Articles

Articles about Doka and AI agents

How Doka works, why a desktop agent matters, and what is happening with AI. page 6.

July 17, 2026·4 min read

What Is MCP (Model Context Protocol), Explained Simply

MCP is a standard that gives an AI model access to external tools. A plain-language explanation, examples, and how to connect an MCP server to an agent.

mcptoolsagents
July 17, 2026·2 min read

DeepSeek Locally on Your Computer — Private and Without Limits

How to run DeepSeek on your own computer and work with it locally — no data sent to outside servers, no limits, no subscription. With access to files and the terminal through an agent.

deepseekmodelslocal
July 17, 2026·4 min read

An AI Agent for Writing Code: Coding Alongside an Agent Locally

How an AI coding agent differs from autocomplete, what the 'describe the task — the agent writes, runs, and fixes' loop looks like, which model to pick, and where the trust boundary sits. A practical breakdown using Doka.

codeagentsdevelopment
July 17, 2026·3 min read

AI for Working With Excel: Analyzing Spreadsheets Locally, No Cloud

How to use AI for working with Excel spreadsheets — merging data, finding discrepancies, computing totals, and preparing reports without uploading work files to the cloud. A look at what it can do, and an honest look at its limits.

excelspreadsheetsprivacy
July 17, 2026·2 min read

AI in the Terminal: An Agent That Runs Commands and Fixes Errors Itself

How an AI agent works right in the terminal — runs code, builds a project, runs tests, and fixes errors itself in a loop, with confirmation for risky commands. Using the Doka desktop agent as the example.

terminalagentscode
July 17, 2026·4 min read

How to Connect an MCP Server to an AI Agent: A Step-by-Step Guide

A step-by-step walkthrough of connecting an MCP server to a desktop agent — where to find a server, what to fill in, how to pass tokens, and what to do if the tools don't show up. Using Doka as the example.

mcptoolssetup
July 17, 2026·4 min read

Model Context Protocol Explained: How the Protocol Actually Works

A technical breakdown of Model Context Protocol (MCP) — what it's made of, how the client-server relationship works, what transports exist, and why the standard was needed in the first place.

mcpprotocolarchitecture
July 17, 2026·4 min read

How to Customize an AI Agent to Fit You: Projects, Skills, and Your Own Rules

How to turn a general-purpose AI agent into a personal assistant for your work — through projects with their own system prompt, Markdown skills, connecting your services, and memory of your preferences. A practical breakdown using Doka.

setupagentsskills
July 17, 2026·5 min read

AI for Document Analysis: Extract, Compare, and Check — Locally

How to use AI for document analysis — extracting data, comparing versions, finding risks in contracts, and pulling together reports. A breakdown by profession, and an honest look at privacy, formats, and limits.

documentsanalysisprivacy
July 17, 2026·4 min read

How to Install AI on Your Computer for Free: Options and the Simplest Path

What it actually means to install AI on a computer, how local AI differs from a browser chat, and how to set it up for free, without a subscription or the command line. A look at the options and the pitfalls.

installationlocalfree
July 15, 2026·3 min read

An AI Agent on a Schedule — Morning Briefings and Routine on Autopilot

How to set up an AI agent that runs on a schedule: builds a morning briefing, tracks news, and handles routine tasks by cron — on its own, with no input from you. Using the Doka desktop agent as the example.

automationschedulesagents
July 14, 2026·3 min read

Custom Skills for an AI Agent — Teaching a Model to Work by Your Own Rules

How to give a model your own procedures, checklists, and answer style through Markdown skills — so you stop repeating the same instructions in every chat. Using the Doka desktop agent as the example.

skillssetupagents