diff --git a/source/_posts/2025-11-06-ai-engineering-abstractions-wanted.markdown b/source/_posts/2025-11-06-ai-engineering-abstractions-wanted.markdown
new file mode 100644
index 00000000..bc17f3d1
--- /dev/null
+++ b/source/_posts/2025-11-06-ai-engineering-abstractions-wanted.markdown
@@ -0,0 +1,16 @@
+---
+title: AI Engineering Abstractions Wanted
+kind: article
+author: Atharva Raykar
+created_at: 2025-11-06 00:00:00 UTC
+layout: post
+---
+* No good abstraction to talk to an LLM (context creation and manipulation)
+* No standardised LLM conversation format
+* Inconsistent handling of thinking tokens
+* No easy (or performant) way to create reproducible sandboxes/envs for agents
+* No good context observability tools
+* Poor MCP client and server implementations
+* Poor LLM gateway implementations
+* No good flexible eval annotation tool that supports stuff like semantic clustering
+* Poor library/SDK story outside Python and JS ecosystems