AI Readiness AuditRef. APM-17588A8A · Confidential
Ledger API
An independent assessment of whether the Ledger API specification is ready for AI-assisted integration and autonomous agents, prepared for Formance.
60/100
Significant gaps
Functional for AI-assisted builds.
Not ready for autonomous agents.
Not ready for autonomous agents.
Reach AI-ready by Phase 1; resolve all findings → 100 · AI-ready
F
D
C
B
A
60
055708085100
F · Not readyD · Significant gapsC · Needs workB · Mostly readyA · AI-ready
0
Critical blockers : no findings stop an operation group outright
1771
Total instances: 0 critical, 187 high, 746 medium, 838 low
66
Rule groups across 4 pillars: 0 critical, 187 high sev. instances
Executive summary
Your Ledger API scores 60.4 out of 100, reflecting significant gaps in standards compliance and documentation readiness for AI. The API is functional for AI-assisted builds but not ready for autonomous agents. The SDK readiness for AI stands at 78.4, while the MCP readiness shows significant gaps at 57.8. To improve your API's effectiveness, address the 187 high findings identified during the audit.
Readiness by pillar
Significant gaps
60 / 100
FoundationThe spec itself
55/100
Standards Compliance
OpenAPI validity, structural correctness, specification conformance, and import linting: can machines trust your spec?
55Not ready
Build Time ReadinessAI writes the code
66/100
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
54Not 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
78Needs work
Runtime ReadinessAgents make the calls
58/100
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
58Significant gaps
Score projection · what fixing each phase unlocks
Todaycurrent score
Phase 1fix highs
Phase 2+ fix mediums & lows
About this report. We evaluated the Ledger 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
55 / 100
Active risk · Standards compliance
Fix Specification Violations to Prevent Breaks
You must correct seven high-severity specification violations to ensure toolchains, SDK generation, and downstream integrations function correctly.
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
66 / 100
Active risk · Documentation readiness for AI
AI readers misinterpret Ledger API details
You must provide comprehensive descriptions for parameters and operations to ensure accurate understanding.
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
Elevated risk · SDK readiness for AI
SDKs return incorrect types and formats
You should address the ambiguous schema layer to improve the accuracy of generated SDKs and 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
58 / 100
Elevated risk · MCP readiness
Agents misinterpret API operations and semantics
You must address confusable operations and misleading descriptions to ensure safe execution in the Ledger API.
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