feat(llma): add evals docs

[carlos-marchal-ph]

We should add screenshots later but it's non-trivial to get them looking nice so it's worth shipping this as is for the moment.

Old description for draft

This is a draft because of two main reasons.

First is I couldn't manage to get this to work locally, encountered a couple of errors and at the end got stuck here when running pnpm start:

Stuck

warn undefined
chunk commons [mini-css-extract-plugin]
Conflicting order. Following module has been added:
 * css
./node_modules/.pnpm/css-loader@5.2.7_webpack@5.101.3/node_modules/css-loader/di
st/cjs.js??ruleSet[1].rules[8].oneOf[1].use[1]!./node_modules/.pnpm/postcss-load
er@4.3.0_postcss@8.5.6_webpack@5.101.3/node_modules/postcss-loader/dist/cjs.js??
ruleSet[1].rules[8].oneOf[1].use[2]!./src/components/RadixUI/css/toast.css
despite it was not able to fulfill desired ordering with these modules:
 * css ./node_modules/.pnpm/css-loader@5.2.7_webpack@5.101.3/node_modules/css-lo
ader/dist/cjs.js??ruleSet[1].rules[8].oneOf[1].use[1]!./node_modules/.pnpm/postc
ss-loader@4.3.0_postcss@8.5.6_webpack@5.101.3/node_modules/postcss-loader/dist/c
js.js??ruleSet[1].rules[8].oneOf[1].use[2]!./src/styles/global.css
   - couldn't fulfill desired order of chunk group(s)
component---src-templates-api-endpoint-tsx,
component---src-templates-api-endpoint-tsxhead
   - while fulfilling desired order of chunk group(s) commons,
component---src-pages-careers-tsx, component---src-pages-contributors-tsx,
component---src-pages-merch-tsx, component---src-pages-careers-tsxhead,
component---src-pages-contributors-tsxhead
success Building development bundle - 84.069s
success Writing page-data.json files to public directory - 0.436s - 2/9224
21146.34/s

Second is that our data for the screenshots looks quite wonky, since the naming scheme for evals is all over the place, a lot of them are missing descriptions, and many of them don't follow the convention true = pass, false = fail. Shouldn't be too hard to fix, but would take a bit of time.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
posthog	Ready	Preview	Jan 2, 2026 11:23am