We are the largest active AAA agency in Turkey. We are a team of 6 people. We acquired +150 new clients in 2 days and we are looking for the last 1 teammate because we cannot handle the demand. I have to say this from the very beginning: This is not something you think you can experience. If you are not good with the following tools, I have to turn you away without offense. Please don't read on if you are not confident, not cooked and not hungry to get rich. Because we need to work fast and at a fast pace. We need to complete and send the system in a few hours. Read below and if you think you can go for it, just comment down below or DM me from Instagram (@noborabekar) --- We’re hiring an AI Systems Builder — someone who combines no-code mastery, AI architecture sense, and a get-shit-done attitude to create automation and intelligence across the company. You’ll build systems that help our teams think faster, act smarter, and remove operational bottlenecks — not just automate workflows, but rethink them entirely. 🚧 What You’ll Actually Do Design and build AI agents and workflows that replace internal operations Use tools like n8n, Airtable, Webhooks, LangChain-style logic, GPTs, VAPI, and vector DBs Identify internal bottlenecks (e.g. reporting, manual decision points, ops chaos) and build intelligent systems around them Set up automated reporting, Slack agents, async assistants, and internal tools Integrate multiple tools — WhatsApp, Stripe, Slack, Webflow, Notion, Meta Ads, Looker Studio, Typeform, etc. Own everything from idea to delivery — you spot problems, propose systems, and ship them Continuously test and evolve AI workflows as models and tools advance 🧠 What You Bring Proven experience building AI-based internal systems, not just prompting Familiarity with LLM architecture, agents, memory, API chaining, tool calling, etc. Hands-on skills with no-code tools: n8n, VAPI, Airtable, etc. You’re comfortable debugging APIs, testing webhooks, using developer docs

Complex agents can increase costs due to long prompts. So here I will briefly explain how you can do fine-tuning in the simplest way possible. This will allow you to reduce costs and increase the intelligence of your voice agent threefold. (If you need any help, just mention me in the comments and I'll try to help you) 1- Prepare your detailed prompt. 2- Send it to Gemini and ask it to optimise this document for fine-tuning. Request that it optimise for maximum agent intelligence performance using metadata, detailed triggers, if conditions, and structural adjustments. 3- Export the document in any format. txt, rtf, etc. 4- Go to Cursor (you need to download it to your computer) and upload the document to the left panel. In the chat section, mention the document using ‘@’ and ask it to generate the document in jsonl format. Specify that no changes should be made to the main content. 5- Save the JSONL output to your desktop and go to this link: https://platform.openai.com/finetune/ftjob-sdyqx7k3DmRpf0pQa85PYOKg 6- Upload the jsonl document to the field that appears on the screen. Set a fixed seed, such as ‘53’. Enter your name in the suffix field for the model. It can be anything. Select GPT 4.1 as the base model. 7- In the Configure hyperparameters section, open ‘Number of epochs’ and set it to 3. Then press the Create button. 8- Once the process is complete, go to Postman from the web. 9- Enter the following formats and click the Send button. POST: https://api.vapi.ai/assistant Headers: Key: Authorization Value: Bearer [YOUR_VAPI_PRIVATE_KEY] Body: { "name": "[YOUR_NEW_VAPI_AGENT_NAME]", "model": { "provider": "custom-llm", "url": "https://api.openai.com/v1/chat/completions", "model": "[YOUR_FINETUNED_MODEL_NAME_THAT_YOU_ENTERED_TO_SUFFIX_SECTION]", "messages": [ { "role": "system", "content": "[YOUR_VAPI_SYSTEM_PROMPT_SHORT_VERSION]"

how can i get to level two?

If even one beginner can learn something from this, then my message will have been conveyed. If you're a beginner, for the love of God... stop watching lessons. I'm saying that I made this mistake and wasted MONTHS of my life. I thought, “This is a skill game, so the more I watch people who know what they're doing, the more I'll learn.” Most of us make this mistake of course BUT... Watching a lesson to grasp the basics is certainly good. But thinking you can learn by sitting back while eating Doritos is unrealistic. When you learn something from a video, put it into practice IMMEDIATELY. But most of the time, it's better to learn the job yourself. Just jump in, connect the nodes, surf the n8n, write a prompt. IT'LL BE SUCK ANYWAY IF IT'S YOUR FIRST TIME Doesn't matter if you've watched 6823 videos about the topic or not even 1. That’s the only recipe. You can’t learn, without getting your hands dirty. And anything extra you do besides that is just a waste of time. So get out and do something. Make some mistakes.