The most important best practice is to provide (one shot / few shot) examples within a prompt
Unknown[1]
These examples showcase desired outputs or similar responses, allowing the model to learn from them and tailor its own generation accordingly
Unknown[1]
These examples showcase desired outputs or similar responses, allowing the model to learn from them and tailor its own generation accordingly
Unknown[1]
This approach aligns with how humans prefer positive instructions over lists of what not to do
Unknown[1]
High-quality instructions are essential for any LLM-powered app, but especially critical for agents
Unknown[2]
Sign Up To Try Advanced Features
Get more accurate answers with Super Search, upload files, personalized discovery feed, save searches and contribute to the PandiPedia.
Sorry, Pandi could not find an answer.
Let's look at alternatives:
- Modify the query.
- Start a new thread.
- Remove sources (if manually added).
- Request a manual search from our human research team.