Trengotrengo.com
Trengo's API program shows strength in agent understanding and context quality, but two areas are holding back partner activation: the developer onboarding experience is effectively closed — signup is sales-gated and there is no quickstart — meaning partners and their AI agents cannot get hands-on without a human conversation. Secondary to that, the lack of documented idempotency and retry guidance creates operational risk once partners do integrate.
API DesignA clean, typed, well-governed API contract agents can reason about3 pass0 warn0 fail100A+
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Schema coverage & depthvia sdk | 25/25 | package.json "types" → dist/types/src/entry.esm.d.ts. Investigated: sdk 100%. | Typed, complete request/response schemas are what make agent function-calling possible. |
| pass | Security & governance hygienevia sdk | 15/15 | Code is formatter-clean with zero linter errors and zero style warnings. Investigated: sdk 100%, wellknown 0%. | No leaked secrets, no critical lint violations, no OWASP API Top-10 spec smells, and a published vulnerability-disclosure channel. |
| pass | Example coveragevia sdk | 10/10 | README is present and includes a runnable quickstart. Investigated: sdk 100%. | 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 examples0 pass0 warn2 fail40F
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| fail | Self-service developer portalvia docs | 0/29 | The signup page is sales-gated (contact-sales / request-access language detected), so an agent can't self-serve. Investigated: docs 0%. Fix: Add a public self-service signup path so developers (and coding agents) can integrate without sales contact. | 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. |
| na | Code samples in docs | —/18 | No surface produced evidence for this capability in this run. | 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 pass3 warn0 fail68C
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Docs reachable, not hard auth-gatedvia docs | 30/30 | All 1 pages are publicly accessible. Investigated: docs 100%. | Agents can only index and fetch docs they can reach — past auth gates and over correct HTTP semantics. |
| warn | llms.txt present, valid & comprehensivevia docs | 22.5/30 | No llms-full.txt was found at any candidate origin, so agents can't grab your full docs in one fetch. Investigated: docs 75%, 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. |
| warn | Crawlable / AEOvia wellknown | 6/12 | No sitemap found via robots.txt or /sitemap.xml on the docs host, so AI search engines have no crawl map for your docs. Investigated: wellknown 50%. Fix: Publish an XML sitemap and reference it from robots.txt. | Bots allowed plus a fresh sitemap make docs findable by agent crawlers. |
| warn | Registry & SDK presencevia sdk | 2.3/28 | No official SDKs were found on npm, PyPI, or GitHub, so agents must call the API by hand. Investigated: sdk 8%, docs 0%, cli 0%, mcp 0%, wellknown 0%. Fix: Publish at least one official SDK and list it on the org's docs site or package registries. | Listing in MCP registries and publishing SDKs puts the API where agents and their tooling look. |
Agent UnderstandingAgents can correctly interpret your APIs — machine-readable errors, consistent descriptions, structured data, parseable docs1 pass1 warn0 fail87A
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| pass | Agent-navigable, token-efficient docsvia docs | 22/22 | All 1 pages contain server-rendered content. Investigated: docs 100%. | Server-rendered, clean, small-footprint docs are what an agent can cheaply fetch and parse correctly. |
| 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. |
| 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 | Docs structured data | —/8 | No surface produced evidence for this capability in this run. | 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. |
| na | Description consistency across surfaces | —/7 | Only 0 surface description(s) with ≥6 tokens available; need at least 2 to compare. | Every surface tells the same story about what the product is. |
Agent UsabilityAgents have the context to use your APIs reliably, not just find them1 pass1 warn1 fail52D
| Signal | Points | Findings | Rationale | |
|---|---|---|---|---|
| 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. |
| pass | Runnable collection with test scriptsvia sdk | 9/9 | README is present and includes a runnable quickstart. Investigated: sdk 100%, platform 0%. | A public, maintained collection with assertions is runnable truth agents validate against. |
| fail | Idempotency documentedvia sdk | 0/27 | No built-in retry machinery was found; transient failures are not retried. Investigated: sdk 0%. Fix: Add built-in retry support (retry transient/retryable status codes with backoff) so consumers do not have to implement it themselves. | Documented idempotency lets agents retry safely. |
| 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. |