Agents often fall back to outdated docs or SDKs, which breaks real integrations.
Really like the direction here of providing structured, up-to-date API context instead of relying on web search.
The key insight for us was that the context needs to be language-specific and structured around actual SDK methods, not just an API Reference or OpenAPI Spec. Both of those provide context on the shape of the API but leave it to AI agents to figure out exactly how to call API endpoints and then translate that into code - handling auth, errors, pagination, rate limits etc.
That's 2 levels of inference, one of which can be avoided by providing SDKs and context for those SDKs. The SDK wraps all the plumbing for interacting with the API; AI agents just need to figure out which methods to call.
If you get a chance to try one of the examples in the showcase, we'd love to hear your feedback.
Agents often fall back to outdated docs or SDKs, which breaks real integrations. Really like the direction here of providing structured, up-to-date API context instead of relying on web search.
The key insight for us was that the context needs to be language-specific and structured around actual SDK methods, not just an API Reference or OpenAPI Spec. Both of those provide context on the shape of the API but leave it to AI agents to figure out exactly how to call API endpoints and then translate that into code - handling auth, errors, pagination, rate limits etc.
That's 2 levels of inference, one of which can be avoided by providing SDKs and context for those SDKs. The SDK wraps all the plumbing for interacting with the API; AI agents just need to figure out which methods to call.
If you get a chance to try one of the examples in the showcase, we'd love to hear your feedback.