AI Readiness Audit
Ref. APM-E258930F · Confidential

Knock API

An independent assessment of whether the Knock API specification is ready for AI-assisted integration and autonomous agents, prepared for Knock.

Prepared for
Knock
Subject
Knock API v1.0
Scope
118 operations · 4 pillars · 3 groups
Date
October 2026
46/100
Not ready
Functional for AI-assisted builds.
Not ready for autonomous agents.
Reach Mostly ready by Phase 1; resolve all findings → 100 · AI-ready
Import blocked: SDK, docs, and MCP generators will refuse this spec

The validation engine found 1 blocking violation: The definition for path parameter used in the path URL does not exist.. Import tools reject the specification outright until it is fixed, so nothing downstream can be generated regardless of the other pillar scores. While this gate is open, the Standards Compliance score is capped at 40 and every AI pillar weights standards at 60% (normally 30%). Fixing the blocker in Phase 1 lifts the caps; the score projection below shows what that unlocks.

39
Critical blockers stopping entire operation groups for agents
2178
Total instances: 39 critical, 43 high, 926 medium, 1170 low
45
Rule groups across 4 pillars: 39 critical, 43 high sev. instances
Executive summary

Your API cannot generate SDKs, documentation, or MCPs due to one blocking violation in the specification. The overall composite score of 45.5 out of 100 indicates significant weaknesses, particularly in standards compliance at 36.9 and documentation readiness for AI at 50.5. While the API is functional for AI-assisted builds, it is not ready for autonomous agents, as evidenced by 39 critical findings and 43 high findings across 45 rule groups. Addressing the blocking violation is the most urgent action to improve your API's readiness.

Readiness by pillar
Not ready 46 / 100
FoundationThe spec itself
37/100
Standards Compliance
OpenAPI validity, structural correctness, specification conformance, and import linting: can machines trust your spec?
37Not ready
Build Time ReadinessAI writes the code
51/100
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
51Not 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
51Not ready
Runtime ReadinessAgents make the calls
47/100
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
47Not ready
Score projection · what fixing each phase unlocks
Todaycurrent score
46
Not ready
Phase 1fix criticals
83
Mostly ready
Phase 2+ fix highs
91
AI-ready
Phase 3+ fix mediums & lows
100
AI-ready
About this report. We evaluated the Knock 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

What these gaps cost you in production

4 failure modes across 3 groups, each driven by your audit scores. Several are active risks today.

Foundation The spec itself 37 / 100
Active risk · Standards compliance
Path parameter definitions are missing
You must define the path parameters in the Operation Objects to prevent toolchain failures and integration issues.
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 51 / 100
Active risk · Documentation readiness for AI
AI readers misinterpret API due to documentation gaps
You must improve API descriptions and examples to ensure accurate understanding and prevent flawed assumptions.
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
Active risk · SDK readiness for AI
SDKs generate incorrect types and formats
You should refine the schema layer to ensure accurate AI-generated integration code and SDKs.
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 47 / 100
Active risk · MCP readiness
Agents misidentify operations due to confusion
The Knock API's operation names and descriptions fail to provide clear guidance, risking incorrect execution.
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

What's inside the full report

Unlock the full report

Book a free call to view the full report and the roadmap our team recommends to upgrade your developer and agentic experience.

Book a free call to view the full report