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 Readiness61 talks · 33 primary
What you will hearWise's blueprint for agent-ready fintech APIs, Tesco's agentic action layer, Gravitee on MCP auth, Thales on tokens as attack vectors, WSO2 on agents subscribed to event streams, Expedia on why MCP is not an API behind a gateway.
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 Quality31 talks · 16 primary
What you will hearLorna Mitchell on upgrading to OpenAPI 3.1, Jentic on Arazzo workflows agents can execute, Aristocrat on why a generated AsyncAPI is not a published contract, Adyen on required vs optional fields as a revenue lever, Bally's on spec-first payments.
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 Governance29 talks · 13 primary
What you will hearSpectral in CI at PZU, layered standards for agents from TM Forum, IBM's catalogue of API anti-patterns, MCP Ops from cloudappi, WunderGraph on agent-speed API sprawl.
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 Transparency28 talks · 6 primary
What you will hearAkamai on agents attacking APIs at machine speed, LSEG on incidents and deprecations as data, Treblle on API observability, JPMorgan Chase on thirty years of traffic management.
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 Posture23 talks · 5 primary
What you will hearStandard Chartered on ISO 20022 and autonomous treasury, GSMA on why live CAMARA APIs still take quarters to launch, Ozone on FAPI security profiles in OpenAPI, DigitalApiCraft on consent rails for agents, IG Group on the AI Act and HR decisions.
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 Clarity21 talks · 12 primary
What you will hearStrukt on token spend, Tyk on SaaS dependency and sovereignty, LSEG on entitlements and scopes, and the GreenIO finops talks that put cost and carbon on the same line.
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 Ergonomics13 talks · 7 primary
What you will hearLombard Odier's agentic sandbox, Postman's API and MCP bootcamp, Syntasso on platform APIs as products, SmartBear on what happens when an API falls over in the forest.
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 →
Discoverability17 talks · 1 primary
What you will hearDeutsche Bank on one registry for APIs and MCP servers, Pronovix asking what comes after the developer portal, Vonage on DevRel when the reader is an agent at 3AM.
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 Surface6 talks · 2 primary
What you will hearThe AsyncAPI Initiative on governance for sustainable open standards, AgentGuard as open-source middleware between agents, SPRUCE for open-source GreenOps.
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 Ergonomics1 talks · 0 primary
What you will hearBolt on stochastic APIs: what retries and idempotency mean when every call is another roll of the dice.
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 →
Accountability23 talks · 11 primary
What you will hearCapgemini on a valid API call with an invalid human outcome, Posetiv on GreenOps as a leadership problem, the platform engineering panel on ownership boundaries, Boomi on governing APIs to make AI pay off.
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 rubric19 talks · 4 primary
What you will hearMost of the GreenIO track: Greenpixie and Resilio on AI emissions as a black box, TCO Development certifying cloud resources, the Green Software Foundation on energy per agent task.
What the Kin Score measuresNothing yet. These talks keep saying providers do not disclose energy, carbon or water data. The Kin Score has no facet for that disclosure today; only the finops mapping under Access Clarity comes close.