We've added new features to the Anthropic Console.
Claude can generate prompts, create test variables, and show you the outputs of prompts side by side.
LLM bullshit knife, to cut through bs
RAG -> Provide relevant context
Agentic -> Function calls that work
CoT -> Prompt model to think/plan
FewShot -> Add examples
PromptEng -> Someone w/good written comm skills.
Prompt Optimizer -> For loop to find best examples.
Excited to share our recent article on Sprinklr's RAG capabilities.
https://t.co/tfI5yG2vmy
Check out how @Sprinklr provides customizable guardrails, actions, and tooling capabilities to provide seamless integration tailored to each enterprise's unique requirements.
Great complex read from @remilouf + team @dottxtai on what they're working on
Basically a framework to balance speed + correctness
to help the wave of current LLM excitement convert into truly useful output ⚡️