passdrill
AI & LLM Engineering · AI Agents & Tool Use · Card 030/032 easy

A team building a literary-translation tool has one LLM call produce a draft translation, then a second, separate LLM call critique that draft against specific criteria (tone, idiom, nuance) and return concrete feedback, which is fed back to the first call to produce a revised translation -- repeating this critique-and-revise cycle a few times before returning a final translation to the user. What Anthropic 'Building Effective Agents' pattern is this, and when is it worth the added latency?

  1. Routing -- classifying the translation request by source language and directing it to a specialized prompt per language, which is worth it whenever more than one language is supported
  2. Prompt chaining with no feedback loop -- a fixed sequence of translation subtasks that always runs the same way regardless of the draft's quality, worth it whenever a task can be split into steps
  3. Parallelization by voting -- running several independent translation attempts and picking whichever ones agree, worth it whenever a single translation call is considered unreliable
  4. Evaluator-optimizer -- one call generates a response while a separate call evaluates it and provides feedback in a loop, worth the added latency specifically when there are clear evaluation criteria and when iterative refinement based on that feedback provides measurable value, such as when a human's articulated feedback would visibly improve the response
Next card → Shuffle