---
title: "Waymark report for together.ai"
canonical: "https://waymark.genedai.me/score/together.ai"
last-updated: "2026-08-24T02:20:24.527Z"
---

# Waymark report for together.ai

Waymark scored together.ai 81.2/100 (B) on 24 Aug 2026.
Score: 81.2/100 — Usable with gaps
Scanned: 2026-08-24T02:20:24.527Z
Canonical report: https://waymark.genedai.me/score/together.ai

## Layer breakdown

- Discovery: 14.8/20 (12 of 18 eligible checks passed)
- Access: 24.7/30 (17 of 24 eligible checks passed)
- Usability: 33.5/40 (9 of 12 eligible checks passed)
- Payments: N/A (excluded from the denominator)

## Findings

### 1. AGENTS.md

- Layer: discovery
- Result: failed
- Evidence: agents.md status 404.
- Recommended fix: Publish /agents.md with agent-oriented usage notes.

### 2. Well-known AI catalog

- Layer: discovery
- Result: failed
- Evidence: No ai-plugin.json or ai-catalog.json.
- Recommended fix: Add /.well-known/ai-plugin.json or /.well-known/ai-catalog.json.

### 3. OpenAPI / Swagger link

- Layer: access
- Result: failed
- Evidence: No OpenAPI/Swagger link in HTML.
- Recommended fix: Link to an OpenAPI or Swagger document from the homepage.

### 4. CORS / API hint

- Layer: access
- Result: partial
- Evidence: No CORS header or obvious API path.
- Recommended fix: If you expose an API, send Access-Control-Allow-Origin for intended clients.

### 5. OAuth / OIDC well-known

- Layer: access
- Result: failed
- Evidence: No oauth-authorization-server or openid-configuration.
- Recommended fix: Publish /.well-known/openid-configuration or oauth-authorization-server if you authenticate agents.

### 6. AI crawlers not blanket-blocked

- Layer: access
- Result: failed
- Evidence: robots.txt Disallow: / for * or common AI bots.
- Recommended fix: Avoid Disallow: / for GPTBot, ClaudeBot, PerplexityBot unless intentional.

### 7. MCP SSE / HTTP hint

- Layer: usability
- Result: failed
- Evidence: No MCP/SSE hint on the homepage.
- Recommended fix: Document an MCP HTTP or SSE endpoint.

### 8. llms-full.txt

- Layer: discovery
- Result: failed
- Evidence: llms-full.txt status 404.
- Recommended fix: Optionally publish /llms-full.txt for one-shot ingest.

### 9. HTTP Link header

- Layer: discovery
- Result: failed
- Evidence: No rel=sitemap|describedby|api-catalog|alternate on homepage.
- Recommended fix: Send RFC 8288 Link headers for related machine resources.

### 10. /index.md fallback

- Layer: access
- Result: failed
- Evidence: index.md status 404.
- Recommended fix: Serve a markdown homepage at /index.md.

### 11. MCP Apps UI hint

- Layer: usability
- Result: failed
- Evidence: No MCP Apps hint (N/A unless you return UI).
- Recommended fix: If you return UI, declare io.modelcontextprotocol/ui resources.

### 12. ai-plugin.json

- Layer: discovery
- Result: failed
- Evidence: No /.well-known/ai-plugin.json.
- Recommended fix: Optionally publish a plugin-style capability manifest.

### 13. API catalog linkset

- Layer: discovery
- Result: failed
- Evidence: API present without RFC 9727 catalog.
- Recommended fix: Add /.well-known/api-catalog pointing at OpenAPI.

### 14. change-password well-known

- Layer: access
- Result: failed
- Evidence: Login surface without /.well-known/change-password.
- Recommended fix: If users have passwords, serve /.well-known/change-password.

### 15. CLI tool

- Layer: usability
- Result: failed
- Evidence: No CLI mention.
- Recommended fix: Publish an official CLI.

### 16. RSS or Atom document

- Layer: access
- Result: partial
- Evidence: No /feed or /rss.xml document.
- Recommended fix: Publish /rss.xml or /atom.xml.

## Interpretation

Public technical snapshot; not a guarantee of task completion. Private and authenticated workflows are outside this scan. Cite scanned_at and the canonical report URL; the URL serves the latest completed snapshot and can change after a rescan.

The official Waymark score is Discovery 20 / Access 30 / Usability 40 / Payments 10. N/A and scanner-error checks drop out of the denominator; they are not scored as failures. An observed agent journey is supporting evidence and does not change the numeric score.