Step-by-step playbooks for AI workflows · 10 articles
Hands-on walkthroughs, cheatsheets, prompt recipes and step-by-step playbooks for AI dev workflows.
By leveraging Common Lisp's homoiconic nature, developers can build a recursive agent loop that dynamically writes, compiles, and registers its own tools.
Why it matters
You can design highly minimal agent systems where the LLM writes its own runtime code to expand its active tool catalog.
Open full storySvelteChatKit is an open-source, provider-agnostic UI kit for SvelteKit 2 and Svelte 5 (runes). It simplifies building AI interfaces with modular state management, streaming support, and plug-and-play config providers.
Why it matters
It allows developers to build chat interfaces that are not locked into a single LLM vendor.
Open full storyDan Luu shares deep insights on engineering workflows with coding agents, explaining why heavy testing methodologies like fuzzing and property-based testing are highly suited to AI-driven development where manual code review becomes impractical.
Why it matters
As AI agents generate code at superhuman speeds, manual code reviews become a bottleneck. Transitioning to a continuous automated testing workflow ensures code reliability without manual intervention.
Open full storyA single native, clearly labelled placement in front of engineers who build with AI, backed by transparent numbers.
Claim the slotA creative narrative explaining core Large Language Model (LLM) concepts through the perspective of "Lenny," an 80-billion-parameter model. It helps developers intuitively explain tokenization, context windows, and tool-calling to non-technical stakeholders.
Why it matters
Explaining AI concepts to non-technical stakeholders or beginners is notoriously difficult. This narrative-driven approach translates complex engineering realities like context limits and generation loops into relatable, human-scale analogies.
Open full storySimon Willison demonstrated using the DSPy framework to optimize Datasette Agent's production system prompts. By running automated evaluations on a gold-standard dataset, the framework exposed critical prompting flaws like column guessing.
Why it matters
Instead of manually tweaking prompts and hoping for the best, you can use DSPy's structured evaluations and metrics to programmatically fix prompt hallucinations.
Open full storyImplement a rigorous project-level CLAUDE.md contract to enforce architectural constraints, security defaults, and documentation standards. This method enables cross-session continuity and forces Claude to adopt your specific coding philosophy from the first prompt.
Why it matters
Establishing a living contract with Claude Code eliminates repetitive configuration, enforces security by design, and ensures consistent quality across all engineering tasks.
Open full story