Home
Scenario-based tutorials with real screenshots, prompts, workflow templates and pitfalls.
A three-level user research & interview prompt pack: beginner semi-structured interview outline (anti-leading-questions), intermediate single-transcript structured insights (quote-tagged, no fabrication), expert N-transcript cross-sample synthesis into personas + JTBD + opportunity map (affinity mapping, frequency counts, conflict flagging). 4 general constraints (anti-fabrication/de-identification/human review) and 5 pitfalls.
A three-level code testing prompt pack: beginner generates unit tests per function (signature and boundary list first, N cases each for normal/boundary/error, pytest/jest parameterized), intermediate parameterized batch cases with a test plan (coverage gaps, minimal mocking), expert integration/E2E strategy and test refactor (test pyramid, contract tests, redundancy pruning). Includes a 5-minute cheatsheet. Anti-fabrication constraints embedded (no invented APIs, no fabricated coverage numbers). Differentiated from the general coding and review/debug packs--this one handles writing tests only.
A six-step SOP for AI automated test generation: when to use + baseline (coverage/defect escape) -> unit tests from code -> regression tests from issues -> batch boundary/parameterized cases -> test maintenance (stale assertions/redundancy) -> human gate + CI. Each step ships copyable pytest and jest code, plus 5 pitfalls (loose assertions/interdependencies/fake coverage/mock drift/not testing the real path) and 5 FAQ. Iron rule: AI only drafts, human review + CI green before merge.
A complete SOP for production AI Agent observability and online evaluation in six steps: defining the baseline (latency/token cost/tool success rate/error rate), distributed tracing (Langfuse @observe decorator + Phoenix register + OpenTelemetry spans), token and cost tracking, tool-call artifact logging, online evaluation (LLM-as-judge automated scoring + user thumbs feedback via create_score), and alerting with iteration (threshold rules + dashboards). Each step includes copyable Python code, 6 pitfall entries, and 5 FAQ items. Open-source tools first; LangSmith mentioned as a SaaS option.
A six-step SOP for cutting LLM API costs: quantify baseline, prefix caching (Qwen3.8-Max charges ¥1/M on cache hit vs ¥12 on miss, a 12x gap), model routing (expensive models for hard tasks, cheap for easy), batch API (latency for discount), context trimming with dedup, and monitoring. Each step ships with Python code, pitfalls, and FAQ.
DeepSeek's prefix cache makes long-session costs bifurcate (0.02 yuan hit vs 1 yuan miss, a 50x gap), but general agents do not optimize for DeepSeek's cache. This SOP walks through DeepSeek-Reasonix (community-built, unofficial) end-to-end: npm install, reasonix setup, reasonix.toml config sketch, cache-aware maintenance, executor+planner dual-model, and MCP plugins. All commands from the README; config fields per official docs.
An n8n workflow for knowledge base auto-update: content source trigger -> fetch content -> dedupe -> LLM summary + keywords + classification -> vectorize and write to KB -> notify. Keeps your docs library current. Includes a .json template and advanced tips (full rescan, staleness detection, permissions).
An n8n workflow for invoice processing automation: email/upload trigger -> extract attachment -> OCR/LLM field extraction -> validate -> IF pass write to finance system else human review -> archive. Includes compliance notes (sensitive financial data, recommend local OCR + private LLM, per local tax regulations). Includes a .json template download.
A three-level product management prompt pack: beginner user stories, intermediate structured PRD (9 sections), expert roadmap and requirement breakdown (Epic->Feature->Story + RICE/MoSCoW). Includes a competitor cheatsheet. Anti-fabrication constraints embedded throughout.
A three-level research/literature review prompt pack: beginner single-paper extraction (6 elements), intermediate multi-paper comparison (table + consensus/divergence), expert full review (structure + gap analysis + citation suggestions, with a hard verify-all-citations-against-originals guardrail). Includes a cheatsheet prompt and anti-fabrication guardrails.