diff --git a/AGENTS.md b/AGENTS.md
index 96776a3fae7..500a2162fd0 100644
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -224,4 +224,12 @@ See `CLAUDE.md` and the `Makefile` for standard commands. Key notes:
 cd litellm && poetry run ruff check .
 ```
 
-Ruff is the primary fast linter. For the full lint suite (including mypy, black, circular imports), run `make lint` per `CLAUDE.md`.
\ No newline at end of file
+Ruff is the primary fast linter. For the full lint suite (including mypy, black, circular imports), run `make lint` per `CLAUDE.md`.
+
+### UI Dashboard tests
+
+```bash
+cd ui/litellm-dashboard && npx vitest run
+```
+
+The full suite (281 files, ~2800 tests) takes ~5 minutes. Use `npx vitest run src/path/to/file.test.tsx` for a single file.
\ No newline at end of file
diff --git a/dev_config.yaml b/dev_config.yaml
new file mode 100644
index 00000000000..17658df9031
--- /dev/null
+++ b/dev_config.yaml
@@ -0,0 +1,6 @@
+model_list:
+  - model_name: fake-openai-endpoint
+    litellm_params:
+      model: openai/fake
+      api_key: fake-key
+      api_base: https://exampleopenaiendpoint-production.up.railway.app/