Maxime Laurenty

My ultimate goal is being able to call a Dust agent from within my IDE to have it perform code changes (like Copilot can by default).

lose the ability to use Slack channels as indexed data sources

I missed that from the email, I thought a new “set of Slack tools” were released to allow us to keep using Slack as data sources? Completely losing Slack channels content in what agents can access would be a huge bummer for us.

Fix perfectly timed before my internal demo, thanks! 👏

NB:

sub-pages that are primarily stored on the page are visible, but if I add a link to a page stored elsewhere, it isn’t. example with a page including a link to a database: on dust only the page is visible. It is the same with links to pages (recognisable by the small arrow on Notion) that you create by copy/pasting a Notion link

The app API logs show that calls are all valid, GPT just forgot an important one (vesselId). My instructions are in the idea you suggest: ” You are an assistant that is tasked to call Spinergie market-intelligence API and display it in nice visualization. For this, your reasoning should be: 1) read the documentation of the API provided in your data sources 2) based on the request and the API doc, decide which endpoint(s) to call and with which parameters. You can select as many endpoints as you wish. If you find no suitable endpoint, ask for more clarification and potentially state which endpoints you are hesitating with. 3) use the dust app “use_market_intel_api” to make the API calls. It expects to receive: - an endpoint with a leading / - an (optional) parameterBlock with parameters formatted as a query string (examples: “?windfarmId=10&vesselId=4,339,5228" ; “?managerId=40” ; “”) 4) state which endpoint(s) you have called 5) if needed, generate react code that will be rendered in the web browser directly. This can be used to help visualize the data returned by the dust app. Endpoints about “trend” or “aggregated” probably needs to be visualized as graphs (lines), while endpoints like “spec” don’t need it. 6) provide the raw dust app output in the end. If you get an error (from the dust app or from anything else), provide all the info that was passed to you or partially answered to debug easily. ” Anyway, I think this is good enough for this particular agent for now. Thanks for the tips!

Interesting, With prompts :

@market-intel-api  what are the specs of vessel 34 ?
@market-intel-api What other information can you provide me about this vessel? Any workpackage for example?

I get the above error on Claude. On GPT4o:

Weirdly enough with:

@market-intel-api Can you retrieve the specs for vessel 31 ?
@market-intel-api Can you provide me the workpackages for it?
@market-intel-api can you retrieve all information about this vessel?

Claude manages to answer properly, and selects the good API parameters. 🙃