdown), and none of the well-known root paths (/llms.md, /auth.md, /agents.md, /developers.md). |
| Bot-UA markdown serving | Fail, 0 of 1 | No probed bot User-Agent (ChatGPT-User, Claude-User, Perplexity-User) receives markdown when requesting HTML. Optional: detect AI-bot UAs server-side and serve them a markdown representation directly. |
| JSON-LD structured data | Fail, 0 of 2 | No JSON-LD structured data found on homepage |
| Organization schema completeness | Fail, 0 of 1 | No JSON-LD found - Organization schema missing |
| Sitemap exists | Pass, 1 of 1 | Valid sitemap found at https://www.adm.com/en-us/sitemap.xml with 1949 entries |
| Metadata completeness | Pass, 1 of 1 | All metadata signals present: canonical URL, lang="en-us", og:image, og:type |
| Page token budget | Pass, 1 of 1 | All 6 measured pages fit an agent context budget (largest ~2K tokens) |

| Check | Result | What Ora saw |
| --- | --- | --- |
| MCP server / manifest | Did not apply, 0 of 10 | No MCP server or manifest found |
| MCP well-known discovery | Fail, 0 of 2 | No MCP server URL discovered |
| Public API with reachable endpoints | Did not apply, 0 of 8 | No publicly reachable API surface detected (REST and GraphQL both absent or auth-gated) |
| Public API/docs linked from homepage | Did not apply, 0 of 4 | No public API or documentation page linked from homepage |
| OpenAPI spec published | Did not apply, 0 of 8 | No OpenAPI/Swagger specification found |
| Developer portal | Did not apply, 0 of 5 | No developer portal found |
| OAuth 2.0 support | Pass, 5 of 5 | OpenID Connect discovery endpoint found at https://adm.com |
| Scoped permissions | Did not apply, 0 of 5 | No declared OAuth scopes, security schemes, or scoped-permission documentation found |
| CLI tool available | Did not apply, 0 of 3 | No CLI tool found |
| WebMCP support | Fail, 0 of 8 | No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 2 of 2 same-origin script bundle(s) for modelContext registrations) |

| Check | Result | What Ora saw |
| --- | --- | --- |
| Brand name discoverability | Pass, 3 of 3 | adm.com ranks #2 for "ADM food ingredients" |
| Developer resource discoverability | Did not apply, 0 of 4 | Agent searched for "adm" developer resources but found nothing relevant |

The six payment checks did not apply on this read: Ora did not read the site as a shop.

## Three fixes to hand to the web team

Ora estimates how many points each open check would return. These are the largest on this read, in Ora's words where it gave them, so a leader can hand the list over without translating it.

1.  WebMCP support, worth about 17.8 points by Ora's estimate: No WebMCP support detected - no document.modelContext / navigator.modelContext usage found (scanned 2 of 2 same-origin script bundle(s) for modelContext registrations).
2.  Product + docs MCP coverage, worth about 4.4 points by Ora's estimate: This bonus needs two MCP servers: one for your product so agents can take actions, and a separate one for your documentation so agents can answer questions from your docs.
3.  ARD discovery, worth about 3.7 points by Ora's estimate: No /.well-known/ard.json, no same-site rel="ard" link, and no legacy /.well-known/ai-catalog.json.

## Our read

ADM has made its website easy for AI agents to read and has given them nothing to do. The door is open: all four test agents reached adm.com, and robots.txt lets search, training and user-triggered agents in, so Access reads 20 of 28. The reading is good too. The home page gives 3,802 characters without JavaScript under clean headings, all 5 sampled inner pages read the same way, a sitemap lists 1,949 entries, a well-formatted llms.txt of 131 lines sits at the root, and every metadata tag Ora checks is present. The one gap is structured data: there is no JSON-LD, so no Organization record tells an agent who ADM is. The act layer is where the score stops. OpenID Connect discovery answers, but Ora found no public API, MCP server, OpenAPI specification or developer portal, and Usability reads 6 of 15. The fix worth most is WebMCP, about 17.8 points. A C at 56: the shop window is spotless and the counter has no one behind it.

## Test your own site

Run the same scan on your own domain at [ora.ai](https://ora.ai/?utm_source=amireadyforagents.com&utm_medium=referral&utm_campaign=check). The score, the layers and the fixes on this page come from its public result for adm.com; a scan of a public site takes a few minutes and needs no account.

-   [Scan your domain on Ora](https://ora.ai/?utm_source=amireadyforagents.com&utm_medium=referral&utm_campaign=check)The same checks, the same scoring, on your own site.
-   [The self-check, 18 questions](https://amireadyforagents.com/self-check)What to ask for, in business terms, before the scan.
-   [All the 360 checks](https://amireadyforagents.com/blog)The other companies in this series, newest first.

## Sources

1.  [Ora report for adm.com](https://ora.ai/score/adm.com?utm_source=amireadyforagents.com&utm_medium=referral&utm_campaign=check) (ora.ai/score/adm.com), read 20 Nov 2026. Vendor claim.

Last reviewed 20 November 2026

Reviewed 20 November 2026. [1 source](#sources), each with the day it was read.
