Drew Breunig
CEO and Co-founder
Cmpnd
Prompts Rot. Keep the Source.
Prompts Rot. Keep the Source.
AI agents learn what we want from our feedback, then compress that intent into prompts, skills and memories—and discard the evidence. The result is a collection of natural-language artefacts that decay as models change and edge cases accumulate. Prompts rot; skills bloat; memories quietly encode stale assumptions.
Drew Breunig argues that feedback and execution traces should be treated as source code. Instead of preserving only prose instructions, teams should retain the examples that express their intent and repeatedly compile them into task-specific workflows. He will show why smarter models do not remove the need for this discipline, how code and other precise representations can replace fragile instructions, and why compiled workflows can be more auditable, reliable and maintainable than general agents—especially inside enterprises.
Drew Breunig
Drew Breunig is the CEO and co-founder of Cmpnd, where he works on DSPy and helps teams build reliable AI applications. He is editing The Context Engineering Handbook for O'Reilly Media, and advises the Overture Maps Foundation on its Global Entity Reference System, which makes it easy to join geospatial datasets. Previously he ran strategy, data science and strategic client projects at PlaceIQ (acquired by Precisely), and with Nicholas Felton co-founded Reporter, an award-winning app. He writes about AI, data, geo and culture at dbreunig.com.