diff --git a/README.md b/README.md
index 46f63ce..611e6cc 100644
--- a/README.md
+++ b/README.md
@@ -8,21 +8,23 @@ GPTC provides both a CLI tool and a Python library.
 
 ### Classifying text
 
-    python -m gptc <modelfile>
+    python -m gptc classify <compiled model file>
+
+This will prompt for a string and classify it, then print (in JSON) a dict of
+the format `{category: probability, category:probability, ...}` to stdout.
+
+Alternatively, if you only need the most likely category, you can use this:
+
+    python -m gptc classify [-c|--category] <compiled model file>
 
 This will prompt for a string and classify it, outputting the category on
 stdout (or "None" if it cannot determine anything).
 
-Alternatively, if you need confidence data, use:
-
-    python -m gptc -j <modelfile>
-
-This will print (in JSON) a dict of the format `{category: probability,
-category:probability, ...}` to stdout.
-
 ### Compiling models
 
-    python -m gptc <raw model file> -c|--compile <compiled model file>
+    python -m gptc compile <raw model file>
+
+This will print the compiled model in JSON to stdout.
 
 ## Library
 
diff --git a/gptc/__main__.py b/gptc/__main__.py
index d9627b5..350ae36 100644
--- a/gptc/__main__.py
+++ b/gptc/__main__.py
@@ -6,34 +6,44 @@ import json
 import sys
 import gptc
 
-parser = argparse.ArgumentParser(description="General Purpose Text Classifier")
-parser.add_argument("model", help="model to use")
-parser.add_argument(
-    "-c",
-    "--compile",
-    help="compile raw model model to outfile",
-    metavar="outfile",
-)
-parser.add_argument(
+parser = argparse.ArgumentParser(description="General Purpose Text Classifier", prog='gptc')
+subparsers = parser.add_subparsers(dest="subparser_name", required=True)
+
+compile_parser = subparsers.add_parser('compile', help='compile a raw model')
+compile_parser.add_argument("model", help="raw model to compile")
+
+classify_parser = subparsers.add_parser('classify', help='classify text')
+classify_parser.add_argument("model", help="compiled model to use")
+group = classify_parser.add_mutually_exclusive_group()
+group.add_argument(
     "-j",
-    "--confidence",
-    help="output confidence dict in json",
+    "--json",
+    help="output confidence dict as JSON (default)",
     action="store_true",
 )
+group.add_argument(
+    "-c",
+    "--category",
+    help="output most likely category or `None`",
+    action="store_true",
+)
+
 args = parser.parse_args()
 
 with open(args.model, "r") as f:
-    raw_model = json.load(f)
-if args.compile:
-    with open(args.compile, "w+") as f:
-        json.dump(gptc.compile(raw_model), f)
+    model = json.load(f)
+
+if args.subparser_name == 'compile':
+    print(json.dumps(gptc.compile(model)))
 else:
-    classifier = gptc.Classifier(raw_model)
+    classifier = gptc.Classifier(model)
+
     if sys.stdin.isatty():
         text = input("Text to analyse: ")
     else:
         text = sys.stdin.read()
-    if args.confidence:
-        print(json.dumps(classifier.confidence(text)))
-    else:
+
+    if args.category:
         print(classifier.classify(text))
+    else:
+        print(json.dumps(classifier.confidence(text)))