Home
Scenario-based tutorials with real screenshots, prompts, workflow templates and pitfalls.
A three-level general coding prompt pack: beginner function generation, intermediate refactor and optimization, expert system design and multi-file scaffolding. Includes a cheatsheet prompt. Constraints: runnable, edge cases, no fabricated APIs, human review required.
A three-level financial analysis prompt pack: beginner financial-statement reading, intermediate valuation and peer comparison (DCF/multiples), expert risk decomposition and investment thesis. Anti-fabrication constraints and compliance disclaimer (not investment advice).
A RAG chunking strategy SOP: four strategies (fixed/recursive/semantic/structure-aware), chunk_size and overlap tuning, parent-child chunks and late chunking, recall evaluation. Includes LangChain splitter code example.
An LLM fine-tuning SOP: full LoRA/QLoRA workflow. When to fine-tune vs RAG vs prompt, data prep (instruction format), base model selection, QLoRA 4-bit quantized loading, training config, evaluation, merge and deploy. Includes peft/transformers code examples.
A complete SOP for building production-grade Agents with LangGraph 1.2: typed state and checkpointer durability, per-node timeouts, RetryPolicy auto-retry, error_handler fallback, and interrupt-based human approval. Includes runnable Python code, a parameter reference table, and a pitfall log.
This n8n workflow automates meeting minutes end to end: after upload, Whisper transcribes the recording, an LLM extracts topics/decisions/action items, and the result goes to Feishu, email, and Notion. Unlike the Meeting Notes Prompt Pack (text-to-minutes only), this is an unattended pipeline - a 30-minute meeting can go from upload to minutes-in-chat in under 3 minutes.
RSS/trend topic sourcing -> LLM scoring -> LLM writing -> SEO optimization (title/meta/keywords/FAQ/JSON-LD) -> quality check -> CMS draft publish; built for solo creators/indie sites to compress daily publishing from 4h to 30min.
A reusable SEO copywriting prompt pack covering title generation, meta description writing, body structure, keyword placement, and internal linking across three difficulty levels-feed to AI before writing to avoid rework.
A reusable prompt pack for getting LLMs to write correct SQL, explain and optimize queries, and chain through data profiling -> cleaning -> analysis -> visualization. Three levels (copy-and-use / with variables / chained); core constraints: paste schema, name dialect, go step by step.
Breaks RAG quality into three measurable layers-retrieval quality (context precision/recall), generation faithfulness, and answer relevance-and evaluates each with Ragas, TruLens, and DeepEval. Includes eval-set field design, 4 copy-paste code/prompt blocks, 6 pitfalls, and 5 FAQs. Complements the existing "Dify build SOP" by focusing purely on evaluation.