Huntay.

AI Agents & Automation

Customer support, sales and operations agents that work 24/7—connected to your own data.

I design and build production-grade AI agents: assistants that answer customers on WhatsApp and your website, qualify and follow up leads, search your documents and ERP data, and automate repetitive back-office work. They are built on RAG, LangChain/LangGraph and Dialogflow CX, and integrated with the tools you already use.

Who it's for

  • Teams answering the same customer questions every day
  • Sales teams losing leads because follow-up is slow
  • Companies whose knowledge is scattered across documents, emails and ERP
  • SMEs that want AI results without hiring an AI team

What you get

  • Use-case analysis and ROI-driven prioritization
  • A working AI agent connected to your data (RAG) and tools
  • Channels: WhatsApp, website chat, Chatwoot or your CRM
  • Human handover, guardrails and conversation analytics
  • Deployment, monitoring and continuous improvement

Typical projects

WhatsApp customer support agent that resolves common requests and hands complex ones to your team
Sales agent that answers product questions, qualifies leads and books meetings
Internal assistant that answers staff questions from manuals, policies and technical docs
Operations agent that reads ERP data, prepares reports and flags anomalies

Technologies

  • LangChain
  • LangGraph
  • RAG
  • Vector databases
  • Dialogflow CX
  • Chatwoot
  • WhatsApp Business API
  • Python
  • GCP

How we work

A simple, transparent process from first call to production.

  1. 01

    Intro call

    We talk about your goals, constraints and timeline. You get an honest first assessment.

  2. 02

    Discovery & proposal

    I analyse the problem, your existing systems and the options, then send a clear scope, roadmap and proposal.

  3. 03

    Build in short iterations

    Work happens in short sprints with regular demos, so you see progress early and can steer.

  4. 04

    Launch & handover

    Production rollout with monitoring, documentation and knowledge transfer to your team.

  5. 05

    Grow

    Optional ongoing support, optimization and advisory as your product and team grow.

Frequently asked questions

What does an AI agent need to work well?

Clear use cases and access to the right knowledge: documents, FAQs, product data or ERP records. I start by mapping these sources, then build retrieval (RAG) so answers are grounded in your own data instead of the model's guesses.

Will an AI agent replace my support team?

No. It handles repetitive questions and routes complex or sensitive cases to people with full context. In a previous project, this approach made ticket resolution about 80% faster.

Let's talk about your project

Book a 30-minute intro call. You'll get honest first recommendations and a clear next step.