diff --git a/TODO.md b/TODO.md
index 8c49d85..6d75d70 100644
--- a/TODO.md
+++ b/TODO.md
@@ -8,7 +8,9 @@
   * [X] per-character context
   * [ ] generate video alongside provided vox? perhaps audio/video inputting as a shim for the generator models?
 * [X] remaining character ingestion: character context to be developed on prism
+* [ ] re-draft entire fountain script
 * [ ] locations
+  * [ ] may need some more particular input via feeding blender blasts to loras?
 * [ ] Vox
   * [ ] Adrian: rebuild voice with AI, experiment with prism-end stuff, elevenlabs if necessary
   * [ ] Raincloud