AI Readiness Audit
Ref. APM-49D1C882 · Confidential

Demand API

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

Prepared for
Booking.com
Subject
Demand API v3.1
Scope
39 operations · 4 pillars · 3 groups
Date
October 2026
35/100
Not ready
Gaps for AI-assisted builds.
Not ready for autonomous agents.
Reach AI-ready by Phase 2; resolve all findings → 100 · AI-ready
Import blocked: SDK, docs, and MCP generators will refuse this spec

The validation engine found 1 blocking violation: Reference could not be resolved.. 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.

2
Critical blockers stopping entire operation groups for agents
3537
Total instances: 2 critical, 305 high, 999 medium, 2231 low
42
Rule groups across 4 pillars: 2 critical, 305 high sev. instances
Executive summary

Your API cannot generate SDKs, documentation, or MCPs due to a blocking violation in the specification. The overall composite score of 34.9 out of 100 indicates significant readiness issues, with standards compliance at 23.8 and documentation readiness for AI at 42.5. The audit identified 305 high findings and 2 critical findings across 42 rule groups, revealing substantial gaps for AI-assisted builds and a lack of readiness for autonomous agents. Addressing the blocking violation is the most urgent action to take for any progress.

Readiness by pillar
Not ready 35 / 100
FoundationThe spec itself
24/100
Standards Compliance
OpenAPI validity, structural correctness, specification conformance, and import linting: can machines trust your spec?
24Not ready
Build Time ReadinessAI writes the code
42/100
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
43Not 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
41Not ready
Runtime ReadinessAgents make the calls
38/100
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
38Not ready
Score projection · what fixing each phase unlocks
Todaycurrent score
35
Not ready
Phase 1fix criticals
51
Not ready
Phase 2+ fix highs
92
AI-ready
Phase 3+ fix mediums & lows
100
AI-ready
About this report. We evaluated the Demand 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 24 / 100
Active risk · Standards compliance
Resolve References to Prevent Breakage
You must resolve references in the Demand API specification to avoid breaking toolchains and downstream integrations.
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 42 / 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 must clarify the schema layer to ensure accurate AI-generated integration code.
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 38 / 100
Active risk · MCP readiness
Agents cannot execute Demand API safely
The operation descriptions lack necessary content, success responses are missing, and request bodies are improperly structured, which jeopardizes API functionality.
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