Dust vs Procore AI Go

Dust

The whole platform is MIT on GitHub, with a public OpenAPI document of 68 operations, llms.txt and a remote MCP server that acts with the signed-in user's access. API calls that run agents draw only on a paid workspace credit pool, and the terms of service could not be read.

Procore AI Go

Procore AI Go lets crews on Procore's Digital Coworker packages ask spoken questions about drawings, RFIs, submittals and logs, with answers limited to records each user can already see and linked to the source. It is a read-only iOS beta through TestFlight, and no API or MCP tool reaches it, so an outside agent can't use it.

Dust

1. Use https://eu.dust.tt for a workspace in the EU region and https://dust.tt otherwise, for both the API and the MCP server
2. Connect an MCP client by OAuth and send the resource parameter in authorisation and token requests. API keys do not work on the MCP server
3. Expect HTTP 429 with type rate_limit_error when the credit pool, the programmatic monthly cap or the key's spend cap is exhausted. Retrying will not help
4. Call GET /api/v1/w/{wId}/search with limit (1 to 100, default 25) and cursor, or a data source view's search with top_k
5. Keep document upserts under 120 a minute per workspace

Procore AI Go

1. Don't plan to call Procore AI Go. It's a voice app for people on an iPhone, with no programmatic interface
2. For Procore project data, use Procore's REST API under the customer's OAuth app instead
3. Expect each question asked in the app to use the company's Procore Credits, unless it's on the flat-fee Starter Pack
4. Ask the Procore Company Administrator to join the programme in Procore Explore if a crew needs the app