diff --git a/internal/handler/search.go b/internal/handler/search.go
index a944167..823a754 100644
--- a/internal/handler/search.go
+++ b/internal/handler/search.go
@@ -70,19 +70,15 @@ var collectionQueryByWeights = map[string]string{
 	"other_documents": "10,10,2,2",
 }
 
-// collectionTextMatchType lets specific collections opt-in to `sum_score`
-// instead of the Typesense default `max_score`.
+// searchStopwordsSet is the name of the Typesense stopwords set applied to
+// every search. The set is configured server-side (`PUT /stopwords/common`)
+// and contains conversational words like "letter", "to", "of", "essay", etc.
 //
-// `sum_score` boosts documents that match in MULTIPLE fields, so e.g. a letter
-// whose `recipient_display` AND `content` both contain the query ranks above
-// a letter that only matches in `content`. Useful for collections that have a
-// strong metadata field (recipient, title) tied to the user's intent.
-//
-// `max_score` (default elsewhere) preserves single-field dominance — important
-// for verses where the canonical verse should beat commentaries that quote it.
-var collectionTextMatchType = map[string]string{
-	"letters": "sum_score",
-}
+// Without this, a query like "letter to tusta krsna" ranks letters that merely
+// contain "letter" and "to" in their body above letters whose recipient is
+// actually "Tusta Krsna", because those common tokens contribute heavily to
+// the multi-field score.
+const searchStopwordsSet = "common"
 
 // searchResultItem represents a single search result in the API response.
 type searchResultItem struct {
@@ -212,6 +208,7 @@ func (h *SearchHandler) multiSearch(ctx context.Context, collections []string, q
 			Prefix:           stringPtr("true"),
 			NumTypos:         stringPtr("2"),
 			ExhaustiveSearch: &exhaustive,
+			Stopwords:        stringPtr(searchStopwordsSet),
 			// Boost docs whose tokens are exact matches and appear early in the field
 			// so "karma" outranks "karmic" and frequent matches outrank single ones.
 			PrioritizeExactMatch:    &prioritizeExact,
@@ -220,9 +217,6 @@ func (h *SearchHandler) multiSearch(ctx context.Context, collections []string, q
 		if weights != "" {
 			params.QueryByWeights = stringPtr(weights)
 		}
-		if tmt := collectionTextMatchType[col]; tmt != "" {
-			params.TextMatchType = stringPtr(tmt)
-		}
 		searches = append(searches, params)
 	}
 
@@ -287,6 +281,7 @@ func (h *SearchHandler) singleSearch(ctx context.Context, collection, query stri
 		Prefix:           stringPtr("true"),
 		NumTypos:         stringPtr("2"),
 		ExhaustiveSearch: &exhaustive,
+		Stopwords:        stringPtr(searchStopwordsSet),
 		// Boost docs whose tokens are exact matches and appear early in the field
 		// so "karma" outranks "karmic" and frequent matches outrank single ones.
 		PrioritizeExactMatch:    &prioritizeExact,
@@ -295,9 +290,6 @@ func (h *SearchHandler) singleSearch(ctx context.Context, collection, query stri
 	if weights := collectionQueryByWeights[collection]; weights != "" {
 		params.QueryByWeights = stringPtr(weights)
 	}
-	if tmt := collectionTextMatchType[collection]; tmt != "" {
-		params.TextMatchType = stringPtr(tmt)
-	}
 
 	sr, err := h.ts.Client.Collection(collection).Documents().Search(ctx, params)
 	if err != nil {