--- title: "FAQ - AI Adoption Questions Answered | Cerevisor" description: "Answers to 33 questions CEOs and founders ask about AI adoption: ROI, data security, organizational readiness, pricing, and how Cerevisor compares to hiring in-house, Big 4, freelancers, and AI agencies." canonical_url: https://cerevisor.com/faq type: page --- # Frequently Asked Questions Honest answers to the questions CEOs, founders, and operators ask about AI adoption and the Cerevisor harness. ## AI Agents and Harnesses, Explained - **What is an AI agent?**: An AI agent is a language model given a goal, a set of tools, and the latitude to decide its own steps. Instead of answering one question and stopping, it can plan, call tools (search the web, read a file, hit an API), check its own work, and loop until the task is done. A chatbot responds; an agent acts. In Cerevisor you compose agents on a visual canvas and decide exactly how much autonomy each one gets. - **What is an AI harness?**: A harness is the layer between you and the raw AI models that makes a fleet of agents actually runnable. It orchestrates who does what, passes context between steps, calls tools and MCP servers, keeps humans in the loop, and records everything that happened. Without one you are gluing prompts together by hand and hoping it holds. Cerevisor is a desktop harness, so that orchestration, auditing, and provider-switching ships out of the box. - **What is the difference between a chatbot and an AI agent?**: A chatbot is one model and one prompt: you ask, it answers, the conversation is the product. An agent is given a goal and the tools to pursue it across many steps, often handing off to other agents along the way. Chatbots are great for quick answers; agents are for work that has a process: research, drafting, review, routing, follow-up. The moment your task needs more than one prompt, you are really building a workflow, which is what a harness is for. - **What is an AI skill?**: A skill is a reusable, packaged capability an agent can call: a saved prompt, procedure, or mini-workflow that encodes how to do one job well, such as writing a brief, extracting data from an invoice, or reviewing code against a checklist. Instead of re-explaining the task every time, you build the skill once and any agent can use it. Cerevisor includes a skills library so your team's best procedures become assets you reuse, not instructions you retype. - **What is a multi-agent workflow?**: It is several specialized agents working together on one job, each handling the part it is best at. A planner breaks down the work, an extractor reads source material, a writer drafts, a reviewer checks, and a router decides what runs next. This mirrors how a team operates and produces better results than asking one model to do everything in a single prompt. Cerevisor's canvas is built for exactly this: you wire the agents together and watch the work flow between them. - **What is MCP (Model Context Protocol)?**: MCP is an open standard for connecting AI models to tools and data: filesystems, browsers, databases, and your own internal systems. A model that speaks MCP can call those tools without anyone writing custom glue code for each one. Cerevisor's runtime is MCP-aware out of the box, so you plug in an MCP server and your agents can use it as a tool, with every call captured in the run's audit trail. - **What does 'human in the loop' mean?**: It means a person stays in control at the points that matter: approving an action before it runs, reviewing output before it ships, or being asked to decide when the agent is unsure. Full autonomy is rarely what you want for real work; you want speed where it is safe and a checkpoint where judgment is required. Cerevisor lets you place approval and review steps anywhere on the canvas, so agents move fast on the routine parts and pause for you on the consequential ones. - **What is a local-first AI app, and why does it matter?**: Local-first means the software runs on your own machine and your data stays there rather than passing through a vendor's servers. For AI work that matters because your prompts, your provider API keys, and your run history are sensitive. Cerevisor runs locally and talks straight to whichever AI providers you choose; your keys never leave your device, and Cerevisor never sees your prompts or outputs. ## Building and Automating with AI - **How do I build an AI agent?**: At the simplest level you give a model a clear goal, the tools it needs, and instructions for how to behave, then test it on real tasks and refine. The hard part is rarely the first prompt; it is the orchestration around it: handing context between steps, calling tools reliably, knowing when to stop, and seeing what went wrong. A harness gives you that scaffolding so you focus on the logic. In Cerevisor you drag an agent onto the canvas, pick its model, give it instructions and tools, and run it, with no glue code to write. - **Do I need to know how to code to build AI agents?**: No. Cerevisor's canvas is built for people who think in workflows, not code: you compose agents, connect them, and add approval steps visually. If you do write code, nothing gets in your way, and you can drop in custom logic and connect your own tools via MCP. For most people the real constraint is iteration speed on the workflow, not engineering capacity, and that is what the canvas removes. - **How do I automate tasks in my work and life with AI?**: Start by picking one repeatable task that eats your time and has a clear input and output: triaging an inbox, turning notes into a summary, drafting first-pass replies, pulling data out of documents. Map the steps you take by hand, then assign each step to an agent and put a review checkpoint wherever a mistake would be costly. Cerevisor is built for exactly this loop: build the workflow once, run it on demand, inspect what happened, and improve it, so a one-off automation becomes something you can trust to repeat. - **How is this different from automation tools like Zapier or Make?**: Classic automation tools connect apps with fixed if-this-then-that rules, and they are excellent when the steps never vary. AI agents handle the messy parts those tools cannot: reading unstructured text, making judgment calls, writing prose, deciding what to do next. Cerevisor is for the work that needs reasoning at each step, not just data moving between apps, and it keeps a human in the loop where the decision actually matters. - **Where do I start if I have never built an agent before?**: Download Cerevisor and run the prebuilt agents in the guided onboarding; you will have a multi-agent workflow running within minutes before you build anything of your own. From there, pick one real task, copy a template close to it, and adjust. You learn the concepts (agents, skills, tools, review steps) by running them, not by reading about them first. - **What kinds of work can AI agents handle today, and what should stay manual?**: Agents are strong at research, drafting, summarizing, extracting and reformatting data, first-pass review, and routing work to the right next step. They are still unreliable on anything needing real-world judgment, high-stakes irreversible decisions, or guaranteed accuracy without a human check. The practical answer is to let agents do the volume and keep yourself on the checkpoints, which is the entire reason Cerevisor makes human-in-the-loop review a first-class part of every workflow. ## About the Harness - **What is the Cerevisor harness?**: Cerevisor is a desktop app for building, running, and refining multi-agent AI workflows on a visual canvas. You compose your own agents, hand work between them, and keep humans in the loop wherever judgment matters. It runs on your machine and talks directly to the AI providers you already use. - **Who is it built for?**: Operators, founders, consultants, and small teams who want AI inside their daily workflows without hiring an in-house ML team or signing a year-long enterprise contract. It is designed for people who think in workflows: ops leads automating internal processes, founders building product features, consultants packaging repeatable expertise. You do not need to write code, but the canvas does not get in your way if you do. - **Is this a SaaS product or a desktop app?**: Desktop app. The harness runs on Windows and macOS, on your machine. There is no Cerevisor cloud account to provision, no team workspace to manage, and no server-side runtime in the path of your runs. You bring your own provider keys; we never see them. - **How do I get started?**: Download the installer for Windows or macOS, run the guided onboarding, and try the prebuilt agents. You will be running your first multi-agent workflow within minutes. Add your provider API keys when you are ready to use your own models. The app is in active alpha, free to start, with a 7-day full Pro trial. ## Privacy and Security - **Where does my data go when I run a workflow?**: From the harness on your machine straight to the AI provider you chose for that agent: Anthropic, an OpenAI-compatible endpoint, Ollama, Codex CLI, or whatever else you wired in. Cerevisor servers are not in that path. We do not see your prompts, your runs, or your outputs. - **Where are my provider API keys stored?**: Locally on your machine. They never leave the device, they are never transmitted to Cerevisor, and we could not retrieve them if asked. Removing the harness removes them with it. - **Are my workflows or runs uploaded anywhere?**: No. Workflows live as .cerevisor files and worlds live as .cerevisor-world files on your disk. Run artifacts (NDJSON audit logs, outputs, intermediate state) stay local. Nothing is synced to Cerevisor unless you explicitly export and share it yourself. - **What about audit trails for compliance and reviews?**: Every run produces an NDJSON audit log on disk covering every prompt, tool call, model response, and approval. You can replay a run end to end, diff today against last week, and answer 'why did the agent do that?' from data instead of memory. The files are yours, in a format you can pipe into whatever compliance or analytics tooling you already use. - **Can I run it offline with local models?**: Yes. Point an agent at Ollama or any OpenAI-compatible local endpoint and the workflow runs without an internet connection. You can also mix local and cloud providers in the same workflow when you want privacy on some steps and frontier capability on others. ## Models, Providers, and MCP - **Which AI providers does the harness support?**: Anthropic (Claude), any OpenAI-compatible endpoint (OpenAI, Groq, Together, OpenRouter, Azure OpenAI, and similar), Ollama for local models, and Codex CLI for terminal-based coding agents. Adding a new OpenAI-compatible endpoint is a configuration change, not a rewrite. - **Can I mix providers inside one workflow?**: Yes, and that is one of the main reasons to use a harness. Use a frontier model for planning, a fast cheap model for extraction, a local model for sensitive steps, and a specialist model for code review, all in one workflow. Each agent picks its own provider. - **How does MCP work in Cerevisor?**: The runtime is MCP-aware out of the box. Plug in any MCP server (filesystem, browser, database, custom internal tools) and your agents can call them as tools without you writing glue code. Every MCP call shows up in the audit trail like the rest of the run. - **Will the harness be outdated in six months as models change?**: The model landscape changes fast and the harness is built for that. It does not lock you to one provider, and adopting a new endpoint or model is a config change, not a rewrite. The runtime is updated regularly to keep up with new providers, MCP servers, and tool patterns so your workflows keep running on the best model for the job. ## Pricing and Value - **What does it cost?**: Free to start, with a 7-day full Pro trial that unlocks every paid feature on real work. See the pricing page for current Pro pricing, or to join the Pro waitlist while paid plans are still in pre-launch. Pro is built around individuals and small teams, not enterprise procurement. No implementation fees, no required engagement. You pay for the harness; you pay your AI providers separately for model usage. - **Why pay for the harness instead of using ChatGPT or Claude directly?**: One-prompt chat tools are great when one model with one prompt is enough. Real workflows almost never are. You typically need a planner, an extractor, a writer, a reviewer, and a router; you need to call tools and MCP servers; you need to replay what happened. Bolting that onto a chat UI means reinventing the orchestration layer. The harness ships that out of the box. - **Why use the harness instead of stitching together our own multi-agent setup?**: You can. Going DIY means writing glue code, debugging context plumbing, building your own audit trail, wiring up MCP servers, and maintaining all of it. Teams spend months on this and end up with something that works for one workflow and is fragile beyond it. The harness gives you a working canvas, multi-model orchestration, NDJSON audit logs, and an MCP-aware runtime on day one. You bring your own provider keys and your own logic; the plumbing stays predictable. - **Are there founding-user prices?**: Yes. Lock in founding-user status during the alpha and your founding price stays with you for life, even after standard pricing is announced. See the pricing page for details. The harness is in active development and feedback from early users actively shapes the roadmap. ## Why a Harness - **Why use the harness instead of hiring AI engineers?**: Hiring is the right move when you have a long-running product surface that demands deep custom infrastructure. For most operators the constraint is not engineering capacity, it is iteration speed on workflows. A senior AI engineer in Western Europe runs EUR 80,000-150,000/year before benefits and equity, and 6-12 months to ramp. The harness lets a small team run multi-agent workflows on day one, with the option to layer in custom code where it actually matters. Use it alongside engineers, not instead of them. - **Why not just stick with a single AI chatbot or a one-agent tool?**: One-agent tools are fine when one model with one prompt is enough. Real workflows almost never are. You typically need an architect to plan, an extractor to read, a writer to draft, a reviewer to check, and a router to decide what runs next. Bolt those onto a chat UI and you end up reinventing the orchestration layer. The harness is built for that from the start: visual canvas, per-agent provider override, skills library, and a full audit trail of every run. - **What makes the Cerevisor harness different from other agent platforms?**: Three things. First, it runs locally on your machine, so prompts, runs, MCP traffic, and provider keys never reach Cerevisor. Second, it is provider-neutral by design: Anthropic, Ollama, OpenAI-compatible endpoints, and Codex CLI all work, and you can mix providers per agent in one workflow. Third, every run lands as an NDJSON audit trail you can replay, diff against last week's, and answer 'why did the agent do that?' from data, not memory. ## Support, Updates, and Lock-in - **What happens after I subscribe? Am I locked in?**: No. Cancel anytime from the Lemon Squeezy customer portal and you keep Pro through the end of the period you have already paid for. The first paid purchase has a 14-day money-back request window. Workflows and worlds live as plain files (.cerevisor and .cerevisor-world) on your machine, so even if you stop subscribing, what you built is still yours to version, share, and re-run. - **Do I get updates and bug fixes after I install?**: Yes. Cerevisor is in active alpha with regular releases. Updates ship through the desktop app and you receive them for as long as your subscription is active. Founding-user pricing locks in for life when you subscribe during the alpha, so future price changes do not affect you. - **Can I share workflows with my team?**: Yes. Workflows and worlds are plain files on disk, so sharing is whatever your team already does for files: a shared drive, a git repo, an attachment in chat. Provider keys stay on each person's machine, so teammates use their own credentials when they re-run what you sent. - **How do I report a bug or request a feature?**: Email support@cerevisor.com or use the contact form in the footer. Alpha members get a direct path to the team, and feedback actively shapes the roadmap. If something breaks, we want to hear about it.