diff --git a/streamexecutor/Doxyfile.in b/streamexecutor/Doxyfile.in
index 3b8bdda..8ca45f1 100644
--- a/streamexecutor/Doxyfile.in
+++ b/streamexecutor/Doxyfile.in
@@ -811,7 +811,7 @@
 # that contain example code fragments that are included (see the \include
 # command).
 
-EXAMPLE_PATH           = @CMAKE_CURRENT_SOURCE_DIR@
+EXAMPLE_PATH           = @CMAKE_CURRENT_SOURCE_DIR@/examples
 
 # If the value of the EXAMPLE_PATH tag contains directories, you can use the
 # EXAMPLE_PATTERNS tag to specify one or more wildcard pattern (like *.cpp and
@@ -825,7 +825,7 @@
 # irrespective of the value of the RECURSIVE tag.
 # The default value is: NO.
 
-EXAMPLE_RECURSIVE      = NO
+EXAMPLE_RECURSIVE      = YES
 
 # The IMAGE_PATH tag can be used to specify one or more files or directories
 # that contain images that are to be included in the documentation (see the
@@ -983,7 +983,7 @@
 # Minimum value: 1, maximum value: 20, default value: 5.
 # This tag requires that the tag ALPHABETICAL_INDEX is set to YES.
 
-COLS_IN_ALPHA_INDEX    = 5
+COLS_IN_ALPHA_INDEX    = 1
 
 # In case all classes in a project start with a common prefix, all classes will
 # be put under the same header in the alphabetical index. The IGNORE_PREFIX tag
@@ -1068,7 +1068,7 @@
 # see the documentation.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-HTML_EXTRA_STYLESHEET  =
+HTML_EXTRA_STYLESHEET  = @CMAKE_CURRENT_SOURCE_DIR@/customdoxygen.css
 
 # The HTML_EXTRA_FILES tag can be used to specify one or more extra images or
 # other source files which should be copied to the HTML output directory. Note
@@ -1352,7 +1352,7 @@
 # The default value is: NO.
 # This tag requires that the tag GENERATE_HTML is set to YES.
 
-GENERATE_TREEVIEW      = NO
+GENERATE_TREEVIEW      = YES
 
 # The ENUM_VALUES_PER_LINE tag can be used to set the number of enum values that
 # doxygen will group on one line in the generated HTML documentation.
diff --git a/streamexecutor/customdoxygen.css b/streamexecutor/customdoxygen.css
new file mode 100644
index 0000000..a40ac95
--- /dev/null
+++ b/streamexecutor/customdoxygen.css
@@ -0,0 +1,20 @@
+body {
+  background-color: #e0e0eb;
+}
+
+div.header {
+  margin-left: auto;
+  margin-right: auto;
+  max-width: 60em;
+  padding-left: 2em;
+  padding-right: 2em;
+}
+
+div.contents {
+  margin-left: auto;
+  margin-right: auto;
+  max-width: 60em;
+  background-color: white;
+  padding: 2em;
+  border-radius: 1em;
+}
diff --git a/streamexecutor/examples/CMakeLists.txt b/streamexecutor/examples/CMakeLists.txt
index a522052..1d09a54 100644
--- a/streamexecutor/examples/CMakeLists.txt
+++ b/streamexecutor/examples/CMakeLists.txt
@@ -1,2 +1,2 @@
-add_executable(example Example.cpp)
-target_link_libraries(example streamexecutor)
+add_executable(cuda_saxpy_example CUDASaxpy.cpp)
+target_link_libraries(cuda_saxpy_example streamexecutor)
diff --git a/streamexecutor/examples/Example.cpp b/streamexecutor/examples/CUDASaxpy.cpp
similarity index 95%
rename from streamexecutor/examples/Example.cpp
rename to streamexecutor/examples/CUDASaxpy.cpp
index a96648a..eab0cbe 100644
--- a/streamexecutor/examples/Example.cpp
+++ b/streamexecutor/examples/CUDASaxpy.cpp
@@ -1,4 +1,4 @@
-//===-- Example.cpp - Example code for documentation ----------------------===//
+//===-- CUDASaxpy.cpp - Example of CUDA saxpy with StreamExecutor API -----===//
 //
 //                     The LLVM Compiler Infrastructure
 //
@@ -15,6 +15,7 @@
 ///
 //===----------------------------------------------------------------------===//
 
+#include <algorithm>
 #include <cassert>
 #include <cstdio>
 #include <cstdlib>
@@ -51,6 +52,7 @@
 /// [Example saxpy compiler-generated]
 
 /// [Example saxpy host PTX]
+// The PTX text for a saxpy kernel.
 const char *__compilergen::SaxpyPTX = R"(
   .version 4.3
   .target sm_20
@@ -130,8 +132,6 @@
 
   // Process output data in HostX.
   std::vector<float> ExpectedX = {4, 47, 90, 133};
-  for (size_t I = 0; I < ArraySize; ++I) {
-    assert(HostX[I] == ExpectedX[I]);
-  }
+  assert(std::equal(ExpectedX.begin(), ExpectedX.end(), HostX.begin()));
   /// [Example saxpy host main]
 }
diff --git a/streamexecutor/include/streamexecutor/StreamExecutor.h b/streamexecutor/include/streamexecutor/StreamExecutor.h
index d25da01..942cd32 100644
--- a/streamexecutor/include/streamexecutor/StreamExecutor.h
+++ b/streamexecutor/include/streamexecutor/StreamExecutor.h
@@ -7,8 +7,9 @@
 //
 //===----------------------------------------------------------------------===//
 
-/// \mainpage Getting Started
+/// \mainpage Welcome to StreamExecutor
 ///
+/// \section Introduction
 /// \b StreamExecutor is a wrapper around CUDA and OpenCL host-side programming
 /// models (runtimes). This abstraction cleanly permits host code to target
 /// either CUDA or OpenCL devices with identically-functioning data parallel
@@ -19,9 +20,10 @@
 /// LLVM project or as a standalone project depending on LLVM as an external
 /// package.
 ///
+/// \subsection ExampleUsage Example Usage
 /// Below is an example of the use of the StreamExecutor API:
 ///
-/// \snippet examples/Example.cpp Example saxpy host main
+/// \snippet examples/CUDASaxpy.cpp Example saxpy host main
 ///
 /// In the example, a couple of handler functions, \c getOrDie and \c
 /// dieIfError, are used to handle error return values in the StreamExecutor
@@ -30,10 +32,12 @@
 /// versions of these handlers so that errors are handled more gracefully than
 /// just exiting the program.
 ///
+/// \subsection CompilerGeneratedCode Compiler-Generated Code
+///
 /// The example also references some symbols from a compiler-generated
 /// namespace:
 ///
-/// \snippet examples/Example.cpp Example saxpy compiler-generated
+/// \snippet examples/CUDASaxpy.cpp Example saxpy compiler-generated
 ///
 /// Instead of depending on the compiler to generate this code, you can
 /// technically write the code yourself, but this is not recommended because the
@@ -55,6 +59,9 @@
 /// MultiKernelLoaderSpec instance should be generated by the compiler if
 /// possible, not by the user.
 
+/// \example examples/CUDASaxpy.cpp
+/// Running saxpy on a CUDA device.
+
 #ifndef STREAMEXECUTOR_STREAMEXECUTOR_H
 #define STREAMEXECUTOR_STREAMEXECUTOR_H