What Is Gemini Agent? Google's Universal Work Agent Explained
Gemini Agent is Google's universal work agent for persistent tasks, multi-agent coordination, model routing, and work across business…
Kostja12 min read
AI Agents
46 articles in this category.
AI Agent Connectors Explained: MCP, OAuth, and Permissions
Learn how AI agent connectors use MCP, OAuth, scopes, resource permissions, and approval gates—and how to evaluate a connector before it…
Kostja13 min read
What Is an Agent Harness? Architecture, Loops, and Safety
Learn what an AI agent harness does, how its execution loop, context, tools, sandbox, approvals, tracing, and recovery fit together, and…
Kostja13 min read
OpenAI Plugins Explained: Skills, MCP, UI, Events, and Distribution
What OpenAI Plugins are in 2026, how skills, MCP servers, UI extensions, events, and hooks fit together, and when a smaller integration is…
Floatboat10 min read
Batch Convert Markdown Files — When One File Becomes a Folder
How to batch convert a folder of markdown files to PDF, Word or HTML: pandoc scripts, GUI tools, failure modes, and when folder-scale work…
Kostja14 min read
Why Markdown Runs the AI Pipeline — Context In, Contracts Through, Output Out
Markdown has become the working format of AI pipelines: the context LLMs read best, the contract agents exchange, and the structure RAG…
Kostja16 min read
Convert HTML to Markdown — Clean Captures From Web and AI Chats
Convert HTML to Markdown to turn AI chat replies and web clippings into clean, portable .md files — what survives, what breaks, and the…
Kostja11 min read
What Is Markdown? — Plain-Text Format Behind Docs, Notes and AI
Markdown is the 2004 plain-text syntax that became the default for docs, git repos, note apps and AI output — how it works, its dialects,…
Kostja13 min read
Codex Harness Open Source — OpenAI's Agent Runtime
OpenAI's Codex harness is open on GitHub: exec, SDK, and app-server. What's in the agent loop, what's not open, and how it compares to…
Judy12 min read
What Is Doubao Work? ByteDance's AI Office Agent Explained
Doubao Work explained as an AI office agent: verify its desktop, cloud, Feishu, artifact, permission, pricing, and regional boundaries…
Kostja3 min read
Cordis Plugin Framework: How DeepSeek Harness Composes Services
A practical explanation of Cordis beneath DeepSeek Harness: contexts, services, dependency injection, effects, events, isolation, hot…
Jade5 min read
DeepSeek Agent Function Calling: Schemas, Loops, and Safety
Learn DeepSeek function calling for agents: tool schemas, strict mode, parallel tool calls, thinking mode, MCP, and production repair…
Judy11 min read
What Is Grok Bot? xAI's Cloud-Computer Agent Explained
Grok Bot explained: how its always-on cloud computer, routines, multi-bot coordination, X integration, access model, and approval…
Judy8 min read
How to Build a DeepSeek Agent: From API Key to Your First Agent
Step-by-step guide to building a DeepSeek Agent with V4 Pro and V4 Flash. Covers API setup, model selection, tool calling, the agent loop,…
Judy2 min read
What Is Claude Code — Anthropic's Terminal Coding Agent
Claude Code explained: Anthropic's terminal coding agent, its plan mode, sub-agents, and MCP — and how it differs from Cowork, Tag, and…
Ketd11 min read
What Is Claude Cowork? Features, Access, Limits, and the New Claude Experience
Claude Cowork explained: how it completes knowledge-work tasks across files and tools, how it differs from Chat and Claude Code, where it…
Jade8 min read
What Is Claude Tag? Anthropic's Shared Slack Agent Explained
Claude Tag lets teams delegate work to @Claude from selected Slack channels. Learn how channel memory, connected tools, permissions, and…
Jade4 min read
What Is a DeepSeek Agent? Models, Harnesses, Tools, and Types
A DeepSeek Agent is an agent harness using a DeepSeek model. Learn the difference between models and agents, current integrations, tool…
Jade3 min read
Voice Agent vs Voice Dictation for Work — Pick the Right Layer
Voice agents execute work from speech; voice dictation turns speech into text. A solopreneur guide for exploration, prompts, co-authoring,…
Tan Shaoqing12 min read
What Is a Voice Agent? Definition, Architecture, and Job Shapes
A voice agent is speech-in, speech-out AI for real-time conversation. Learn the definition, architecture, and how it differs from dictation…
Tan Shaoqing15 min read
Voice Mode vs Dictation for AI Agents — Which Job Shape Fits?
Voice mode vs dictation for AI agents: two-way speech or speech-to-text? Compare ChatGPT, Claude, coding tools, and solo founder workflows.
Tan Shaoqing13 min read
What Is Voice Dictation for AI Agents? — Defined
Voice dictation for AI agents turns speech into agent prompts—not chat replies. Learn the definition, five job shapes, and how it differs…
Tan Shaoqing13 min read
How to Use Obsidian with an AI Agent Safely
Use an AI agent with Obsidian without handing over your whole knowledge base. This practical workflow covers access scope, read-only…
Judy6 min read
Context Engineering for AI Agents: What to Include, Exclude, and Persist
A practical guide to context engineering for AI agents: instructions, tools, retrieval, memory, compaction, security boundaries, and…
Pan Yang6 min read
Dynamic Workflows: Build Agents or Use a Workspace?
Dynamic Workflows raises a practical question: should solo operators build agent orchestration or use a workspace built for execution?
Nova3 min read
Genspark Super Agent: What's New in 2026 and Who It Fits
Genspark Super Agent explained through official capabilities and a reproducible research-to-artifact test: sources, permissions, retries,…
Kostja3 min read
Agentic AI Systems: Build, Buy, or Use a Hybrid?
A practical build-versus-buy framework for agentic AI systems, covering task fit, governance, integration, evaluation, total cost, lock-in,…
Nova10 min read
HTML Is the New Markdown: What the Argument Actually Means
Trace the documented HTML-is-the-new-Markdown argument, inspect its examples, and separate human-facing artifact design from Markdown…
Kostja4 min read
How to Build an AI Agent with ChatGPT in 2026
Build a reusable agent workflow in ChatGPT without an API: choose the right ChatGPT surface, define instructions, knowledge, apps,…
Nova8 min read
How to Build AI Agents for Repeated Work
Build an AI agent for repeated work with a task contract, bounded tools, state, approvals, evaluations, observability, and safe…
Nova8 min read
5 Questions to Ask Before You Give a Browser AI Your Logins
Before you let a browser AI agent touch your Gmail or CRM, walk through these 5 questions on permissions, memory, and prompt injection.
Nova9 min read
What Can a Browser AI Agent Actually Do?
A task-by-task guide to browser AI agent capabilities, limits, permissions, failure modes, and reproducible tests for research, forms,…
Nova7 min read
How to Stop Context Switching with a Workspace Agent
Use a task recovery packet to reduce context rebuilding, then compare a workspace agent with a maintained project note in a one-week test.
Nova3 min read
Workspace Agents for Solo Operators: When They Fit
Learn when a workspace agent fits solo work, which permissions and failure modes to inspect, and how to run a controlled 14-day buying…
Nova3 min read
What Are AI Workspace Agents? A Plain-Language Guide
AI workspace agents are a new category of AI that works inside your real workspace — files, browser, tools. Here's what they are and who…
Nova2 min read
Claude Managed Agents: What They Mean for Solo Companies
Claude Managed Agents gives builders a hosted agent runtime. Learn when that infrastructure helps a solo company, what it does not replace,…
Nova3 min read
AI Agent Workflow: Fixing What Vibe Coding Breaks
Turn vibe-coded prototypes into reviewable software with a bounded AI agent workflow: acceptance criteria, repository rules, tests, diff…
Nova8 min read
What Is Vibe Coding? Can Solo Founders Ship Faster?
Vibe coding lets anyone build with AI and plain language. Here's what it can do for a one-person company — and where it breaks.131 chars
Nova10 min read
What Are Claude Managed Agents?
Claude Managed Agents is Anthropic's hosted runtime for long-running agents. Learn what it manages, where it fits, its limits, and how…
Nova7 min read
Why AI Forgets Between Sessions—and How to Fix It
Diagnose why an AI loses context between chats by separating context windows, session history, long-term memory, retrieval, and privacy…
Nova9 min read
What Is a Persistent AI Agent — and Why Does It Matter?
A persistent AI agent doesn't forget you when the session ends. Here's what that actually means for how you work — and why it's becoming…
Nova10 min read
Why Your AI Forgets You Every Single Session
Every time you close a chat tab, your AI forgets everything. Here's what solo operators actually lose — and why it matters more than most…
Nova9 min read
Custom AI Agent Development: Architecture, Scope, and Acceptance
A practical guide to custom AI agent development: decide whether you need an agent, define requirements, design tools and state, control…
Nova12 min read
How to Build an AI Agent: From Task Contract to Recovery
A practical guide to building an AI agent from task definition and tool design through permissions, state, evals, observability,…
Nova10 min read
AI Agent Development Services: A Buy-vs-Build Guide
Evaluate AI agent development services by scope, architecture, security, evidence, pricing structure, contracts, and a practical paid-pilot…
Nova9 min read
AI Agent Use Cases: Real Examples and a Selection Guide
Choose an AI agent use case by inputs, tools, outputs, approval gates, and failure modes. Includes documented examples and a practical…
Nova8 min read
/blog/category/ai-agents