diff --git a/examples/gpt-5/gpt-5_prompting_guide.ipynb b/examples/gpt-5/gpt-5_prompting_guide.ipynb index 6ef24da9df..8521367cd9 100644 --- a/examples/gpt-5/gpt-5_prompting_guide.ipynb +++ b/examples/gpt-5/gpt-5_prompting_guide.ipynb @@ -10,7 +10,7 @@ "\n", "While we trust it will perform excellently “out of the box” across a wide range of domains, in this guide we’ll cover prompting tips to maximize the quality of model outputs, derived from our experience training and applying the model to real-world tasks. We discuss concepts like improving agentic task performance, ensuring instruction adherence, making use of newly API features, and optimizing coding for frontend and software engineering tasks - with key insights into AI code editor Cursor’s prompt tuning work with GPT-5.\n", "\n", - "We’ve seen significant gains from applying these best practices and adopting our canonical tools whenever possible, and we hope that this guide, along with the [prompt optimizer tool](http://platform.openai.com/chat/edit?optimize=true) we’ve built, will serve as a launchpad for your use of GPT-5. But, as always, remember that prompting is not a one-size-fits-all exercise - we encourage you to run experiments and iterate on the foundation offered here to find the best solution for your problem." + "We’ve seen significant gains from applying these best practices and adopting our canonical tools whenever possible, and we hope that this guide, along with the [prompt optimizer tool](https://platform.openai.com/chat/edit?optimize=true) we’ve built, will serve as a launchpad for your use of GPT-5. But, as always, remember that prompting is not a one-size-fits-all exercise - we encourage you to run experiments and iterate on the foundation offered here to find the best solution for your problem." ] }, { @@ -19,7 +19,7 @@ "source": [ "## Agentic workflow predictability \n", "\n", - "We trained GPT-5 with developers in mind: we’ve focused on improving tool calling, instruction following, and long-context understanding to serve as the best foundation model for agentic applications. If adopting GPT-5 for agentic and tool calling flows, we recommend upgrading to the [Responses API](https://platform.openai.com/docs/api-reference/responses), where reasoning is persisted between tool calls, leading to more efficient and intelligent outputs..\n", + "We trained GPT-5 with developers in mind: we’ve focused on improving tool calling, instruction following, and long-context understanding to serve as the best foundation model for agentic applications. If adopting GPT-5 for agentic and tool calling flows, we recommend upgrading to the [Responses API](https://platform.openai.com/docs/api-reference/responses), where reasoning is persisted between tool calls, leading to more efficient and intelligent outputs.\n", "\n", "### Controlling agentic eagerness\n", "Agentic scaffolds can span a wide spectrum of control—some systems delegate the vast majority of decision-making to the underlying model, while others keep the model on a tight leash with heavy programmatic logical branching. GPT-5 is trained to operate anywhere along this spectrum, from making high-level decisions under ambiguous circumstances to handling focused, well-defined tasks. In this section we cover how to best calibrate GPT-5’s agentic eagerness: in other words, its balance between proactivity and awaiting explicit guidance.\n", @@ -134,12 +134,10 @@ "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", "\n", - "We’ve seen statistically significant improvements in evaluations when using the Responses API over Chat Completions—for example, Taubench-Retail score increases from 73.9% to 78.2% just by switching to the Responses API and including previous_response_id to pass back previous reasoning items into subsequent requests. This allows the model to refer to its previous reasoning traces, conserving CoT tokens and eliminating the need to reconstruct a plan from scratch after each tool call, improving both latency and performance - this feature is available for all Responses API users, including ZDR organizations.\n", - "\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", "\n", - "We’ve seen statistically significant improvements in evaluations when using the Responses API over Chat Completions—for example, we observed Tau-Bench Retail score increases from 73.9% to 78.2% just by switching to the Responses API and including `previous_response_id` to pass back previous reasoning items into subsequent requests. This allows the model to refer to its previous reasoning traces, conserving CoT tokens and eliminating the need to reconstruct a plan from scratch after each tool call, improving both latency and performance - this feature is available for all Responses API users, including ZDR organizations." + "We’ve seen statistically significant improvements in evaluations when using the Responses API over Chat Completions—for example, we observed Tau-Bench Retail score increases from 73.9% to 78.2% just by switching to the Responses API and including `previous_response_id` to pass back previous reasoning items into subsequent requests. This allows the model to refer to its previous reasoning traces, conserving CoT tokens and eliminating the need to reconstruct a plan from scratch after each tool call, improving both latency and performance - this feature is available for all Responses API users, including [ZDR organizations](https://platform.openai.com/docs/guides/migrate-to-responses#2-update-multi-turn-conversations)." ] }, { @@ -300,7 +298,7 @@ "- Changing auto-assignment to occur after contacting a patient, auto-assign the earliest same-day slot after informing the patient of your actions. to be consistent with only scheduling with consent.\n", "- Adding Do not do lookup in the emergency case, proceed immediately to providing 911 guidance. to let the model know it is ok to not look up in case of emergency.\n", "\n", - "We understand that the process of building prompts is an iterative one, and many prompts are living documents constantly being updated by different stakeholders - but this is all the more reason to thoroughly review them for poorly-worded instructions. Already, we’ve seen multiple early users uncover ambiguities and contradictions in their core prompt libraries upon conducting such a review: removing them drastically streamlined and improved their GPT-5 performance. We recommend testing your prompts in our [prompt optimizer tool](platform.openai.com/chat/edit?optimize=true) to help identify these types of issues.\n", + "We understand that the process of building prompts is an iterative one, and many prompts are living documents constantly being updated by different stakeholders - but this is all the more reason to thoroughly review them for poorly-worded instructions. Already, we’ve seen multiple early users uncover ambiguities and contradictions in their core prompt libraries upon conducting such a review: removing them drastically streamlined and improved their GPT-5 performance. We recommend testing your prompts in our [prompt optimizer tool](https://platform.openai.com/chat/edit?optimize=true) to help identify these types of issues.\n", "\n", "### Minimal reasoning\n", "In GPT-5, we introduce minimal reasoning effort for the first time: our fastest option that still reaps the benefits of the reasoning model paradigm. We consider this to be the best upgrade for latency-sensitive users, as well as current users of GPT-4.1.\n", @@ -329,7 +327,7 @@ "Occasionally, adherence to Markdown instructions specified in the system prompt can degrade over the course of a long conversation. In the event that you experience this, we’ve seen consistent adherence from appending a Markdown instruction every 3-5 user messages.\n", "\n", "### Metaprompting\n", - "Finally, to close with a meta-point, early testers have found great success using GPT-5 as a meta-prompter for itself. Already, several users have deployed prompt revisions to production that were generated simply by asking GPT-5 what elements could be added to an unsuccessful to elicit a desired behavior, or removed to prevent an undesired one.\n", + "Finally, to close with a meta-point, early testers have found great success using GPT-5 as a meta-prompter for itself. Already, several users have deployed prompt revisions to production that were generated simply by asking GPT-5 what elements could be added to an unsuccessful prompt to elicit a desired behavior, or removed to prevent an undesired one.\n", "\n", "Here is an example metaprompt template we liked:\n", "```\n",