# Where Should Your AI Agents Run? By Dan Seyer, Founder, Build Marketing · Published 2026-10-06 > This guide is for founders, CMOs and business leaders deciding where their AI agents should live. It is the third of five parts. ## Where should your AI agents run? Run each agent where the data it needs and the people who check its work already are. There are five places: inside the tools your team already uses, on your team's desktops, on your website for people, on your website for other companies' AI agents (over the A2A protocol), and in the back office on a schedule. Start inside your own team, where a person sees every result and mistakes stay private, and move an agent toward customers only once it has earned trust. Then decide whose computers run it: your software vendor's, your AI provider's hosted service, or your own infrastructure when your data must stay with you. **AI agents for your business, part 3 of 5:** [What is an AI agent?](https://www.buildmarketing.ai/what-is-an-ai-agent.md) · [How to build an AI agent](https://www.buildmarketing.ai/how-to-build-an-ai-agent.md) · Where should AI agents run? · [Can you buy AI agents?](https://www.buildmarketing.ai/can-you-buy-ai-agents.md) · [Platforms to run your own agents](https://www.buildmarketing.ai/platforms-to-run-your-own-ai-agents.md) Test your website: [run MachineReady](https://www.buildmarketing.ai/machineready/) to see how AI agents read it, or [send our A2A agent](https://www.buildmarketing.ai/a2a/) to see if it can talk to theirs. ## AI Summary Where an agent runs decides who meets it, what it can reach and how much can go wrong. There are five places: inside the tools your team already uses, on your team's desktops, on your website for people, on your website for other companies' AI agents, and in the back office on a schedule. The rule of thumb is to run an agent where the data it needs and the people who check its work already are. Start where the downside is smallest, inside your own team, and move an agent closer to customers only once it has earned trust. Then decide whose computers it runs on: your vendor's, your AI provider's or your own. ## Background In [Part 1](https://www.buildmarketing.ai/what-is-an-ai-agent), we defined an agent and how to think about it. In [Part 2](https://www.buildmarketing.ai/how-to-build-an-ai-agent), we covered how to build one. This part answers the question most teams skip: where should it run? An agent that lives somewhere your team never goes is forgotten within a month. An agent that faces customers before it is ready can do real damage. Getting the place right is as important as getting the agent right. ## Five Places an Agent Can Run **Five places an agent can run** | Where it runs | Who it serves | Good first jobs | What to watch | Time to start | |---|---|---|---|---| | Inside the tools your team already uses | Your own people | Meeting prep, CRM updates, first drafts | It can see what its user can see | Hours | | On your team's desktops | One person at a time | Analysis, writing, building, file-heavy work | It acts with that person's access on their machine | Hours | | On your website, for people | Prospects and customers | Answering questions from your content, routing leads, booking calls | Accuracy and tone: it speaks for the brand | Days to weeks | | On your website, for other AI agents (A2A) | Buyers' AI agents doing research | Product facts, fit, booking a call | What you are willing to share with a machine | Days to weeks | | In the back office, on a schedule | The business | Monitoring, enrichment, weekly reports, data cleanup | Nobody is watching, so log and review its work | Weeks | The test: run the agent where the data it needs and the people who check its work already are. ### 1. Inside the tools your team already uses The fastest start. ChatGPT, Claude, Microsoft Copilot and Google Gemini can work as agents for one person or a team: research across the web, work through files and connect to tools such as Google Drive, Slack, HubSpot and Salesforce. Your CRM, help desk and marketing platform increasingly ship their own agents too. The agent sees what its user can see, which makes permissions simple and mistakes contained, because a person is right there to catch them. ### 2. On your team's desktops An agent that works beside one person on their own computer, with access to their files, browser and applications. This is where knowledge work gets done: analysis across a folder of spreadsheets, a long document drafted from research, a website or a report built and checked. Claude on the desktop and Claude Code work this way, as do similar tools from OpenAI and others. The person is the boss, in real time. ### 3. On your website, for people An agent that answers prospects and customers in a chat on your site, from your own content. It qualifies visitors, answers questions at any hour and books the next step. Because it speaks for your brand, accuracy and tone matter more here than anywhere else. Ground it strictly in your published content, tell it what it must never say, and hand anything sensitive to a person. Our site chat, [Ask BuildMarketing.ai](https://www.buildmarketing.ai/ask/), answers only from our own articles and pages and links to its sources. ### 4. On your website, for other AI agents The newest place and the least understood. Buyers are starting to send their own AI agents to research vendors. Those agents look for a published agent card and talk to it directly over A2A, the open Agent2Agent protocol, rather than reading pages. A company without one is described by whatever the buyer's agent can scrape. Our A2A agent tells a visiting agent what we do and who we work with, can check a website with MachineReady, and can pass a message to me without the buyer ever loading a page. You can [watch it happen](https://www.buildmarketing.ai/a2a/). For more on why this matters, see [Does Your Website Need to Speak Agent?](https://www.buildmarketing.ai/does-your-website-need-to-speak-agent) ### 5. In the back office, on a schedule An agent that runs on its own, every night or every Monday, on a server or a cloud service rather than anyone's laptop. It reads your systems, does the work and leaves the result for review: a competitor digest, enriched leads, a cleaned data set, a weekly report. Nobody watches it run, so logs and a regular review matter most here. The agent behind MachineReady works like this, scanning and learning in the background and proposing changes for my approval. ## How to Choose Ask four questions about the job: - **Who is it for?** Your own people point to places 1 and 2. Buyers point to places 3 and 4. The business as a whole points to place 5. - **What data does it need?** Run it where that data already lives, with the access it already has, rather than copying data somewhere new. - **Who checks its work, and when?** If a person checks every result in the moment, places 1 and 2 are natural. If checking happens later, choose place 5 and build in a review. - **What happens if it is wrong?** Start where a mistake is cheap and private. Move toward customers only once the record shows it is ready. A common path is to prove an agent in place 1 or 2, where a person sees every result, then promote it: onto a schedule in place 5 once it runs reliably, or onto the website in place 3 or 4 once its answers are consistently right. ## Whose Computers Does It Run On? Once you know where an agent meets its users, decide where it physically runs. There are three options: - **Your software vendor's cloud.** Agents built into Salesforce, HubSpot, Microsoft 365 or your help desk run inside that product. The least work, and your data stays where it already is, but the agent can only do what the vendor allows. - **Your AI provider's cloud.** Services such as Claude Managed Agents host the agent and a private workspace for it, run it on a schedule and keep its logs, so you manage no servers. OpenAI, Google, AWS and Microsoft offer similar services. A good balance of control and effort for most businesses. - **Your own infrastructure.** Frameworks such as the Claude Agent SDK let developers run agents on your own servers or cloud account, next to your own data. The most control, and the most work. Worth it when data must not leave your environment or the agent is part of your product. Data rules decide many of these choices. Before you pick, check where the agent's data will be processed and stored, whether the provider trains on it, and what your customers' contracts and your industry's regulations require. Part 5 compares the platforms in detail. ## How We Run Ours At Build Marketing, the five places map to real agents. Our team works with Claude in place 1 and on the desktop in place 2, which is also how this website and its tools are built. The site chat runs in place 3, the A2A agent in place 4, and the MachineReady learning agent in place 5. Each moved outward only after it had earned trust closer to home. ### Test yourself 1. What is the best rule of thumb for where an agent should run? - A. Wherever the vendor recommends - B. Where the data it needs and the people who check its work already are - C. Always on your own servers - D. On your website, so customers see it Answer: B. An agent placed where its data and its reviewers already are gets used and gets checked. One placed anywhere else tends to be forgotten. 2. Where should a brand-new agent usually start? - A. Facing customers on your website - B. Inside your own team, where a person sees every result - C. Running unattended on a schedule - D. Talking to other companies' agents Answer: B. Start where mistakes are cheap and private, then promote the agent as its record earns trust. 3. What is A2A? - A. A way to train AI models - B. An open protocol that lets AI agents talk to each other directly - C. A website analytics tool - D. A type of CRM Answer: B. A2A, the Agent2Agent protocol, lets a buyer's AI agent find your agent card and ask your agent questions directly, without reading pages. 4. An agent runs every night with nobody watching. What matters most? - A. A bigger model - B. A log of what it did and a regular review - C. A chat interface - D. Running it on a laptop Answer: B. Unattended agents need a record of their actions and a person who reviews it, because nobody sees the work as it happens. 5. When is running an agent on your own infrastructure worth the extra work? - A. Always - B. When data must not leave your environment or the agent is part of your product - C. Only for chatbots - D. Never, hosted is always better Answer: B. Your own servers give the most control, which pays off when data rules require it or the agent is part of what you sell. Now put it to work on your own website: [run MachineReady](https://www.buildmarketing.ai/machineready/) to see how AI agents read it, or [send our A2A agent](https://www.buildmarketing.ai/a2a/) to see if it can talk to theirs. Both are free. ## Conclusion Where should your AI agents run? Where the data they need and the people who check their work already are. Start inside your own team, where a person sees every result. Promote proven agents to a schedule or to your website. Then choose whose computers run them based on how much control you need and where your data is allowed to go. Next in the series: [Can You Buy AI Agents? What Exists in 2026](https://www.buildmarketing.ai/can-you-buy-ai-agents). Can buyers' agents talk to your website? [Send our A2A agent to your site](https://www.buildmarketing.ai/a2a/) to find out, or [run MachineReady](https://www.buildmarketing.ai/machineready/) for a full report. [Get in touch](https://www.buildmarketing.ai/#Get-In-Touch) if you want help deciding where your first agent should live.