Time to First Token
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization
About Time to First Token
Time to First Token is a structured 10 week curriculum covering LLM inference serving and optimization, designed around 30 minutes of study a day. It walks through batching, KV caching, quantization, throughput versus latency tradeoffs and the serving stack choices that decide your infrastructure bill. Worth the hour a week the moment self-hosting or inference cost stops being a rounding error.
More Guides
Standing Rules Instead of Permission Prompts
Ashley Childress spent four and a half months rebuilding how she works with AI coding agents, and the core move is a good one: stop treating permission prompts as your safety system. Clicking "approve" forty times per task is not oversight — it is fatigue theater. She replaced it with 134 standing rules that define what the agent may do up front. What the guide covers Why click-to-approve stops being a real guardrail once volume goes up. How to write standing rules that constrain behavior instead of interrupting it. Treating the agent like a direct report: context, expectations, and review at the right altitude. Nine concrete practice changes, each with the reasoning and evidence behind it. Why it is worth your time This is the rare "here is how I do things differently" post that shows its work. It is especially relevant now that agents are being handed more autonomy by default — the guardrails have to move from per-action prompts to written policy, and this is a working example of what that looks like. Read it on dev.to .
awesome-mcp-servers
awesome-mcp-servers is one of the most complete curated lists of Model Context Protocol servers — the growing catalog of tools you can plug into Claude, Cursor, and any MCP-capable agent to give it real capabilities. Browsing it is the fastest way to discover what your agent could be connected to: databases, browsers, file systems, APIs, and hundreds of niche integrations. A must-bookmark reference as MCP becomes the default way agents touch the outside world.
awesome-claude-skills
awesome-claude-skills is a curated, community-maintained list of Claude Skills, resources, and tools for customizing your AI workflows. Instead of writing every skill from scratch, you can browse what others have already built and refined. It is the fastest way to see the shape of the emerging skill ecosystem — design, research, engineering, and automation skills you can install and adapt. A great reference whether you are learning the pattern or looking for something to reuse.
Awesome LLM Apps
Awesome LLM Apps is a curated collection of more than 100 AI agent and RAG applications you can actually run — not just links, but working code you clone, customize, and ship. Each app demonstrates a real pattern, from multi-agent teams to retrieval pipelines. Why it is worth bookmarking If you learn best by reading real implementations, this is one of the fastest ways to see how production-shaped agent and RAG apps are wired together. It spans models, frameworks, and use cases, so you can find a starting point close to whatever you are building. 100+ runnable agent and RAG apps with source code Covers multi-agent systems, RAG, and tool use A practical reference library for builders Browse the collection on GitHub .
A disciplined method for keeping AI coding agents on a short leash — reliable results, less drift
The Short-Leash AI Coding Method
This widely-discussed essay lays out a "short leash" method for working with AI coding agents: instead of handing a model a broad task and hoping, you constrain each step, verify frequently, and keep the agent tightly scoped so it cannot wander. The piece is a practical, opinionated playbook for builders who have felt the pain of an agent confidently producing plausible-but-wrong code. It is a useful counterweight to "vibe coding," arguing that discipline and small verified increments beat autonomy when correctness matters.