<html><body><div dir="ltr">
<br>
</div>
<br>
<div class="gmail_quote">
<div dir="ltr" class="gmail_attr">On Nov 8, 2026 at 12:00:59, Dave Morris via AI-interop <<a href="mailto:ai-interop@ivoa.net">ai-interop@ivoa.net</a>> wrote:<br></div>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex" type="cite">
<div>
<div dir="ltr">
Hiya,<br><br>Following on from the apps session on AI adoption. I had a quick <br>conversation with Google AI chat (gemini-3.8-flash) and together we came <br>up with the following suggestion:<br><br>...<br><br>General idea is the /context endpoint is a list resources an agent <br>should read before trying to use the service and the data it provides. <br>It allows data providers to curate the instructions for their own <br>particular resource.<br><br></div></div></blockquote><div class="gmail_quote"><br></div><div class="gmail_quote" dir="ltr">For SIA I think this would be a pretty simple thing to have because I think SIA already has a mechanism where you can ask for a VOTable that returns the ranges of acceptable parameters and distinct enum-like values. So we already have code in the service that is summarizing things.</div><div class="gmail_quote" dir="ltr"><br></div><div class="gmail_quote" dir="ltr">I still think that something like this should be augmented by improving semantic linkages of result columns within the results (at Rubin we return multiple fluxes for each filter but there is no easy way to link ugrizy together per algorithm or point at an algorithm reliably). A /context endpoint with information that can not be determined from the models is good but it’s even better if the results have more information.</div><div class="gmail_quote" dir="ltr"><br></div><div class="gmail_quote" dir="ltr">— </div><div class="gmail_quote" dir="ltr">Tim Jenness</div><div class="gmail_quote" dir="ltr"><br></div>
</div></body></html>