During the AI Engineer Code Summit 2026, leading software developers and speakers drew a firm line against the uncritical deployment of generative models. On November 12 and 13, 2026, Dex Horthy, Philip Kiely, and Kent C. Dodds, alongside other summit participants, published the 'No AI Slop Manifesto'. The document was launched simultaneously via a GitHub Gist and the website slopmanifesto.com, instantly sparking widespread discussion across the technical community. It addresses the accelerating influx of substandard, unexamined machine output across enterprise codebases and internal documentation.
The manifesto deliberately frames itself as a contemporary parallel to the landmark Agile Manifesto of 2001. Just as the agile pioneers pushed back against rigid waterfall methodologies, this new initiative challenges the blind trust placed in raw generative throughput. The authors use the term 'AI slop' to describe automated code snippets, pull requests, and technical memos pushed into workflows without rigorous human validation. Engineering leaders are discovering that inflating generation speed often fails to deliver meaningful improvements in end-product quality.
The authors anchored their framework around three core operating tenets designed to guide engineering teams and leadership. Foremost among them is 'outcomes over output', emphasizing durable business and functional value rather than raw token generation. The second pillar, 'understanding over speed', demands that programmers maintain a complete conceptual grasp of their codebase rather than chasing rapid code synthesis. Finally, 'our own thinking over a model’s first draft' asserts that human critical reasoning must remain the definitive anchor of the software development lifecycle.
This shift in perspective carries concrete operational consequences for the broader software industry. When large language models and autonomous agents can generate arbitrary volumes of code and documentation at negligible marginal cost, project overhead inevitably shifts downstream. The primary bottleneck is no longer the synthesis of new lines of code, but the rigorous verification, auditing, and maintenance of incoming automated drafts. Reviewers face mounting fatigue from low-effort pull requests that require disproportionate human labor to review and debug.
The debate reflects a broader reckoning across professional software engineering, where the structural limitations of raw automation are becoming evident. While automated code completion tools were initially hailed as an unalloyed productivity multiplier, complex production environments are now revealing severe maintenance overhead and compounding technical debt. Unvetted model outputs frequently introduce subtle bugs that pass initial unit tests while degrading architectural integrity over time. The signatories caution that development teams risk relinquishing intellectual ownership of their systems if output generation remains unchecked.
Consequently, rigorous quality assurance is reclaiming its role at the core of technical leadership and engineering culture. The manifesto urges organizations to establish demanding verification criteria and prevent developers from delegating ultimate code accountability to probabilistic engines. Engineers are increasingly expected to act as critical auditors and system architects whose core value lies in deep structural discernment and failure analysis. The No AI Slop Manifesto ultimately signals an important maturation phase for an industry moving past speculative enthusiasm toward disciplined engineering reality.

