NLW and Nufar Gaspar discuss how knowledge workers can move beyond one-shot prompting by using agentic loops. They explain the design of verifiable finish lines, how to decide which tasks should be looped, and ways to prevent runaway costs. The episode also covers composing multiple agents into work graphs that can research, review, and refine outputs autonomously.
This summary was generated from show notes and public descriptions, not from a full transcript review. Details may contain inaccuracies.
Novel
•
Agentic Loops: Moving Beyond One-Shot Prompting
NLW and Nufar introduce agentic loops as a way for knowledge workers to produce more complete and reliable work by having the AI repeatedly refine its output.
Multi-Agent Work Graphs: Composing Research, Review, and Refinement
NLW and Nufar explain how to compose multiple agents into a work graph, where one agent researches, another reviews, and a third refines the output autonomously.