--- title: "How to Build an AI OS for Your Business, Step by Step | Kylon" description: "A practical guide to building a business AI operating system: pick the first job, write the context, connect data, add Agents and approvals, then automate." url: "https://kylon.io/ai-os/how-to-build" language: "en" --- Guide8 min read # How to build an AI OS for your business Start with one recurring job, give it the context and data it needs, put the Agent in the Room where the team already talks about that work, and keep a person in front of anything that leaves the building. Then add the next job. Kylon TeamProduct October 26, 2026 1. 1 Write it down Context 2. 2 Connect tools Data 3. 3 Give it the job Agents 4. 4 Add to the Room Workspace 5. 5 A person signs off Approvals Usable from here 6. 6 Schedule it Automations 7. 7 Build the tool Apps The build path. Each step adds one layer of the AI OS, and the job is usable after step 5. ## Start with one job, not the whole company An AI OS grows one job at a time. The first job decides whether the team trusts the rest, so pick one that is easy to check. - **It repeats.** Weekly reports, inbox triage, client follow-ups, CRM updates after calls. - **Its inputs already live in your tools.** Mail, calendar, CRM, documents, a finance system. - **A person checks the result today.** That person becomes the approver, so nothing about who signs off changes. Write the job down in two sentences: what comes in, and what a good result looks like. That is the brief for every step below. ## The seven steps 1. 1 ### Write down the context What the company does, who decides what, and the rules for this job: pricing limits, tone for clients, what counts as urgent. In Kylon this goes into Workspace knowledge, which every Agent reads, and into the Agent's own instructions. 2. 2 ### Connect the data the job touches Add the Connections for the mailbox, calendar, CRM or documents the job reads. Grant each one only to the Agents and people who need it. Data with no home yet, such as a tracker kept in a spreadsheet, can become a Database App. 3. 3 ### Create the Agent and give it the job Give the Agent a name, a role and the skills for the job. If the work already runs in Claude Code or Codex on someone's computer, connect that one instead with Invite my agent, so the setup you built keeps working. See [Claude Code AI OS for teams](https://kylon.io/ai-os/claude-code). 4. 4 ### Put it in the Room where the work is discussed A new Agent is private and in no Room. Add it to the Room where the team already talks about this job, so requests and results land where people read. 5. 5 ### Keep a person in front of anything that leaves the Room Emails, record changes and anything a client will see come back as a draft with Approve and Edit. The person who checks this work today is the one who approves it. 6. 6 ### Run it on a schedule or a trigger Once the job works when someone asks, make it an Automation: every Monday at 9, when a form comes in, when a message arrives. The result still lands in the same Room and still waits for approval. 7. 7 ### Build the App when the same table keeps coming up When people keep asking for the same list or dashboard, ask an Agent to build it as an App. It opens next to the conversation and reads the same data the Agents write. ## Review it after 30 days Read the threads for the job and answer four questions. The thread already has the request, the draft, the edits and the approval, so this is reading, not a survey. - How many drafts were approved as written, and how many were edited first. - Which requests the Agent could not finish, and what context or access was missing. - Who outside the original team started asking it for work. - Which step a person still does by hand that the Agent could prepare. Fix the context or the access behind each miss, then pick the next job. The second job reuses the context, Connections and Room from the first, which is the point of an operating system. ## Watch one built live Liam Ottley sets up his own business on Kylon in [his full course livestream](https://www.youtube.com/watch?v=ONd2UNBmQ40&t=4593s): onboarding, connecting Notion, Slack and Google Calendar, approving the first Agents, and later [Agents handing work to each other](https://www.youtube.com/watch?v=ONd2UNBmQ40&t=11010s). Kylon sponsors Liam's videos about Kylon. ## Questions people ask **Do I need to code to build an AI OS?** No. The workspace, Connections, Agents, Automations and Apps are set up in Kylon, and Apps are built by asking an Agent. People who already work in Claude Code or Codex can also drive the workspace from there with the Kylon CLI. **What should the first job be?** A recurring job whose inputs are already in your tools and whose result a person checks today. That person becomes the approver. **When should a job become an Automation?** After it has worked on request for a while and the approvals are mostly made as written. The Automation runs the same job on a schedule or a trigger and still posts the result for approval. ## Keep reading [All AI OS guides](https://kylon.io/ai-os) [ ### Claude Code AI OS for teams Keep the CLAUDE.md, skills and tools you built, and let the whole team use the same agent in a Room. ](https://kylon.io/ai-os/claude-code)[ ### AI OS examples by team Accounting, property management, recruiting, sales, agencies and internal tools: the jobs, the Agents and what a person approves. ](https://kylon.io/ai-os/examples)[ ### What is an agentic operating system? How an agentic OS differs from a computer OS and from the AIOS research project, and what to look for in one. ](https://kylon.io/ai-os/agentic-operating-system) Build an AI OS for your team, or for your clients. [Build your AI OS](https://app.kylon.io/sign-up) [Build AI OS for your clients](https://kylon.io/partner)