Atomic AI advice extracted from the best creators. Quick tips you can use right now.
This Week
Feb 5 – Feb 11 #AI Agents
This week focused on building reliable AI systems. Key insights on writing persistent system prompts and handling hallucinations in production environments.
Agentic engineering is the professional evolution of vibe coding. You're not writing code directly 99% of the time — you're orchestrating AI agents who do and acting as oversight. The key difference: vibe coding was for fun throwaway projects, agentic engineering claims the leverage of agents without compromising software quality.
Set up a fixed-budget experiment loop: the human writes a strategy document (a Markdown file), the AI agent iterates on training code. Each experiment runs for exactly 5 minutes on a fixed metric, so every change is fairly compared. The agent commits improvements to a git branch and discards failures. 100+ experiments can run overnight without human involvement.
Give every AI experiment an identical wall-clock budget (e.g. 5 minutes). Measure with a vocabulary-size-independent metric like bits-per-byte. If results improve, commit to git and make it the new baseline. If not, git reset. This "ratchet" ensures the model only ever improves — roughly 12 experiments per hour, 100+ overnight.
Claws are persistent AI agent systems (like OpenClaw) that add orchestration, scheduling, context management, tool calls, and persistence on top of LLM agents. They're a new layer of the AI stack: LLMs → LLM agents → Claws. Look for implementations where the core engine is small enough to fit in your head and in an AI's context window (~4000 lines), making it manageable, auditable, and flexible.
Instead of traditional config files, use a skills-based approach: write instructions that tell an AI agent how to modify actual code to add features. For example, "/add-telegram" as a skill that instructs the agent to integrate Telegram. This prevents config mess and if-then-else monsters. The meta: write maximally forkable repos and use skills to fork into any desired configuration.
Creator of Datasette, co-creator of Django. Writing about LLMs, prompt engineering, and building with AI.
Professor at Wharton studying AI and innovation. Author of "Co-Intelligence".
Former Director of AI at Tesla, OpenAI co-founder. Coined "vibe coding" and "agentic engineering". Building Eureka Labs.
AI researcher at Notion. Building tools for thought and exploring human-AI interaction.