# First ElevenLabs Voice Agent: 8 Setup Mistakes to Avoid > First ElevenLabs voice agent mistakes: the default prompt left in, no AI disclosure, a slow LLM, testing a Draft and going live too soon. Source: https://learn.ynteractive.com/content/blog/elevenlabs-first-agent-mistakes · Updated 2026-10-20 · Free from Stepthrough (https://learn.ynteractive.com) Quick answer The biggest mistake with a first ElevenLabs [voice agent](https://learn.ynteractive.com/content/glossary/voice-agent) is leaving the [system prompt](https://learn.ynteractive.com/content/glossary/system-prompt) as *You are a helpful assistant.* That is what every blank agent starts with, and it tells the agent nothing about your business, your hours or what it must never say. The others follow from the same rush: a greeting that hides that it is an AI, a slow model, testing before you **Publish**, and putting the agent on a real line while the messages still sit in **Conversations**. The [Your First Voice Agent in ElevenLabs lesson](https://learn.ynteractive.com/modules/elevenlabs-first-agent) avoids each one as you build. Last updated October 20, 2026 [Take the free module →](https://learn.ynteractive.com/courses/ai-agents-101/6)Module 6 of the free [AI Agents 101](https://learn.ynteractive.com/courses/ai-agents-101) course, about 9 minutes. No account needed. By [Robert Breen](https://learn.ynteractive.com/content/about) · Published October 20, 2026 · Updated October 20, 2026 · 5 min read ElevenLabs · Voice Agents · Troubleshooting · AI Receptionist The example business is made up: Cedar Creek Plumbing, a small family company, and Riley, the after-hours [AI receptionist](https://learn.ynteractive.com/content/glossary/ai-receptionist) you build for it in ElevenLabs Agents (ElevenAgents). ## What are the most common first voice agent mistakes? | # | Mistake | Fix | | --- | --- | --- | | 1 | Keeping *You are a helpful assistant.* | Paste a real job: emergencies, details to collect, hours, rules | | 2 | No rule against guessing | Add: never guess a price or promise an arrival time | | 3 | Long, chatty answers | Add: one or two sentences, like a real phone call | | 4 | A greeting that hides the AI | Name the company, say it is AI, say the call may be recorded | | 5 | Choosing a voice without listening | Click play, then **Use** | | 6 | A big, slow LLM | Pick a fast model, like **Gemini 3.5 Flash** | | 7 | Testing while it still says **Draft** | Click **Publish** and confirm first | | 8 | Going live with no alert | Read **Conversations**, then connect a number and an alert | ## Which mistakes are in the system prompt? **1. Keeping the default prompt.** Click inside **System prompt** and replace the default with the real job. Riley's prompt lists what counts as an emergency (active leak, burst pipe, no water, sewage backup), tells it to collect a name, phone number and address and read the number back, gives the office hours, and says when the callback comes: within 15 minutes for emergencies, the next business morning for anything else. Without the hours in the prompt, the agent has to guess them. **2. No rule against guessing.** A made-up price or arrival time on the phone sounds like a promise. Riley's rules say: never guess a price or promise an arrival time, and say the plumber will go over that on the callback. Safety rules belong here too: for a gas smell, tell the caller to leave the house and call the gas company or 911 first. **3. Long, chatty answers.** What reads fine on screen is too long when spoken. The prompt says to keep answers to one or two sentences, like a real phone call, and to be calm and kind, because people calling at night are often stressed. ## Which mistakes are about how it sounds? **4. A greeting that hides the AI.** The **First message** is the first thing callers hear. Riley's says: *Hi, thanks for calling Cedar Creek Plumbing. I'm Riley, the after-hours AI assistant, and this call may be recorded. How can I help you tonight?* Callers should always be told they are talking to AI, and ElevenLabs requires it too: that is the **Disclosure Requirements** link in the editor. Recording and consent rules vary by state, so check yours. **5. Choosing a voice without listening.** Under **Voices**, click the **Primary** voice, then the **Voice** row, and search the library. The lesson searches *calm* and clicks play next to **Dana - Calm and Clear** before clicking **Use**. A voice made for promos can sound wrong to someone with water on the floor. **6. A big, slow LLM.** The **LLM** decides what the agent says. A big model thinks longer, and on a phone call the caller hears the pause. LLM use is also charged on top of call minutes. Pick a fast Flash model: the lesson uses **Gemini 3.5 Flash**. The [AI latency](https://learn.ynteractive.com/content/glossary/ai-latency) entry explains the trade-off. ## Which mistakes happen at test time? **7. Testing while it still says Draft.** The **Draft** chip at the top means your changes are not live yet. Click **Publish**, check what changed in **Review Changes**, add a short description if you like, and click **Publish** again. Then click **Preview** and the round phone button to call it in your browser. **8. Going live with no alert.** In the lesson, every call is saved under **Monitor**, then **Conversations**, where **Overview** gives a summary and **Transcription** has the whole call. That is the only place the plumber would find the message. Read the transcript after every test, and don't put the agent on a real line until you have connected a phone number and an alert. The [AI receptionist setup checklist](https://learn.ynteractive.com/content/blog/ai-receptionist-setup-checklist) covers urgent handoffs, and [how to test a voice AI agent](https://learn.ynteractive.com/content/blog/how-to-test-a-voice-ai-agent) gives you a list of tricky test callers. ## Try it free, step by step **Your First Voice Agent in ElevenLabs: An After-Hours Receptionist**. Build an after-hours phone receptionist for a small plumbing company: system prompt, a greeting that says it is AI, a calm voice and a fast model, then test-call it in your browser and read the… You do every step yourself in a practice copy of ElevenLabs Agents, it checks your work as you go, and “Do it for me” finishes any step you get stuck on. Free, and nothing touches your real accounts. [Start the free lesson](https://learn.ynteractive.com/modules/elevenlabs-first-agent) [Or read the full step-by-step guide](https://learn.ynteractive.com/content/elevenlabs-voice-agent-tutorial-after-hours-receptionist) ## Key takeaways - Replace the default prompt with the real job, the hours and the rules. - Write "never guess a price or promise an arrival time" into the prompt. - Say it is an AI and that the call may be recorded, in the first message. - Listen to the voice, and pick a fast LLM. - **Publish** before you test, and read every transcript. - Don't go live until messages reach a person. The [first voice agent FAQ](https://learn.ynteractive.com/content/blog/elevenlabs-first-agent-faq) answers the how-to questions, and the setup is on one printable page in the [cheat sheets library](https://learn.ynteractive.com/content/cheat-sheets). To compare platforms first, see [ElevenLabs vs Vapi vs Retell AI](https://learn.ynteractive.com/content/compare/elevenlabs-vs-vapi-vs-retell-for-voice-agents). ## Frequently asked questions **Why does my agent say "you are a helpful assistant" things?** Because the **System prompt** still has the default. Click inside it, paste the real job, then **Publish** again. **Why are my test changes not showing up?** The agent is probably still on **Draft**. Click **Publish** and confirm in **Review Changes**, then start a new **Preview** call. **My agent pauses before every answer. What can I change?** Check the **LLM**. A big model thinks longer. Open **LLM**, click the model marked **Primary**, and pick a fast Flash model. **Is it enough to read the summary?** No. **Overview** is a good start, but read **Transcription** too, word for word, to check the agent said only what the prompt allows. ## Free lessons in this post - [Your First Voice Agent in ElevenLabs: An After-Hours Receptionist](https://learn.ynteractive.com/content/elevenlabs-voice-agent-tutorial-after-hours-receptionist): Build an after-hours phone receptionist for a small plumbing company: system prompt, a greeting that says it is AI, a calm voice and a fast model, then test-call it in… ## Related terms Plain-English definitions, each with an example from a free lesson. [Voice agent](https://learn.ynteractive.com/content/glossary/voice-agent) · [System prompt (system message)](https://learn.ynteractive.com/content/glossary/system-prompt) · [AI receptionist](https://learn.ynteractive.com/content/glossary/ai-receptionist) · [Deep learning](https://learn.ynteractive.com/content/glossary/deep-learning) · [Model distillation](https://learn.ynteractive.com/content/glossary/model-distillation) · [Turn-taking (voice agents)](https://learn.ynteractive.com/content/glossary/turn-taking) · [AI latency](https://learn.ynteractive.com/content/glossary/ai-latency) · [Conversational AI](https://learn.ynteractive.com/content/glossary/conversational-ai) [The full AI glossary](https://learn.ynteractive.com/content/glossary) ## Related prompts - [AI receptionist script prompt](https://learn.ynteractive.com/content/prompts/ai-receptionist-script-prompt): A copy-ready prompt that drafts an AI receptionist's instructions: greeting, questions, what it must never say and when to hand… [All free prompt templates](https://learn.ynteractive.com/content/prompts) ## Keep reading - [ElevenLabs First Voice Agent FAQ: Prompt, Voice, Preview](https://learn.ynteractive.com/content/blog/elevenlabs-first-agent-faq): Building your first ElevenLabs voice agent? Answers on Blank Agent, the system prompt, first message, picking a voice and LLM, Publish and Preview. - [After-Hours AI Receptionist: 8 Mistakes Offices Make](https://learn.ynteractive.com/content/blog/elevenlabs-after-hours-receptionist-mistakes): After-hours AI receptionist mistakes: no message flow, no urgent flag, tax advice, asking for sensitive numbers, unapproved facts and no alert to the team. - [ElevenLabs Knowledge Base: 8 Mistakes That Cause Bad Answers](https://learn.ynteractive.com/content/blog/elevenlabs-knowledge-base-mistakes): ElevenLabs knowledge base mistakes: an unchecked PDF, no "never guess" rule, missing services, RAG too early, testing only easy questions, stale prices. [All blog posts](https://learn.ynteractive.com/content/blog) · [All free tutorials](https://learn.ynteractive.com/content)