Browse categories
Explore
Fiverr Pro
English
$
USD
I will build a custom ai agent with rag, langchain or n8n
Adam M
About this gig
Need an AI agent that does one real job for your business, not just chat?
I build AI agents in Python with LangChain, LangGraph or n8n. The agent can search your documents (RAG), call the tools or APIs you approve, and return an answer or an action you can check.
New here? Start small. The Basic package is a scoped starter: one agent, one task, one read-only tool, delivered in 3 days. It is a low-risk way to see how I work before a bigger build.
What you can get:
- One focused agent (Basic) or a multi-tool workflow agent (Standard, Premium)
- RAG over your PDFs, docs or FAQs so answers come from your data
- Tool calls such as search, a REST API, a spreadsheet or a database read
- Step logs so you can see which tool was used and why
- Human approval before any write action (Premium)
- Clean source code and a README you can run yourself
How it works:
1. You describe the task and send example inputs
2. We agree on the tools and what the agent must never do alone
3. I build, test on your examples and deliver
Message me before ordering if you are unsure which package fits.
Get to know Adam M
Adam M
AI Engineer, RAG, ML and Agents
- FromMorocco
- Member sinceSep 2025
- Avg. response time1 hour
Languages
English, French, Arabic
I build production AI systems: RAG chatbots grounded in your docs, custom ML and deep learning models, generative AI apps, and tool-using agents. Python, LangChain, LlamaIndex, PyTorch, FastAPI. You get source code, evaluation, and a handoff - not a wrapped chatbot template. I will tell you if RAG, a model, or an agent is the wrong tool. Based in Morocco. English and French.
FAQ
What can the $35 Basic agent do?
One clearly defined task with one read-only tool, for example answering questions from one document set or looking up data from one API. It comes with a simple chat or API endpoint and a README. Bigger workflows belong in Standard or Premium.
Do you use LangChain, LangGraph or n8n?
All three, depending on the job. n8n suits no-code friendly workflows you want to edit yourself. LangChain or LangGraph in Python suit custom logic. Tell me your preference, or I will suggest one before we start.
Which AI model do you use and who pays for it?
Usually OpenAI or Anthropic models, or a local model if your data must stay private. API usage is billed to your own account, so you keep control of keys and costs. I can work with placeholder keys and you plug in yours.
Can the agent send emails or change data?
Only if we agree on it, and only with a human approval step before the action runs. Basic and Standard are read-only by default. I will not connect live write access without that safety step.
What do I need to send to start?
A short description of the task, example inputs and expected results, any documents the agent should use, and API docs or test access for the tools. If an API is not ready yet, I can use a mock and you swap it later.
