# Blog — Daniil Okhlopkov

English notes and imported posts about AI agents, Claude Code, data and Telegram.

## Материалы

- [Telegram Bot API vs MTProto: Methods Available to Bots](/en/articles/telegram-bot-api-vs-mtproto-methods/) — Which MTProto methods can Telegram bots call? A production-tested Bot API comparison with bot-token methods, user-only limits, and Telethon examples.
- [183 AI Bots on Telegram with 44M Users: What the Data Shows](/183-ai-bots-telegram-44m-users/) — Research into AI agents on Telegram: 183 bots with 44.3M combined MAU. BotFather doubled to 7.3M. Telegram is the default AI product interface.
- [21 Questions That Expose Gaps in Your AI Agent's Knowledge](/21-questions-ai-agent-knowledge-gaps/) — A curated list of uncomfortable questions to ask Claude Code, Codex, or any AI coding agent. Each answer reveals blind spots in how the agent understands you.
- [AI Tools I Actually Tried in March 2026: Honest Review](/ai-tools-march-2026-honest-review/) — AI tools March 2026 review: paperclip, gstack, conductor.build, x402, agent-browser and Chrome debug port — what stayed useful in real Claude Code/Codex workflows.
- [Always-On AI Agent: Running Claude Code 24/7 on a Server](/always-on-ai-agent-server-setup/) — How to run an AI agent 24/7 on a server: Claude Code-style loop, Telegram interface, cron jobs, durable memory, health checks and safety boundaries.
- [Telegram MCP Server for Claude Code: Telethon, MTProto and Real Workflows](/telegram-mcp-server-guide/) — Telegram MCP Server guide for Claude Code: Telethon, MTProto, Bot API limits, FastMCP architecture, userbot safety, allowlists and audit logs.
- [Claude Code /compact: What It Does, What Survives](/claude-code-compaction-explained/) — Claude Code /compact explained: what context automatically compacted means, what survives compression, compact prompts, hooks and how to recover lost context.
- [Decentralized AI Compute: Cocoon vs Bittensor vs Gonka Compared](/decentralized-ai-compute-cocoon-bittensor-gonka/) — Comparing three decentralized AI compute protocols: Cocoon (TON), Bittensor (TAO), and Gonka (GNK). Architecture, tokenomics, validation, and real-world performance.
- [Claude Code Setup 2026: MCP Servers, Hooks, Skills](/claude-code-setup-mcp-hooks-skills-2026/) — 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](/en-claude-codex-dual-review/) — How to set up cross-validation between Claude Code and OpenAI Codex via MCP. Step-by-step Dual Review protocol with prompt examples.
- [Telegram Ads Keyword Analysis: 61,000 Search Queries from 3,100+ Advertisers](/en-telegram-ads-61k-search-queries-analysis/) — Analysis of 61K search queries from Telegram Ads advertisers. Top niches: tarot, dating, VPN. 3,100+ advertisers, 10,600 unique keywords.
- [Fake Claude Code Website: How I Found a Phishing Site in Google Ads](/en-fake-claude-code-phishing-site-google/) — Phishing site impersonating Claude Code found in Google Ads: copied design, base64-encoded install script, malicious binary. How to spot the fake.
- [How I Automated TON Blockchain Data Analysis with an AI Agent — Habr Article](/en-automated-ton-data-analysis-ai-agent-habr/) — Story of automating TON Blockchain data analysis by building ton-analyst skill for Claude Code. Full article on Habr with examples and code.
- [BotFather MAU Up 43% in 6 Weeks: Telegram as a Platform for AI Agents](/en-botfather-mau-43-percent-growth-telegram-ai/) — BotFather MAU grew from 3.5M to 5M in 6 weeks (+43%). Telegram is a convenient interface for AI agents. Stats on python-telegram-bot, grammY, aiogram.
- [ton-analyst: Open Source AI Skill for TON Blockchain Analysis via Dune Analytics](/en-ton-analyst-open-source-ai-skill-dune/) — Open source ton-analyst skill for Claude Code: automated TON Blockchain data analysis via Dune Analytics. Installation and usage guide.
- [The Singularity Already Happened — Just Not Where You Think: Analysis of 5 AI Metrics](/en-singularity-already-happened-5-ai-metrics/) — Analysis of 5 AI progress metrics: only academic papers show hyperbolic growth. Everything else is linear. Singularity = attention, not capabilities.
- [AI Agents for Web Scraping: API/XHR, Playwright](/web-scraping-ai-agents-2026/) — AI agents for web scraping in 2026: API/XHR first, embedded JSON next, Playwright/browser agents for JS/auth, and LLM extraction only after verification.
- [How to Write Claude Code Skills Properly: 7 Common Mistakes to Avoid](/en-write-claude-code-skills-7-mistakes/) — 7 mistakes that break Claude Code skills: no trigger, generic names, empty sections, verbose triggers. Checklist for a good skill file.
- [My AI Dev Tools in 2026: What I Actually Use Daily](/ai-tools-setup-january-2026/) — 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](/en-5-prompts-improved-ai-agent-workflow-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.
- [dania.zip: packaging yourself for AI agents](/dania-zip-packaging-yourself-for-ai/) — How I created an exportable personality spec for AI agents. File structure, tone extraction, and real use cases for a digital twin.
- [Obsidian Second Brain with Claude Code: My Agent-Readable Vault Setup](/second-brain-obsidian-claude-code/) — How I use Obsidian, Claude Code, CLAUDE.md and voice notes as an agent-readable second brain: folder structure, rules, workflows and failure modes.
- [Where to Find SaaS Ideas: acquire.com Reverse Engineering with AI Validation](/en-find-saas-ideas-acquire-com-ai-validation/) — How to find profitable SaaS ideas: parse acquire.com listings, reverse-engineer competitor marketing, validate with AI. Step-by-step checklist from idea to MVP.
- [Claude Code workflow: how I code with AI in 2026](/claude-code-workflow-2026/) — My workflow with Claude Code: plan mode, spec-driven development, and why AI agents replaced autocomplete. Real examples and costs.

[Full archive](/archive/)