optimize metadata for discoverability

README.md

@@ -1,6 +1,6 @@
 ---
-title: Cordon
-emoji: 🧬
+title: Cordon - Log Anomaly Detection
+emoji: 🔍
 colorFrom: blue
 colorTo: green
 sdk: gradio
@@ -8,13 +8,21 @@ sdk_version: "4.44.0"
 app_file: app.py
 pinned: false
 license: apache-2.0
-short_description: Reduce logs to their semantically anomalous parts
+short_description: Find anomalies in logs using AI. Paste logs, get insights.
 tags:
   - log-analysis
   - anomaly-detection
+  - semantic-search
   - embeddings
-  - nlp
   - transformers
+  - devops
+  - sre
+  - observability
+  - debugging
+  - nlp
+  - text-analysis
+  - machine-learning
+  - ai-tools
 ---
 
 # Cordon
@@ -31,6 +39,13 @@ Cordon uses AI to understand the *meaning* of your logs and find the parts that
 4. **Thresholding** — Top anomalies are selected
 5. **Output** — XML-tagged blocks ready for LLM analysis
 
+## Use Cases
+
+- **Debug faster** — Find the needle in the haystack
+- **LLM pre-processing** — Reduce logs to fit in context windows
+- **Incident response** — Surface unusual events quickly
+- **Exploratory analysis** — Discover patterns you didn't know to search for
+
 ## Key Insight
 
 > Repetitive patterns (even errors) are filtered out. Cordon surfaces the *rare* and *unusual* events that stand out from the bulk of your logs.