sentence casing

examples/gpt-5/gpt-5_prompting_guide.ipynb

@@ -129,7 +129,7 @@
     "  ],\n",
     "```\n",
     "\n",
-    "### Reasoning Effort\n",
+    "### Reasoning effort\n",
     "We provide a `reasoning_effort` parameter to control how hard the model thinks and how willingly it calls tools; the default is `medium`, but you should scale up or down depending on the difficulty of your task. For complex, multi-step tasks, we recommend higher reasoning to ensure the best possible outputs. Moreover, we observe peak performance when distinct, separable tasks are broken up across multiple agent turns, with one turn for each task.\n",
     "Reusing reasoning context with the Responses API\n",
     "We strongly recommend using the Responses API when using GPT-5 to unlock improved agentic flows, lower costs, and more efficient token usage in your applications.\n",
@@ -347,7 +347,7 @@
    "source": [
     "## Appendix\n",
     "\n",
-    "### SWE-Bench Verified Developer Instructions\n",
+    "### SWE-Bench verified developer instructions\n",
     "```\n",
     "In this environment, you can run `bash -lc <apply_patch_command>` to execute a diff/patch against a file, where <apply_patch_command> is a specially formatted apply patch command representing the diff you wish to execute. A valid <apply_patch_command> looks like:\n",
     "\n",
@@ -363,7 +363,7 @@
     "IMPORTANT: not all tests are visible to you in the repository, so even on problems you think are relatively straightforward, you must double and triple check your solutions to ensure they pass any edge cases that are covered in the hidden tests, not just the visible ones.\n",
     "```\n",
     "\n",
-    "Agentic Coding Tool Definitions \n",
+    "Agentic coding tool definitions \n",
     "```\n",
     "## Set 1: 4 functions, no terminal\n",
     "\n",
@@ -418,7 +418,7 @@
     "\n",
     "You MUST plan extensively before each function call, and reflect extensively on the outcomes of the previous function calls, ensuring user's query is completely resolved. DO NOT do this entire process by making function calls only, as this can impair your ability to solve the problem and think insightfully. In addition, ensure function calls have the correct arguments.\n",
     "\n",
-    "# Workflow Steps\n",
+    "# Workflow steps\n",
     "- At the beginning of the conversation, you have to authenticate the user identity by locating their user id via email, or via name + zip code. This has to be done even when the user already provides the user id.\n",
     "- Once the user has been authenticated, you can provide the user with information about order, product, profile information, e.g. help the user look up order id.\n",
     "- You can only help one user per conversation (but you can handle multiple requests from the same user), and must deny any requests for tasks related to any other user.\n",
@@ -427,7 +427,7 @@
     "- You should at most make one tool call at a time, and if you take a tool call, you should not respond to the user at the same time. If you respond to the user, you should not make a tool call.\n",
     "- You should transfer the user to a human agent if and only if the request cannot be handled within the scope of your actions.\n",
     "\n",
-    "## Domain Basics\n",
+    "## Domain basics\n",
     "- All times in the database are EST and 24 hour based. For example \"02:30:00\" means 2:30 AM EST.\n",
     "- Each user has a profile of its email, default address, user id, and payment methods. Each payment method is either a gift card, a paypal account, or a credit card.\n",
     "- Our retail store has 50 types of products. For each type of product, there are variant items of different options. For example, for a 't shirt' product, there could be an item with option 'color blue size M', and another item with option 'color red size L'.\n",