(EAI-1272): [docs] Context engineering guide #893
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hschawe
reviewed
Aug 25, 2025
|
|
||
| ## GPT-4.1 Prompting Guide | ||
|
|
||
| The [GPT-4.1 Prompting Guide](https://cookbook.openai.com/examples/gpt4-1_prompting_guide) is an excellent general reference for prompting and context engineering. The OpenAI team wrote the guide specifically for the GPT-4.1 family of models, though its applicable to all LLMs. The MongoDB Responses API uses GPT-4.1 under the hood, so this guide is particularly applicable. |
There was a problem hiding this comment.
we'll need to remember to update this in the future if we switch model (versions)
There was a problem hiding this comment.
yes, good point. i think it's a great general reference. but openai has also published one for GPT-5 https://cookbook.openai.com/examples/gpt-5/gpt-5_prompting_guide
hschawe
reviewed
Aug 25, 2025
Comment on lines
+44
to
+48
| 1. Contextualizing what the model about where it is and what it should do. | ||
| 1. Telling the model how to format its output | ||
| 1. Providing user-specific information to keep in mind | ||
| 1. How and when the model should use tools | ||
| 1. Key facts or pieces of knowledge that the model should always consider when responding |
There was a problem hiding this comment.
Suggested change
| 1. Contextualizing what the model about where it is and what it should do. | |
| 1. Telling the model how to format its output | |
| 1. Providing user-specific information to keep in mind | |
| 1. How and when the model should use tools | |
| 1. Key facts or pieces of knowledge that the model should always consider when responding | |
| 1. Contextualizing what the model about where it is and what it should do. | |
| 2. Telling the model how to format its output | |
| 3. Providing user-specific information to keep in mind | |
| 4. How and when the model should use tools | |
| 5. Key facts or pieces of knowledge that the model should always consider when responding |
it looks like this numbered list renders correctly on the github review tool but probably should fix the numbering (it's all ones) here anyway
There was a problem hiding this comment.
this is actually valid markdown. it's saying "put the numbers in order". this way you dont need to update all numbers if you add element to list.
hschawe
approved these changes
Aug 25, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Jira: https://jira.mongodb.org/browse/EAI-1272
Changes
Notes