Agent workflows: setup, context, review loops, progress artifacts and daily usage.
Материалы
- AI-рилзы для SEO: как собрать video pipeline из Telegram-трендов — Пайплайн AI-рилзов для SEO: Telegram/X трендвотчинг, быстрые видео-эксперименты, метрики saves/shares и превращение победителей в evergreen-страницы.
- AI-агенты ведут проект, пока я в отпуске: Claude Code, Paperclip и GStack без магии — Как я настроил AI-агентов на проект, что сработало во время отпуска, что сломалось и какой workflow нужен, чтобы агент не просто менял код туда-сюда.
- Мой AI-сетап 2026: Claude Code, Cursor, Ghostty, Spokenly и база всех чатов — Практический AI setup из стрима с @og_mishgun: что реально ускоряет работу, зачем Ghostty, Spokenly, OwnYourChat и Descript, и как не утонуть в инструментах.
- Claude Code skills для рефакторинга: что дать AI-агенту, когда задачи закончились — Два сильных skill для Claude Code и Cursor: improve-codebase-architecture и Thermo-Nuclear Code Quality Review. Как заставить агента искать архитектурный долг, а не косметический cleanup.
- AI Tools I Actually Tried in March 2026: Honest Review — Hands-on review of 5 AI tools from March 2026: paperclip task tracker, gstack YC prompts, conductor.build IDE, x402 crypto payments, and agent-browser setup.
- Always-On AI Agent: Running Claude Code 24/7 on a Server — How I run an always-on AI agent on a Hetzner VPS. Architecture, Docker setup, Telegram bridge, memory system, and real costs.
- Telegram MCP Server for Claude Code: Telethon, MTProto and Real Workflows — How to build a Telegram MCP server for Claude Code with Telethon: tools, auth, session strings, async traps, security boundaries and production workflows.
- Claude Code /compact: What It Does, What Survives — Claude Code /compact explained: what context automatically compacted means, what survives compression, compact prompts, hooks and how to recover lost context.
- Claude Code Setup 2026: MCP Servers, Hooks, Skills — Claude Code setup 2026: MCP servers, hooks, skills and subagents, with official Anthropic docs links, mcp add command, Windows/account caveats and a minimal setup map.
- Claude Code + Codex Dual Review: How Two AI Agents Cross-Check Each Other's Plans — How to set up cross-validation between Claude Code and OpenAI Codex via MCP. Step-by-step Dual Review protocol with prompt examples.
- Claude Code + Codex双重审查：两个AI代理如何交叉检查彼此的计划 — Claude Code + OpenAI Codex双重审查流程：用两个AI代理交叉检查计划、代码和边界条件。包含MCP连接、review prompt、适用场景、成本取舍和我实际用来减少agent盲点的协议。
- My AI Dev Tools in 2026: What I Actually Use Daily — Ghostty, Descript, Coolify, and 4 other tools in my daily dev workflow. How they actually fit together after months of use.
- 5 Prompts That Improved My AI Agent Workflow: Tested Hacks for Claude Code — Five battle-tested prompts for Claude Code: ask clarifying questions, don't stop till done, show-don't-tell with playground, multi-agent hiring, memory from mistakes.
- Obsidian Second Brain with Claude Code: My Agent-Readable Vault Setup — How I use Obsidian, Claude Code, CLAUDE.md and voice notes as an agent-readable second brain: folder structure, rules, workflows and failure modes.
- Claude Code workflow: how I code with AI in 2026 — My workflow with Claude Code: plan mode, spec-driven development, and why AI agents replaced autocomplete. Real examples and costs.
- Tips from Claude Code Creator: Git Worktrees, Self-Improving CLAUDE.md, and Code Review — Boris from Anthropic shared Claude Code tips: git worktrees for 3-5 parallel sessions, self-improving CLAUDE.md, Claude as strict reviewer, /techdebt skill.
- Show Me Your AI Setup #1: Ghostty, ownyourchat, Descript и Spokenly — разбор с og_mishgun — Обзор AI-инструментов: Ghostty терминал, ownyourchat для синхронизации чатов с AI, Descript для видеомонтажа, Spokenly для локальной транскрипции.
- Show Me Your AI Setup #1: Ghostty, ownyourchat, Descript, Spokenly — Tools Review — AI tools review: Ghostty terminal, ownyourchat for syncing AI chats to SQLite, Descript for text-based video editing, Spokenly for local transcription on Mac.
- Beads vs Gastown: Should You Use External Frameworks for AI Agents? — Analysis of Beads (agent task tracker) and Gastown (agent orchestration). Why building your own agent setup beats using external frameworks.
- AI Agents in Practice: How to Code with Claude Code and Voice Commands via Telegram — How AI agents work, how to program with them, manage context, and code via Telegram voice messages. Full article with practical examples.
- How to deploy your backend to production with Dokku — Step-by-step Dokku backend deployment for Node.js, FastAPI, Django or similar apps: server setup, SSH keys, domains, env vars and GitHub Actions CI/CD.
- Dokku + Github Actions: automatically deploy app with push to repository — Connect GitHub Actions to Dokku so every push can deploy a Python or Node.js app: SSH setup, workflow file, Dokku repo update and rebuild trigger.
- Deploy Elasticsearch & Kibana with Dokku — Deploy Elasticsearch and Kibana on a Dokku server: install plugins, create services, link apps, expose Kibana and handle production setup details.
- Deploy MeiliSearch with Dokku for production — Deploy MeiliSearch with Dokku in production: app setup, domain, master key, persistent storage, Docker deployment, Python indexing example, and security notes.
Смежные темы
AI-агенты · Claude Code · Codex · MCP · GStack · AI Tools · Second Brain · Web Scraping · TON-данные · Telegram