diff --git a/.jules/bolt.md b/.jules/bolt.md
new file mode 100644
index 0000000..17c8f29
--- /dev/null
+++ b/.jules/bolt.md
@@ -0,0 +1,3 @@
+## 2025-03-01 - [Bolt: Fix Clinical Context Lexicon Generation Time]
+**Learning:** The openmed project's `openmed.clinical.context` relies heavily on `_compiled_context_lexicon` which recursively compiles and computes large numbers of regexs. Because this wasn't cached, it added up linearly during multiple queries or requests (i.e. spans/modifiers evaluations in text).
+**Action:** Use `functools.lru_cache` to cache deterministic regex compilations and lexicon generation in text/NLP pipelines.
diff --git a/openmed/openmed/clinical/context.py b/openmed/openmed/clinical/context.py
index 9fd11df..eccdc60 100644
--- a/openmed/openmed/clinical/context.py
+++ b/openmed/openmed/clinical/context.py
@@ -35,6 +35,7 @@
 
 from __future__ import annotations
 
+import functools
 import re
 from collections.abc import Iterable, Iterator, Mapping, Sequence
 from dataclasses import dataclass, replace
@@ -154,6 +155,8 @@ class _CompiledContextLexicon:
     backward_context_cues: frozenset[str]
 
 
+# Memoize lexicon compilation to prevent repeated regex generation and improve performance
+@functools.lru_cache
 def _compiled_context_lexicon(language: str | None = None) -> _CompiledContextLexicon:
     lexicon = get_clinical_cue_lexicon(language)
     token_boundaries = lexicon.token_boundaries