API Evangelist/Talks/Events
APIdays Paris · CNIT Forest, La Défense · 1–3 December 2026

What the APIdays Paris will teach you, and how the Kin Score measures it

I read every API session on the Paris agenda, all three days, across ten tracks of FOST Paris (Apidays, GenerationAI, GreenIO, the API Standards Conference, the Europe API Conference, APIOps, ContextCon and MCP Summit, and more), and mapped each one to the Kin Score facet it speaks to. Agent Readiness leads again, and this year the talks go past having an MCP server to whether its tools are any good. The speakers are telling you what an API needs to be. The Kin Score is how I measure whether an API actually is that, across the whole catalog.

Pick a facet to see who is talking about it, then go and find them in the room.

339sessions mapped
10tracks
108on agent readiness
26on accountability
23on MCP servers
I'm speaking: Real-World API & Integration Challenges · 12-01, 09:55, Davidia 1/2 (APIOps Conference Paris 2026)Group work: What's Blocking API & Integration Success? · 12-01, 11:00, Davidia 1/2 (APIOps Conference Paris 2026)Group work: From API Challenges to Action Plans · 12-01, 14:15, Davidia 1/2 (APIOps Conference Paris 2026)Open Discussion: The Toughest API Questions We Still Face · 12-01, 16:30, Davidia 1/2 (APIOps Conference Paris 2026)Agents Inherit Your Governance — Whether You Meant Them To or Not · 12-02, 17:00, Aubépine 1 (Apidays)You Cannot Bolt Agent Readiness Onto Ungoverned APIs · 12-02, 17:00, Baobab 3 (Apidays)What Europe's Government APIs Look Like From the Outside-In · 12-03, 09:15, Aubépine 1 (Europe API Conference)

The facets

Each card pairs what the speakers are saying with what the Kin Score checks. Click a card to filter the agenda below. Counts include every talk that touches a facet; "primary" is the facet a talk is mostly about.

Composite facet Conditional facet (applies only where relevant) Standalone score Not measured yet
Agent Readiness108 talks · 65 primary What you will hearOkta on giving every agent its own identity, Postman and Axway on securing, governing and observing agent traffic through a gateway, Bump.sh and Meilisearch on building MCP servers for agents instead of wrapping the API, WunderGraph on letting the model decide while code moves the data, Bayes Impact on where tool calls break mid-stream. What the Kin Score measuresA separate score from the composite. It checks whether an agent can drive the API without a human filling in the gaps: a published OpenAPI, an MCP server, machine-readable auth, idempotency, stable errors, rate-limit headers, agent skills, a well-known catalog, protected resource metadata, and bound vs bearer credentials. How the Kin Score measures Agent Readiness on APIs.io →
Contract Quality56 talks · 24 primary What you will hearThe API Standards Conference: OpenAPI in the age of AI, JSON Schema semantics and validation, The New York Times on AsyncAPI as the contract for every event, Specmatic and Choreo Labs on Arazzo workflows for agents and humans, Apollo on GraphQL variables meeting JSON Schema. What the Kin Score measuresThe depth of the OpenAPI, AsyncAPI, GraphQL and JSON Schema a provider actually publishes: schemas, examples, descriptions, versions. 25% of the composite, its largest facet. How the Kin Score measures it on APIs.io →
Contract Governance50 talks · 25 primary What you will hearOsaango on why API management isn't enough, adorsys turning API guidelines into governance skills, oasdiff against an LLM on breaking changes, Boomi's governance playbook for AI, Mobioos on a governed context layer, JSON Schema standardisation at the IETF. What the Kin Score measuresThe artifacts that constrain a contract: published rulesets, vocabulary, declared conformance, overlays. It reads what a ruleset declares, not the result of running it. How the Kin Score measures it on APIs.io →
Operational Transparency32 talks · 15 primary What you will hearThales and Akamai on token fraud, agent-era attacks and runtime defence, Swapcard evolving a schema without breaking anyone, WSO2 on supply-chain security, BNP Paribas on offensive security in the AI era. What the Kin Score measuresWhether a provider publishes how its API behaves in production: rate limits, a status page, a change log, a deprecation policy, a security disclosure path. How the Kin Score measures it on APIs.io →
Regulatory Posture26 talks · 3 primary What you will hearPwC on auditable agent memory in regulated industries, ABN Amro on sovereignty as architecture, Morgan Stanley on AI governance for financial regulators, plus the Europe API Conference's government track. What the Kin Score measuresApplied only in regulated industries: consent-scoped authorization, a published security and disclosure posture, terms and privacy as a legal basis, and conformance to the industry's data standard. How the Kin Score measures it on APIs.io →
Access Clarity28 talks · 11 primary What you will hearADEO on a stolen key and a runaway bill, Kong and YOWE on AI spend and finops, Wise on selling the outcome rather than the endpoint, the Boomi and Platformable State of the API Economy panel, the French operators on mobile network APIs. What the Kin Score measuresWhat it costs, what you are allowed to do, and how you get in: plans, pricing, sign-up, terms, privacy, a finops mapping, trust and compliance. How the Kin Score measures it on APIs.io →
Developer Ergonomics32 talks · 11 primary What you will hearPostman's API and MCP bootcamp and its agents-run-API-engineering talk, Microsoft on designing for developers who build through coding agents, adorsys on developer experience as strategy, Specmatic on harness engineering with smaller models. What the Kin Score measuresHow quickly someone can get started: SDKs, CLI, portal, getting-started guide, sandbox or console, MCP server, clear auth documentation. How the Kin Score measures it on APIs.io →
Discoverability22 talks · 7 primary What you will hearSAP on Open Resource Discovery, Geonovum on API and AI tooling across Dutch government, an open business capability map for API catalogues, and the APIOps day asking why we still don't know which APIs we have. What the Kin Score measuresWhether the API can be found and understood from machine-readable metadata alone: apis.json completeness, tags, identity signals. How the Kin Score measures it on APIs.io →
Open Source Surface15 talks · 6 primary What you will hearThe AsyncAPI Initiative on two supply-chain incidents in open-source CI/CD, FINOS on open collaboration in finance, Maersk on vendor dependency versus open source. What the Kin Score measuresApplied only where the product itself is open source: a vulnerability disclosure path, a contribution route, a release history, a code of conduct. How the Kin Score measures it on APIs.io →
Create-or-Update Ergonomics0 talks · 0 primary What you will hearNo talk is mostly about it this year. What the Kin Score measuresApplied only where an API accepts writes: is there a create-or-update, and is a write safe to call twice? How the Kin Score measures it on APIs.io →
Accountability26 talks · 14 primary What you will hearThe APIOps Conference group work on ownership and 90-day action plans, Lumo on who watches the agents running the organisation, Theodo on anthropomorphism as an API, Eden AI on the control layer Europe is missing. What the Kin Score measuresStandalone and not yet scored. Who answers for an organisation's use of AI: a published policy that resolves, versioned, with a named owner, an accountable officer and an impact assessment.
Outside the rubric89 talks · 78 primary What you will hearThe GreenIO track on energy, carbon and planetary boundaries, and a long tail of agent-engineering talks (memory, evaluation, coding factories) about building agents rather than publishing APIs. What the Kin Score measuresNothing yet. The Kin Score reads the Spectral rules and pagination that talk automates, but has no facet for energy or carbon disclosure.

The agenda