Nvidianvidia.com
Nvidia's API program shows solid fundamentals in usability and security, but partners and AI agents face two critical gaps: there is no machine-readable discovery entry point (no llms.txt or equivalent), and the docs experience lacks a clear quickstart or code examples — meaning new partners and the coding agents they rely on hit a dead end before writing a single line of integration code. Closing these two gaps should be the immediate priority to enable self-serve partner onboarding and make the API surface legible to AI-driven development workflows.
API DesignA clean, typed, well-governed API contract agents can reason about0 pass3 warn0 fail64C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Schema coverage & depthvia sdk | 12.5/25 | no .d.ts found. Investigated: sdk 50%. Fix: Ship type declarations in the published package (e.g. bundle .d.ts files / add a py.typed marker). | Typed, complete request/response schemas are what make agent function-calling possible. |
| warn | Security & governance hygienevia sdk | 10/15 | Not idiomatic: 0 formatter diff(s), 29 linter error(s). Investigated: sdk 67%, wellknown 0%. Fix: Run the native formatter and fix linter errors so the generated code emits with zero diffs and zero errors. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| warn | Example coveragevia sdk | 5/10 | README is present but has no runnable quickstart. Investigated: sdk 50%, docs 0%. Fix: Add a runnable quickstart (install + first authenticated call) to the README. | Examples carry shape semantics schemas under-specify — for humans and agents alike. |
| na | Machine-readable, versioned contract | —/25 | No surface produced evidence for this capability in this run. | A current OpenAPI version with a declared versioning scheme lets agents reason about the contract. |
| na | Auth declared & discoverable | —/25 | No surface produced evidence for this capability in this run. | Agents can only call an API when they can determine its auth posture — a declared scheme, or an explicit statement that none is required. |
Developer ExperienceThe context both developers and agents need to integrate fast — onboarding, code samples, complete descriptions and worked examples1 pass0 warn2 fail55D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Self-service developer portalvia docs | 29/29 | Signup page at https://www.nvidia.com/en-us/support/ (client-rendered, so its contents couldn't be classified); free tier or sandbox is documented in pricing/docs. Investigated: docs 100%. | A first call without a human in the loop — self-serve credentials, a free tier, or an API that needs none. |
| fail | Quickstart presentvia docs | 0/25 | No quickstart or getting-started page found at the conventional docs paths, so new developers and agents have no obvious first step. Investigated: docs 0%. Fix: Publish a single-page quickstart that goes from zero to a first successful API call. | A quickstart is the fastest path from landing page to first successful call. |
| fail | Code samples in docsvia docs | 0/18 | No code samples detected across 1 sampled docs pages, so a coding agent gets no ready-to-use examples. Investigated: docs 0%. Fix: Add copy-pasteable code samples to API reference and quickstart pages. | Multi-language samples shorten time-to-first-call. |
| na | Description completeness | —/15 | No surface produced evidence for this capability in this run. | Complete descriptions are the context humans and agents need to use endpoints. |
| na | Changelog published | —/13 | No surface produced evidence for this capability in this run. | A published changelog lets partners track changes without surprise. |
Agent DiscoveryPartners and their agents can find your APIs — llms.txt, registries, crawlable and reachable docs1 pass1 warn1 fail63C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Registry & SDK presencevia docs | 28/28 | Indexed on Context7 (websites/nvidia_deeplearning_tensorrt, 11839 snippets). Investigated: docs 100%, sdk 50%, cli 0%. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
| warn | Crawlable / AEOvia wellknown | 9/12 | Sitemap has 49 entries but no lastmod values, so crawlers can't tell what changed recently. Investigated: wellknown 75%. Fix: Add accurate <lastmod> values to sitemap entries — AI-powered search uses them to prioritize crawling. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
| fail | llms.txt present, valid & comprehensivevia docs | 0/30 | No llms-full.txt was found at any candidate origin, so agents can't grab your full docs in one fetch. Investigated: docs 0%, sdk 0%. Fix: Publish a concatenated, agent-readable copy of your documentation at /llms-full.txt on your docs site. | A valid, comprehensive llms.txt is the machine-readable entry point for agents. |
| na | Docs reachable, not hard auth-gated | —/30 | No surface produced evidence for this capability in this run. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs0 pass3 warn0 fail55D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| warn | Agent instructions file (AGENTS.md)via sdk | 5/10 | No agents.md or skill.md context file found (nice-to-have for agent operation). Investigated: sdk 50%, wellknown 0%. Fix: Add an agents.md or skill.md describing how an agent should use this SDK (auth setup, key operations, gotchas). | An AGENTS.md gives coding agents explicit setup, auth, and usage instructions to interpret and operate the API — beyond llms.txt's link index. |
| warn | Docs structured datavia docs | 4/8 | Only OpenGraph/meta tags across 1 assessed pages — no JSON-LD for AI answer engines to cite. Investigated: docs 50%. Fix: Emit JSON-LD with Article/TechArticle @type and dateModified in the rendered docs head. | Structured data (JSON-LD/schema.org) on docs pages gives agents an unambiguous parse target and is what answer engines cite. Detected on the JS-rendered head (Firecrawl) for a bounded page budget, so JS-injected JSON-LD is now caught; pages we can't render are excluded rather than failed. |
| warn | Description consistency across surfaces | 1.1/7 | Mean pairwise description similarity across 2 surfaces (docs, sdk) is 5% (threshold 35% for full credit). Fix: Align the API description across spec, docs, and SDK so an agent reading any one surface gets the same story. | Every surface tells the same story about what the product is. |
| na | Machine-readable errors (RFC 9457) | —/28 | No surface produced evidence for this capability in this run. | RFC 9457 problem details and a documented error-code inventory let agents parse failures without burning tokens. |
| na | Operation purpose clarity | —/25 | No surface produced evidence for this capability in this run. | Agents select the right endpoint from its summary + operationId; clear, named operations make tool-selection reliable — the strongest driver of correct tool choice. |
| na | Agent-navigable, token-efficient docs | —/22 | No surface produced evidence for this capability in this run. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them1 pass2 warn0 fail78B
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Idempotency documentedvia sdk | 27/27 | Built-in retry machinery is present (grep-derived). Investigated: sdk 100%. | Documented idempotency lets agents retry safely. |
| warn | Sandbox separationvia sdk | 10/20 | No test-mode flag or sandbox environment is exposed. Investigated: sdk 50%. Fix: Expose a test-mode flag or sandbox environment so agents can exercise the SDK safely. | An isolated environment lets agents exercise destructive operations safely. |
| warn | Runnable collection with test scriptsvia sdk | 4.5/9 | README is present but has no runnable quickstart. Investigated: sdk 50%, platform 0%. Fix: Add a runnable quickstart (install + first authenticated call) to the README. | A public, maintained collection with assertions is runnable truth agents validate against. |
| na | Rate-limit signaling | —/22 | No surface produced evidence for this capability in this run. | Machine-readable rate-limit headers let agents throttle adaptively. |
| na | Pagination documented & consistent | —/22 | No surface produced evidence for this capability in this run. | Consistent, documented pagination lets agents traverse collections. |
Resources Discovered
The public resources we found for Nvidia — the evidence behind the score. All discovered from public sources; nothing here requires access to your systems.
| Agent hints | Context7 (11,839) |
|---|