See it work

How we build the machines.

Technical write-ups from building WildRun's voice agents and automation stack — Vapi architecture, Cloudflare Workers, latency work, eval frameworks, prompt security, and search plumbing. Written for engineers; the main blog is for the business owners the machines answer for.

kvCORE Webhooks Integration: Connect Calls to Your CRM

Set up kvCORE webhooks integration correctly: skip the Zapier polling delay, connect your AI voice agent, and write call data back automatically.

2026-08-01 · 7 min

Build a Dental AI Receptionist: A Vapi Developer Guide

Learn how to build a dental AI receptionist with Vapi, ElevenLabs, and Cloudflare Workers, including real PMS integration code and production gotchas.

2026-07-06 · 11 min

Cloudflare Workers AI Voice Agents: A Builder's Guide

Learn how to wire Cloudflare Workers AI voice agent LLMs into a real-time pipeline, with streaming, tool calls, and cost math for production use.

2026-07-06 · 11 min

Voice AI Security: Preventing Prompt Injection Attacks

Learn how to defend your voice AI agent against prompt injection, tool-call hijacking, and CRM data poisoning with TypeScript defense patterns.

2026-07-02 · 12 min

How to Test AI Voice Agents: An Evaluation Framework

A practitioner's guide to testing AI voice agents — latency measurement, LLM judging, simulated callers, and CI regression, with runnable TypeScript.

2026-06-28 · 12 min

Vapi Function Calling: Complete Guide for Developers

Learn how Vapi function calling works — custom tools, Code Tools, webhook contracts, and TypeScript patterns for production voice AI agents.

2026-06-27 · 14 min

Best LLM for Voice Agents in 2026: A Developer's Comparison

Compare GPT-4.1, Claude Sonnet 4.6, Gemini 2.5 Flash, and Groq for voice AI. Real TTFT data, function-calling grades, and TypeScript you can deploy today.

2026-06-26 · 12 min

Voice AI Latency Optimization: Achieve Sub-500ms Responses

Learn how to cut voice AI latency below 500ms: streaming pipelines, turn detection tuning, and the right STT/LLM/TTS model choices for production agents.

2026-06-25 · 9 min

ElevenLabs TTS Integration for Voice Agents (2026)

Build a production ElevenLabs TTS integration for voice agents in TypeScript — streaming, WebSocket pipelines, latency tuning, and deployment gotchas.

2026-06-22 · 12 min

Deploy Vapi Agents on Cloudflare Workers: Setup Guide

Set up Vapi Cloudflare Workers webhook handlers in TypeScript. Step-by-step guide covering assistant routing, function calling, secrets, and production gotchas.

2026-06-21 · 11 min

Prompt Engineering for Voice AI Agents: Complete Guide

Practical prompt engineering for voice AI agents: control response latency, prevent hallucinations, handle interruptions, and wire tool calls in Vapi.

2026-06-19 · 12 min

Vapi Webhook Architecture: A Builder's Complete Guide

Master Vapi webhook architecture: configure server URLs, handle all event types, write production TypeScript handlers, and avoid the pitfalls.

2026-06-18 · 12 min

How to Build an AI Voice Agent with Vapi in TypeScript

Learn how to build an AI voice agent with Vapi in TypeScript. Step-by-step: assistant setup, webhook handlers, tool calls, and production latency tips.

2026-06-01 · 12 min

What Is Natural Language Understanding in AI Phone Agents?

Learn how natural language understanding powers AI phone agents, what separates good NLU from poor, and when it actually works for small business calls.

2026-05-28 · 7 min