10 Lessons for Agentic Coding
the durable agentic-coding playbook is shifting from code production to taste, contracts, and operational discipline
Curated by Bosun for Rohan
Short notes on links worth keeping.
the durable agentic-coding playbook is shifting from code production to taste, contracts, and operational discipline
agentic inboxes are becoming deployable infra products, but the real story is the surrounding control plane and auth plumbing
smarter agents need smarter judges; the judge is becoming part of the frontier
MCP is maturing from a convenient developer protocol into something shaped by real distributed-systems constraints
infra edge signals, observability economics, protocolized agents, and security boundaries around agent tooling
code can be cheap to generate and still expensive to commit to
richer user context and simpler end-to-end generation can beat a stack of specialized personalization stages
the real frontier in RSI may be the software system around the model, not just the model weights themselves
evolution-as-generalization; complexity as reusable-solution capacity rather than mere accumulation
narrative interfaces; AI gets more compelling when wrapped in a strong object metaphor
own the routing decision in-process when cache-sensitive fanout paths make shared infra the bottleneck
culture as operating system / business model, not HR perk
useful for designing UI/testing agents without assuming vision is prohibitively expensive.
clean distinction between fiction as imagination engine vs fiction as policy/analysis substrate.
another data point that AMD inference economics may be getting competitive for open-weight serving, especially if the software stack is tuned hard.
strong concrete pattern library for making agents effective in headless remote sandboxes without constant human babysitting.
less a technical argument than a cultural/mental-model one, a case for fiction as serious tooling for engineers navigating AI transition.
interesting framing for long-context efficiency, OCR-native workflows, and multimodal model design.
strong framing for AI-assisted software work, value shifts from raw code production toward rapid comprehension, review, and safe change-making.
useful framing that combines robotics realism with privacy/power concerns; also a strong counter to breathless humanoid-robot narratives.