AI programming engineering
Build reproducible and reviewable AI coding workflows from repository context and change plans to test gates.
OPNFTR KNOWLEDGE CENTER
Organize AI and engineering practice into collections, learning paths, chapters, and cases. Public pages show reviewed and published content only.
Search published tutorials, practical cases, and knowledge articles by title or full text.
Enter collections and learning paths by technical direction as the platform grows.
Build reproducible and reviewable AI coding workflows from repository context and change plans to test gates.
Planning, tool use, and verifiable execution.
Retrieval-augmented generation, evaluation, and knowledge engineering.
Model serving, capacity planning, and safe delivery.
From requirements and tools to evaluation and operations.
Move from quick start to advanced capability and reusable practical cases.
Codex 快速上手教程,从认识 Codex、安装账号、桌面 App、第一个任务到开发者入口,帮助初学者先跑通。
15 chapters02进阶教程 (original language)Codex 进阶教程总览,整理费用上下文、AGENTS.md、Skills、权限管理、自动化、Hooks、沙盒、配置、团队协作和排障路径。
13 chapters03实战案例 (original language)Codex 实战案例库,收录 PPT、Draw.io、Playwright、Obsidian、临床文献综述、Hatch Pet、安卓手机远程操控、命名本地环境、飞书、Figma、Notion、CI 和远程排障案例。
18 casesContinue with OPNFTR's existing AI, technology, and practice articles.
A practical design for pausable, resumable, observable AI workflows with bounded model decisions and safe side effects.
Large-Model APIsLarge-Model APIs: Integration and Cost ControlBuild a reliable model adapter and control API cost with routing, caching, retries, budgets, and explicit failure states…
AI Product OperationsAI Product Feedback Loops: From User Signals to Safe IterationA safe feedback loop that turns reviewed user signals into regression tests, targeted fixes, and reversible releases.
AI Evaluation and ObservabilityAI Evaluation and Observability: Turning Quality into SignalsA layered evaluation and tracing approach that turns AI quality, latency, and cost into actionable release signals.
Fine-TuningParameter-Efficient Fine-Tuning: LoRA Decisions and Release BoundariesA production boundary for parameter-efficient tuning that starts with data quality, measures regressions, and keeps roll…
Multimodal AIMultimodal AI Pipelines for Images, Text, and AudioA traceable multimodal pipeline with input normalization, asynchronous work, quality sampling, and privacy-aware deletio…