FAQ
Questions, answered plainly
FAQ
Working with Dhii
What does Dhii do?
Dhii is an independent AI engineering studio. We design, build and run agentic automations, AI agents, RAG knowledge assistants, chatbots and voice agents, and we fine-tune, train and self-host models — for teams worldwide.
Do you work with international clients?
Yes. We are based in Mumbai (IST, UTC+5:30) and work remotely with clients in other time zones, with overlap hours agreed at the start of each project. Communication is in English.
How does an engagement start?
With a short call and then usually a one- to two-week Discovery Sprint: we map the workflow, prototype on your real data and give you a fixed, written quote for the build.
Which AI models and tools do you use?
Whatever performs best on your evaluation set at a sensible cost — OpenAI, Anthropic and Google models, or open-weight models such as Llama, Qwen, Mistral and Gemma served with vLLM or Ollama. We are vendor-neutral.
Can the AI run on our own infrastructure?
Yes. We deploy private, self-hosted language models on your servers or cloud account so data never leaves your environment. We run this stack ourselves at chat.dhii.ai.
Who owns the code and models?
You do. All code, prompts, datasets, trained weights and documentation are delivered to you, subject only to the licence terms of any third-party base models.
Do you sign NDAs?
Yes. We are happy to sign a reasonable mutual NDA before you share confidential details.
Can you work with our existing developers or vendors?
Yes. Many projects are co-builds: we design the architecture and deliver the first version, then pair with your team or vendor so they can own it.
What if a model provider changes its prices or models?
We build with a model abstraction and an evaluation set, so switching to another model is a measured configuration change rather than a rewrite.
Do you offer support after launch?
Yes, through a monthly retainer covering monitoring, fixes, improvements and model updates — or a clean handover to your team with a runbook.
Service-specific questions
- What is the difference between agentic AI and normal automation? — Agentic AI Automation
- Which operational tasks are good candidates for AI agents? — AI Agents for Business Operations
- When do I actually need a multi-agent system? — Multi-Agent Systems
- n8n, Make or Zapier — which should we use? — Workflow Automation with n8n, Make & Zapier + AI
- Will the AI send emails on its own? — Email & Inbox Automation with AI
- Is web scraping legal? — Browser Automation & AI Web Scraping
- What is an MCP server? — MCP Servers & AI Tool Integrations
- What is RAG and why not just fine-tune a model on our documents? — RAG & Knowledge Assistants
- Can one chatbot work across website, WhatsApp, Slack and Teams? — Custom AI Chatbots for Web, WhatsApp, Slack & Teams
- How natural do AI voice agents sound today? — AI Voice Agents & Call Automation
- When should we fine-tune instead of using prompts or RAG? — LLM Fine-Tuning (LoRA & QLoRA)
- Why train a custom model when LLMs can do so much? — Custom Model Training (Vision, NLP & Tabular)
Every service page has its own FAQ.
Start a project
Have a workflow that should run itself?
Tell us what you want automated or built. You get a written assessment of feasibility, risks and a fixed quote — usually within two business days.