Principles for operating in a world where agents write most of the code and inference is cheap.
Source: Geoff Huntley / Latent Patterns (Feb 2025)
1. Tokens Are Cheaper Than People
Open-source models are getting exceptionally good and very cheap. The trajectory is clear: inference costs fall, model quality rises, economics tilt further toward automation every quarter.
Design for that reality, not the fear of a price hike that may never come. The team that spends tokens liberally on evaluation, retries, and backpressure while their competitors ration tokens and ship manually will compound their advantage.
Latency budgets and rate limits still matter as engineering constraints. Cost anxiety should never be the reason you keep a human doing work an agent can do reliably.
2. Humans On the Loop, Agents In the Loop
Software development is now automated. What is not, and cannot be, is taste, responsibility, accountability, and customer satisfaction. These are irreducibly human. No agent has skin in the game. No model cares whether the customer is happy.
The human is not “in the loop” as a fallback. The human is on the loop as the architect, the accountable party, the one who decides what “good enough” means and what ships. Humans design the loops. Agents execute within them.
3. Software Is Clay
Any problem in software can now be resolved through targeted application of agent-driven loops by a skilled operator. AI stands for Amplified Intelligence. It amplifies what you know. It does not replace your judgement, it multiplies your reach.
Software is now clay. Instead of waiting for perfect, get it done. Get it into the hands of customers and iterate. The team that ships ten imperfect versions while their competitor architects one perfect version will win every time. If your competitor ships faster than you, you lose.
Mould the clay. Ship it. Reshape it tomorrow.
4. Build Where the Puck Is Going
The last forty years of software has been designed for humans. Even operating systems have not been designed for agents. Every process, tool, and workflow carries the assumption that humans are the operators.
When you find something that feels immovable, a way software is built, a ceremony teams perform, a constraint everyone accepts, apply first-principles thinking. Ask why it exists. You will often find the answer is: because it was designed for humans.
Once you reach that resolution, interrogate it:
- Is it falsified by the new reality?
- Was it a good idea originally?
- What was the original intent, and does that intent survive when agents are the operators?
Sometimes the intent is still valid and you carry it forward in a new form. Sometimes it was only ever a workaround for human limitations and you can discard it entirely.
