Playbooks for AI tools and developer workflows
Work through tool comparisons, prompt design and project costs. Pair the guides with our free browser toolkit. English guides are followed by a separate Chinese section.
Five useful starting points
Choose a tool, refine your writing workflow, or plan what it will cost to run.
- ChatGPT vs Claude vs Gemini for writing (decision framework) Choose a writing tool for each stage of your workflow, with a decision framework, pricing notes and a comparison checklist.
- System prompt vs user prompt (ChatGPT & production templates) Separate system instructions from user requests. Includes prompt templates for ChatGPT, Claude and Gemini, with production checks.
- LLM token cost estimation: ChatGPT token counter + OpenAI cost calculator Estimate input and output tokens, apply model rates, and account for retries before you commit to a monthly budget.
- AI content pipeline & writing workflow that ships weekly Plan a repeatable content workflow from brief to publication, with clear responsibilities, draft reviews and fact checking.
More playbooks
- How to run MiniMax H3 locally: ComfyUI and Diffusers setup guide How to run MiniMax H3 locally: GPU memory tiers, ComfyUI workflows, Diffusers CPU offloading, license caveats, and troubleshooting. · hardware, local-ai, video
- Prompt template library for content ops (free, copy-ready) Free AI / ChatGPT prompt template library for content ops — copy-ready prompts for briefs, outlines, drafts, SEO packs, and edits. No signup. · prompts, content, templates
- AI SEO workflow for 2026 (practical, no hacks) A 2026-ready AI SEO workflow: intent mapping, outline freeze, draft assist, on-page packs, internal links, and measurement — without black-hat tricks or fake test claims. · seo, workflow, 2026
- GPT-5.6 Luna vs Claude Haiku 4.5: cost per 1K tokens worksheet A practical worksheet to compare small/fast model costs per 1K tokens — GPT-5.6 Luna vs Claude Haiku 4.5, inputs, outputs, retries, and when price alone misleads. · cost, pricing, comparison
- AI agent tool-calling token overhead How tool schemas, transcripts, and multi-step agent loops inflate token usage — and a practical way to estimate overhead before you ship. · agents, tokens, cost
- AI coding assistant privacy checklist A practical privacy checklist for adopting AI coding assistants: training defaults, retention, secrets, repo scope, and vendor paperwork — without fake security scores. · privacy, devtools, checklist
- Anthropic Batch API cost estimation Estimate Anthropic Batch API spend before you enqueue: discount assumptions, token shapes, failure retries, and a worksheet that stays honest when list prices change. · cost, anthropic, batch
- Best free prompt formatter with no signup What to look for in a free prompt formatter that needs no account: local processing, Markdown cleanup, and a checklist before you paste into production. · tools, prompts, privacy
- Canonical URL for cross-posted AI blogs (Medium and beyond) How to set canonical URLs when you cross-post AI articles to Medium, newsletters, or company blogs — avoid duplicate-content confusion without myths. · seo, publishing, content-ops
- How to document prompt changes like config Treat system prompts like versioned config: changelogs, owners, diffs, rollbacks, and review — so prompt edits do not become invisible production changes. · prompts, ops, process
- Evaluate LLM vendor lock-in: checklist A practical checklist to evaluate LLM vendor lock-in — prompts, SDKs, evals, data terms, and exit drills — before your roadmap depends on one provider. · vendors, architecture, checklist
- IndexNow vs Google sitemap for small sites IndexNow vs Google sitemap for small sites: what each does, when to use both, and a practical submit workflow for static Cloudflare Pages properties. · seo, indexing, ops
- JSON schema output prompt examples for production Production-oriented prompt patterns for JSON / schema-constrained LLM outputs: contracts, examples, validation loops, and failure modes — no fake benchmarks. · prompts, json, production
- LLM feature unit economics for SaaS A practical framework for LLM feature unit economics in SaaS — cost per successful action, gross margin impact, pricing guardrails, and when to kill a feature. · saas, cost, product
- LLM rate limit backoff playbook A practical playbook for LLM rate limits: detect 429s, exponential backoff with jitter, budgets, queues, and user-facing degradation — without magical retry loops. · ops, rate-limits, reliability
- OpenRouter vs direct OpenAI pricing: worksheet Build a pricing worksheet for OpenRouter versus direct OpenAI (or any gateway vs direct) — list price, routing fees, retries, and operational tradeoffs. · cost, pricing, vendors
- Prompt injection defenses for customer-facing bots Defensive playbook for prompt injection on customer-facing bots: trust boundaries, tool permissions, input isolation, monitoring, and incident response — no exploit recipes. · security, defensive, bots
- RAG context window cost estimation Estimate token and dollar cost for RAG features: chunk sizes, top-k, system overhead, retries, and how context windows blow monthly bills. · rag, tokens, cost
- Reduce prompt tokens without losing quality A practical playbook to shrink LLM prompts — cut noise, structure context, compress examples — while keeping the behaviors you actually need. · prompts, tokens, cost
- Retry budget for LLM features: a practical spreadsheet Design a retry budget for LLM-backed features — how many retries, when to fail open/closed, and how retries show up in token spend. · ops, reliability, cost
- AI tool stack for solopreneurs (lean and sane) A lean AI tool stack for solopreneurs: writing, research, coding, publishing, and cost control — with selection criteria and a no-hype setup path. · stack, solopreneur, tools
- Token counting explained for builders and budget owners What tokens are, offline counting methods without an API key, local vs vendor tokenizer differences, calibration workflows, and budgeting without treating vendor docs as mythology. · tokens, cost, fundamentals, tooling
- System prompts for research agents (safe and useful) How to write system prompts for research agents: roles, tool use, citation rules, stop conditions, and anti-hallucination constraints that hold up in production. · system-prompts, agents, research
- LLM cost control for teams: budgets, routing, and guardrails A practical playbook for capping LLM spend: token budgets, model routing, caching, retry policy, and monthly forecasting without a finance PhD. · cost, ops, tokens
- A reusable AI workflow for content ops (without a CMS rewrite) A concrete pipeline for briefs → drafts → edits → publish using LLMs as assistants, with human gates where quality and liability live. · workflow, content, ops
- A practical prompt engineering checklist for shipping work A field checklist for writing prompts that hold up in production — roles, constraints, output schemas, and failure modes — without hype. · prompts, workflow
中文
- 2026 AI SEO 工作流（务实版） 2026 可用的 AI SEO 流程：意图映射、大纲冻结、辅助起草、On-page 打包、内链与更新节奏——不做黑帽，不编造实测。
- 中英双语站点 SEO：sitemap 与收录提交 中英双语静态站的信息架构、canonical、hreflang、sitemap 与 IndexNow/Search Console 提交清单，减少漏收与规范网址混乱。
- 大模型按量计费怎么算：实操清单 把输入/输出 Token、重试、Agent 轮次和单价表拆开，按量计费才能算清；附可直接粘贴的估算步骤与上线检查清单。
- 系统提示词上线注意事项 把系统提示词当产品配置上线：职责边界、拒答规则、工具约定、版本与回滚，避免上线后行为漂移。
- Prompt 清理工具怎么用：无注册、本地整理 用免费 Prompt 清理工具整理 ChatGPT / Claude 草稿：去套话、规范 Markdown、控制长度；强调无注册与本地处理，附上线前检查清单。
- Token 费用估算表格：怎么建一版能复用的 搭建大模型 Token 费用估算表格：费率快照、流量形态、重试与批次折扣；配合本站估算器，避免把促销价写进稳态成本。
- 公众号 AI 初稿质检清单 公众号用 AI 出初稿后的人工质检清单：事实、口径、合规、结构、SEO 与发布前终检，强调可勾选、可复用。
- 小红书 AI 内容流水线：人工审核怎么卡 用 AI 辅助小红书初稿时，如何设计 brief、自动质检、双人审核与发布门禁，降低违规与虚假『实测』风险。
- 团队如何控制 LLM 成本 给小团队的 LLM 费用控制手册：计量、预算、模型路由、压缩上下文、重试策略与月度估算，避免账单失控。