Written by the speakers and attendees of AIE Code Summit 2026

In 2001, 17 software engineers and leaders got together at a ski lodge in Snowbird, Utah to understand the biggest challenge of their time: heavyweight, documentation-driven software development processes.

Out of this we got the Agile Manifesto, four values and twelve principles that changed how most of the industry builds software.

Today we convene to build our own manifesto - the No AI Slop manifesto.

AI increasingly helps us write our code, docs, plans, and messages. We've all been on the receiving end of slop, and most of us have sent some too. Through this work, we have come to value:

Outcomes over output

Understanding over speed

Our own thinking over a model's first draft

Better work over easier work

Improving the system over patching the output

The world moves especially fast these days, but the goal of these resolutions is to embrace our important human role in harnessing AI safely, responsibly, in a way that creates value for everyone, and that will be relevant for years to come.

We believe:

1. AI is the most useful tool most of us have ever worked with, but a swarm of agents can produce more work in a single day than a person can review in our lifetime.
2. Slop is when we put less effort into producing something than we ask the consumer to spend understanding it.
3. Using AI doesn't necessarily make something slop. Slop happens when we pass AI output along without taking responsibility for the quality or the reader's experience.
3. AI cannot replace human judgement, it can only amplify our judgement (or lack thereof).
5. Slop is asymmetric. The cost of producing a thousand-line PR or a ten-page doc is approaching zero, while the cost of reviewing it remains constant.
6. In code, even before AI, slop proliferates when we repeatedly work around problems instead of solving them correctly. It comes from tools that lean HEAVILY toward adding rather than subtracting.
7. A lot of slop comes from pressure. Companies are pushing their people to redefine what is humanly possible.
8. Slop compounds. The more slop sits in our knowledge base, in chat, in code, the more of it the next agent reads and copies.
9. The more slop flying around a team, the more we lose the will to fight it. Communication and quality get worse over time, not better.

Thus we the undersigned resolve that:

10. Human time and attention is incredibly valuable, so we optimize for using it wisely.
11. We fight slop because AI should make our work better, not just easier.
12. We optimize systems, tools, and products for efficient elicitation of human intent and for efficient human understanding.
13. We do our own thinking when working with a model. We explore resources, code, and prior art to truly understand the problem before the work starts.
14. We own the intent, taste, and consequences of what we ship, however much AI helps us make it.
15. When an agent wrote something we're sending, we make that clear, and we check the parts that matter before it goes out.
16. When someone sends us slop, we tell them, kindly, and ask them to review it first. Most of us have needed that same note at some point.
17. There will always be alpha in reviewing something. As models improve, we may stop reading most of the code. We may still review a plan, design, or result, because if we don't, we just get the same output as everyone else.
18. Agent reviews, linters, and verifiers are useful but not sufficent. For now, we still review at least some subset of the outputs. What subset depends on the stakes.
19. What shipped, who's using it, and how it's helping them matters FAR MORE than lines of code, prs merged, tokens spent, or the number of agents running in parallel.
20. Unreviewed output isn't always necessarily bad. One-shot prompts and vibe coding are high leverage tools. "Slop" is bad when it undermines our outcome -- a useful product, a maintainable system, or saving ourselves and our teammates time and energy.
21. When a mistake shows up twice, we scale ourselves and our team by improving the system and its guardrails. Anything a linter, type checker, or automated check can catch, we let it catch.

And finally:

22. None of us has this figured out. We're each relearning what we will and won't accept, and there's no single right answer.

Again, the world moves especially fast these days, but the goal of these resolutions is to embrace our important human role in harnessing AI safely, responsibly, in a way that creates value for everyone, and that will be relevant for years to come.

We look forward to working with the community to evolve these beliefs as the world changes. Comments and feedback on this document are welcome. What is slop? Why does slop happen? Why is slop worth fighting? How do we fight slop?

Special thanks to Philip Kiely, Swyx, Lucas Meijer, Rebecca Bakels, Tejas Kumar, Natalie Serrino, Francisco Javier Arceo, Kent C. Dodds, Ankit Jain, Brandon Waselnuk, Mihail Eric, Justin McCarthy, Raz Berman Gold, Yacine Mahdid, Justin Poehnelt, Lauren Tan, and Kyle Mistele for contributions to this project.

More resources

Sign the manifesto

Add a gist comment with any or all of: name, company, X handle, LinkedIn, and we'll regularly pull signatures into the manifesto.

Signed-off by: [any of: name, company, x, linkedin, etc]

Signatures