# Questions about AI agents for business, answered

- [Where do I start with AI in my business?](https://kazi.apifunnel.ai/answers/where-to-start-with-ai-in-your-business): Start with yourself, not with AI. Find your biggest unlocks, then point AI at them. How Kazi gives AI a shape through playbooks.
- [What should a small business use AI for first?](https://kazi.apifunnel.ai/answers/what-to-use-ai-for-first-in-a-small-business): Pick the job you do every week that you'd hand off tomorrow if you could. Why a recurring job beats a one-off question as your first AI win.
- [How do I find the AI use cases that actually matter for my business?](https://kazi.apifunnel.ai/answers/find-the-ai-use-cases-that-matter): Look at where your week goes, not at lists of AI ideas. The use cases that matter are the jobs only you do today that someone else could.
- [Why does ChatGPT feel like it doesn't do anything useful for my business?](https://kazi.apifunnel.ai/answers/why-chatgpt-feels-useless-for-your-business): A chat window gives you words about the work, not the work. What changes when AI is connected to your apps and runs your jobs, as in Kazi.
- [What's the difference between an AI chat and an AI agent?](https://kazi.apifunnel.ai/answers/difference-between-an-ai-chat-and-an-ai-agent): A chat answers you. An agent works in your apps until the job is done. Plain-words difference, and what it means for a small business.
- [Do I need someone technical to use AI in my business?](https://kazi.apifunnel.ai/answers/do-you-need-someone-technical-to-use-ai): No. If you can explain a job to a new hire, you can give it to an agent. What still takes a little care: connections and access.
- [How do I make AI do a job the same way every time?](https://kazi.apifunnel.ai/answers/make-ai-do-a-job-the-same-way-every-time): Save the procedure, not the prompt. How a Kazi playbook turns a job you did once by talking into one that runs the same way again.
- [Can AI give me a morning rundown of my email, Slack and calendar?](https://kazi.apifunnel.ai/answers/ai-morning-rundown-for-a-business-owner): Yes. Ask once and Kazi checks your email, Slack, calendar and anything else you connect every morning, then sends you one rundown.
- [Is it safe to connect AI to my email and Slack?](https://kazi.apifunnel.ai/answers/is-it-safe-to-connect-ai-to-email-and-slack): It is when the limits are enforced by the platform, not the prompt. What to check, and how Kazi's Only read, Can update and Ask Mode work.
- [How do I get my team to actually use AI?](https://kazi.apifunnel.ai/answers/get-your-team-to-actually-use-ai): Hand them a job that already works, not a tool to figure out. How shared projects and playbooks in Kazi get a small team using AI.
- [Is AI worth it for a business our size?](https://kazi.apifunnel.ai/answers/is-ai-worth-it-for-a-small-business): Small businesses gain the most: you have the fewest people for the most jobs. How to tell if it's worth it before you spend anything.
- [How soon does AI pay for itself in a small business?](https://kazi.apifunnel.ai/answers/how-soon-does-ai-pay-for-itself): As soon as it does a job you'd otherwise spend your own hours on. How to measure it honestly, and what it costs to run in Kazi.
- [How do I connect my own MCP server to an AI assistant?](https://kazi.apifunnel.ai/answers/connect-your-own-mcp-server-to-an-ai-assistant): Paste the server's HTTPS URL, add an API key or sign in with OAuth, and its tools show up. How it works in Kazi, and what to check first.
- [How do I give an AI agent read-only access to my business apps?](https://kazi.apifunnel.ai/answers/give-an-ai-agent-read-only-access-to-business-apps): Set each connection to read-only and make sure the platform enforces it, not the prompt. How Kazi's Only read and Ask Mode work.
- [How do I get an AI agent to remember a correction on its next scheduled run?](https://kazi.apifunnel.ai/answers/get-an-ai-agent-to-remember-corrections-between-runs): Most scheduled agents start every run fresh, so corrections vanish. Keep every run on one thread. How Kazi's scheduled subagents do it.
- [Why does my AI assistant forget things in a long conversation?](https://kazi.apifunnel.ai/answers/why-an-ai-assistant-forgets-things-in-a-long-conversation): Long chats overflow what the model can read, so early details drop out. What actually happens, and how Kazi keeps one thread without a limit.
- [How much does an AI agent cost for a small business?](https://kazi.apifunnel.ai/answers/how-much-does-an-ai-agent-cost-for-a-small-business): Seat plans run per person per month; usage pricing charges for what you run. Kazi's numbers: 25 free credits, then packs from $5, no subscription.
- [How do AI agent credits work, and what does one message cost?](https://kazi.apifunnel.ai/answers/how-ai-agent-credits-work): A credit is a block of model tokens. In Kazi one credit is 100,000 tokens at GPT-5.6 Luna rates, and a typical message costs well under one.
- [Can I use my own OpenAI or Anthropic API key with an AI agent?](https://kazi.apifunnel.ai/answers/use-your-own-openai-or-anthropic-api-key-with-an-ai-agent): Yes, on agents that support bring-your-own-key. Kazi takes OpenAI, Anthropic, Google Gemini and DeepSeek keys, and those turns don't use credits.
- [Is there a HIPAA-compliant AI agent that does more than chat?](https://kazi.apifunnel.ai/answers/hipaa-compliant-ai-agent-that-does-more-than-chat): Most HIPAA AI tools are chat windows. Kazi Private is a full agent on your own instance, hosted under a BAA on open-weight models, run for you.
- [Is there an AI agent that runs in the browser with nothing to install?](https://kazi.apifunnel.ai/answers/ai-agent-that-runs-in-the-browser-with-nothing-to-install): Several agents push deeper work to a desktop app. Kazi runs entirely in the browser and its cloud: your apps, code in a sandbox, no install.
- [Can I give an AI assistant work by voice, hands-free, from my phone?](https://kazi.apifunnel.ai/answers/give-ai-assistant-work-by-voice-hands-free): Voice chat that just answers isn't enough; the job has to run. Kazi Voice takes work hands-free and keeps one thread with your texts and the web.
- [Can an AI agent text me when a long task is finished?](https://kazi.apifunnel.ai/answers/get-a-text-when-an-ai-agent-finishes-a-task): You shouldn't have to watch a tab. Kazi texts you from a shared number when work finishes, and you can text back on the same thread.
- [How can an AI agent call my own API without me writing an integration?](https://kazi.apifunnel.ai/answers/let-an-ai-agent-call-your-own-api): Expose it as a remote MCP server, or connect it and let the agent write the calls in a sandbox. Both work in Kazi, with read-only control.
- [How can a small team share an AI agent without giving it access to everything?](https://kazi.apifunnel.ai/answers/share-an-ai-agent-with-a-small-team): Scope access by project, not by company. In Kazi each project has members with roles and its own agent with a read or write list per app.
- [How do I turn a task I did once with an AI assistant into a repeatable workflow?](https://kazi.apifunnel.ai/answers/turn-a-one-off-ai-task-into-a-repeatable-workflow): Work it out in a chat first, then extract the steps into a playbook and schedule it. How Kazi turns a working thread into a playbook.
- [Should I build automations in n8n or let an AI agent write the code?](https://kazi.apifunnel.ai/answers/n8n-or-an-ai-agent-for-workflow-automation): Visual builders make you wire nodes and still write code in them. An agent writing one script is faster to change. When each one wins.
- [How do you stop MCP tool definitions from filling an agent's context window?](https://kazi.apifunnel.ai/answers/stop-mcp-tool-definitions-filling-the-context-window): Don't load every tool schema up front. Let the agent search for tools and read exact schemas only when it needs them. How Kazi does it.
- [How do you make an AI agent check its prerequisites before it acts?](https://kazi.apifunnel.ai/answers/make-an-ai-agent-check-prerequisites-before-it-acts): Put the check in the tool call, not the system prompt: a required field the agent must answer honestly. The Proof of Work pattern we use in Kazi.
- [Do positive instructions work better than prohibitions in agent prompts?](https://kazi.apifunnel.ai/answers/positive-instructions-vs-prohibitions-in-agent-prompts): Mostly yes for tool choice: name the action and when it helps. Keep hard rules as plain prohibitions. Before-and-after examples from Kazi.
- [Can an AI meeting assistant do things during the call, not just take notes?](https://kazi.apifunnel.ai/answers/ai-meeting-assistant-that-acts-during-the-call): Most meeting bots summarize afterward. Kazi joins Zoom, Meet, Teams, Webex and Slack huddles and can post in chat and share on screen live.
- [What can an AI chief of staff actually do for a small business owner?](https://kazi.apifunnel.ai/answers/what-an-ai-chief-of-staff-does-for-a-small-business): It takes a job, works across your apps, follows up and remembers what you decided. What that looks like in Kazi, and what it can't do.
- [What is a company brain, and does a small business need one?](https://kazi.apifunnel.ai/answers/what-is-a-company-brain): A shared record of decisions, exceptions, people and context that agents read before they act. Why it matters more than the connectors.
- [What should I check before giving an AI agent access to company tools?](https://kazi.apifunnel.ai/answers/check-before-giving-an-ai-agent-access-to-company-tools): Who enforces read-only, what happens with nobody watching, where code runs and who trains on your data. The checklist I'd use, and Kazi's answers.
- [Will an AI agent provider train its models on my business data?](https://kazi.apifunnel.ai/answers/will-an-ai-agent-train-on-my-business-data): It depends on two parties: the agent company and the model provider behind it. Kazi doesn't train on your content. What to check for the rest.
