Skip to content

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

Docs: Ask eval needs a fresh profile per build

Claudeea6352cc5a4c
diff --git a/docs/webgpu-models.md b/docs/webgpu-models.md
index e7b6ab3d6..bdb0e2aa2 100644
--- a/docs/webgpu-models.md
+++ b/docs/webgpu-models.md
@@ -116,9 +116,10 @@ Do all of these on the exact files you will publish.
before and after any change to the in-browser prompt, page context or
runtime. It covers greeting, summary, a fact at the end of a long page,
prices, a follow-up, arithmetic, a selection, Turkish, a prompt injection,
- an Act request, a linked URL and a browser page. To compare two builds,
- load both from the same `--extension` directory so they share the model
- cache.
+ an Act request, a linked URL and a browser page. Use a fresh `--profile`
+ for each build: a reused profile keeps running the service worker of the
+ build it first loaded, so it can silently test old code. The report lists
+ the prompt variant that answered each task (`tiny_ask` or `ask`).
5. **Production harness.** Run `scripts/check-bonsai-webgpu.mjs` online and
`--offline` (with `--vision --image-history` for vision models) and record
the evidence with `scripts/models/bonsai/record_browser_validation.py`.