AI Readiness AuditRef. APM-16F03835 · Confidential
what3words API
An independent assessment of whether the what3words API specification is ready for AI-assisted integration and autonomous agents, prepared for what3words.
92/100
AI-ready
Ready for AI-assisted builds.
Ready for autonomous agents.
Ready for autonomous agents.
Resolve all findings (through Phase 1) → score reaches 100 · AI-ready
F
D
C
B
A
92
055708085100
F · Not readyD · Significant gapsC · Needs workB · Mostly readyA · AI-ready
0
Critical blockers : no findings stop an operation group outright
187
Total instances: 0 critical, 0 high, 76 medium, 111 low
20
Rule groups across 4 pillars: 0 critical, 0 high sev. instances
Executive summary
what3words API scores 91.9/100: AI-ready · Grade A. The weakest pillar is Documentation readiness for AI at 82; the strongest is Standards compliance at 97. We recorded 187 finding instances: 0 critical, 0 high, 76 medium, and 111 low. Ready for AI-assisted builds. Ready for autonomous agents. Every finding lives in the specification, and the roadmap in this report orders the fixes by impact; resolving them projects the score to 100/100.
Readiness by pillar
AI-ready
92 / 100
FoundationThe spec itself
97/100
Standards Compliance
OpenAPI validity, structural correctness, specification conformance, and import linting: can machines trust your spec?
97AI-ready
Build Time ReadinessAI writes the code
87/100
Documentation Readiness for AI
Descriptions that say when to use an operation, examples that pin down every shape: whether an AI can learn the truth of your API from what you publish
82Mostly ready
SDK Readiness for AI
Clean types, predictable naming, correct formats: whether production-grade client code can be generated from your spec, by SDK pipelines and AI coding assistants alike
91AI-ready
Runtime ReadinessAgents make the calls
94/100
MCP Readiness
Whether your operations survive being turned into tools: distinct names, descriptions that carry what an agent must know, safe invocation semantics, auth, error recovery, and context budget
94AI-ready
Score projection · what fixing each phase unlocks
Todaycurrent score
Phase 1fix mediums & lows
About this report. We evaluated the what3words API specification against thousands of deterministic rules we have refined over twelve years of building API tooling, supplemented by AI-based analysis. Every finding is reproducible from the spec itself, scored consistently, and paired with a concrete fix.
What's at stake
Your readiness posture is strong
All 4 readiness pillars are managed. These are the failure modes your spec quality protects you from, and the ones to watch as agent adoption grows.
Foundation
The spec itself
97 / 100
Managed · Standards compliance
Minor spec violations affect integrations
We found two medium issues that could disrupt toolchains and SDK generation, but overall compliance is strong.
22→29
code quality score out of 40: the lift consumers achieve when the underlying spec is clean and standards-compliant
APIMatic Context Plugins research · Series B · June 2026
Build Time Readiness
AI writes the code
87 / 100
Managed · Documentation readiness for AI
Improve API documentation clarity now
You provide sufficient documentation for the what3words API, but refining examples and descriptions will assist AI readers in understanding the API better.
74%
of developers name missing or unclear documentation as the top reason they abandon an API. AI readers are stricter: what a human would ask about, an AI assumes.
APIMatic Developer Experience research · June 2026
Managed · SDK readiness for AI
SDKs generate incorrect types and formats
We found that the schema layer's ambiguity leads to some integration code issues, which you can refine.
0
fabricated API constructs when a coding assistant was grounded in an AI-ready spec. Ambiguity in the spec is what triggers hallucinated integration code
APIMatic Context Plugins research · 6 APIs · 3 models · June 2026
Runtime Readiness
Agents make the calls
94 / 100
Managed · MCP readiness
Autonomous Agents Need Minor Adjustments
The what3words API functions well overall, but agents struggle with tool names and context budgets. Refining these elements will improve execution safety.
65%
reduction in token consumption when agent tools are grounded in authoritative API context. Bloated or confusable tools consume up to 3.3× more.
APIMatic Context Plugins research · Series A · June 2026
The evidence numbers come from our controlled research: 6 experiments across 3 models, 6 commercial APIs, and 3 languages. We derive each card's risk status from this API's pillar scores. Full methodology at apimatic.io.
Contents