AI agents and workflows · n8n · OpenAI · Gemini · React · Supabase · ManyChat · GoHighLevel

AI agents that find the answer and hand the work on.

I have built agents that read a support question or an Instagram DM, look for the answer in a knowledge base, and pass the work on to a specialist agent or to a person on the team. This page shows each one, what a build costs and how one goes.

What I have built

Three parts of one IT troubleshooting engine, built for one client, and an Instagram agent built to book consults in the DMs.

Instagram AI chat agent

I also built an Instagram agent for an agency that sets up booking agents for med spas. It was made to answer DMs from each spa’s own knowledge base (a Google Doc their team edits) and book consults inside the thread. I built it with ManyChat, 7 n8n workflows, an OpenAI model (gpt-4o-mini), GoHighLevel and Google Calendar. It was a client build, delivered, and the engagement ended in July 2026.

Handing over to people

The Instagram agent had a rule for messages the AI should never answer.

The rule

Medical, refund, legal or “talk to a person” messages were never answered by the AI. It took a callback time and contact, then alerted the team.

Someone unsure about a date got a callback too, flagged for the team.

The person asks for a callback instead of picking a date; the agent asks for a time of day and a way to reach them, then says the team has been flagged.
One of the agent’s test conversations, from the client’s sandbox, so no real customer is shown.

What it costs

You get a written scope and a fixed price for each milestone. You sign off before I build anything, so there are no surprise invoices.

  • AI Agent and Workflow Build

    $600 to $1,800 per build

    Covers

    • AI customer agents that know your knowledge base
    • n8n and Make workflows
    • Internal AI assistants that answer with citations
    • Data pipelines
    • API and CRM integrations
  • Maintenance and Growth

    $200 a month

    Covers

    • Up to 5 hours of updates a month
    • Monitoring and small fixes
    • Priority support
    • A monthly summary

Each build is split into fixed-price milestones. Smaller job? Hourly consults and fixes from $15 an hour.

How a build goes

  1. 01 · Day 1

    Call and audit

    A 30-minute call. I look at your current setup, ask where the hours go, and point out what is worth automating first.

  2. 02 · Days 2 to 3

    Written scope

    Deliverables, timeline and a fixed price per milestone, in writing. You sign off before I start.

  3. 03 · 1 to 3 weeks

    Build

    I work in your tools, so the handoff is clean. You see working pieces every few days, with a weekly check-in.

  4. 04 · Final week

    Handoff

    It runs on your accounts, with full documentation and a recorded walkthrough. Yours to keep.

Questions

How long does a typical build take?

Most builds take 1 to 3 weeks from signed scope to handoff. Full audits and small fixes take 3 to 5 days. AI agent and knowledge base projects take 2 to 4 weeks, depending on their size.

What’s not included in a build?

Your hosting (AWS or GCP), domain costs and third-party API spend such as OpenAI, Apify or Pinecone. They are listed in the scope, and I don’t mark them up.

Can you train my team to maintain the workflows?

Yes. Every build comes with documentation, and I can run paid training sessions so your team can extend and fix the workflows without me.

Tell me what your team keeps answering.

On a 30-minute call I’ll look at your current setup, ask where the hours go, and point out what is worth automating first.