AI & Automation

Applied AI that connects to your actual systems: realtime voice agents, Model Context Protocol servers exposing internal tooling to assistants, and LLM pipelines with the retrieval, guardrails and evaluation needed to run in production.

PythonTypeScriptMCPLiveKitGeminiClaudeSupabase

What this covers

Realtime voice agents (LiveKit / streaming)
Model Context Protocol (MCP) server development
LLM integration with internal APIs and data
Retrieval pipelines and structured extraction
Workflow and reporting automation
Evaluation, guardrails and cost control

What you get

Connected: Agents that call your systems, not just chat.
Measured: Evals and logging so quality is observable.
Practical: Automation aimed at a real bottleneck.

Related work

2026

Realtime Voice Banking Assistant

A low-latency voice agent that handles banking enquiries over a live audio session and executes real account operations.

Case study

2026

AdSense MCP Server

An open-source Model Context Protocol server that lets Claude, Cursor and other AI assistants query a Google AdSense account.

Case study

Have something that needs building?

Tell us what you are working on. If it is a fit we will come back with scope, timeline and cost. If it is not, we will say so and point you somewhere better.

Start a conversation accronnik@gmail.com