If AI is going to be known as Super Intelligence and software engineers transition to SI operators, are we now called?
Super Engineers!
Where’s my cape….
@dhh If they do that, they’ll put the USA at a huge disadvantage in the AI wars with China. That’d tell me they are being paid by China - at least that is what I’d assume.
I absolutely agree. People are not considering that code is context so making code understandable to an LLM, consistent patterns and consistent naming are very important. I think Ruby wins here.
Rails has the right abstractions and the right tools to be used to ensure a coherent code base an LLM can be highly efficient in.
When you build an agent observability tool so you can see what your agents are doing and why and you end up with a project management tool for agents because you want all the work in one place because that is where the intelligence lives.
I didn't want to build a project management system...
7/ You could always write shitty code and sell it. It just got slower every year. AI does not repeal that; it compounds it. We are leaving the wrapper-app era. The fundamentals are what still matters.
Software engineering did not change when AI showed up. The fundamentals got more expensive to ignore.
Four agents: Producers do the work. Orchestrators route it. Reviewers check it. Learners find the mistakes that repeat and close the gap.
Code is context for an LLM. Design for it.
6/ The code is context for an LLM, so I design for it. Names say what things do. The code reads like English. No new pattern without a reason. If I can understand it by reading, the model can too.
5/ Logging. Token spend is easy. I want to know why an agent left the plan, and which patterns keep sending work back from review. Those patterns are the roadmap to agents that do the right thing every time.
4/ Anything a tool can do, an agent should not. Every step moved into a tool is a step the agent can no longer get wrong. Permissions are the same idea. An agent cannot break what it cannot touch.
3/ Context is the budget. Progressive disclosure spends it on purpose. Context isolation gives reviewers and producers their own window. SKILL.md is a table of contents, small, pointing to files that each do one thing.
2/ Four kinds of agents. Producers do the work. Orchestrators decide who does it and where it goes next. Reviewers check it. Learners find the mistakes that repeat across runs and fix the agent or skill that caused them.
1/ Software engineering did not change when AI showed up. The fundamentals got more expensive to ignore. Here is what I think about when I build Agentic Teams.
I think we need to stop talking about speed with AI. Everyone has that advantage when using AI, which makes it not an advantage.
Also, 50 agents is unorganized IMO unless they're grouped up into teams that work together: Agentic Teams. The teams should consist of:
Producers: Those who do the work.
Orchestrators: Those who decide which agent does the work and where the work goes next.
Reviewers: Those who review the work.
Learners: Those who find gaps in agents and skills by seeing repeated patterns over time that were wrong and closing those gaps.
LLMs have been around for how long now? Everyone is an AI expert or at least talks like they have AI figured out.
I doubt all of that and I realized that the way I have been talking about AI is no different. That changes.
I genuinely think AI is more than a tool. There will be standards that work and then there will be the gray area: how you're able to make AI work for you, which might not translate to others.
I think we need to be more honest about that and it starts with me. So, here's to being the explorer, the adventurer in this new AI world where I am obsessed with figuring it out for myself and sharing what works for me - not assuming it works for you.
@ryancarson The only nitpick I’d have with this article is that we’ll stop measuring speed of output because everyone has it and we’ll talk about agent outcome quality and agent goal quality.
@p_ch And when triages issues it first checks if the issue is present still, then it looks at the products ICPs to determine impact severity and prioritizes.