Insights

Leçons d'IA en production.

Notes terrain sur les agents vocaux, RAG, systèmes autonomes, et les arbitrages qui comptent quand l'IA rencontre la production.

IA vocale·22 avr. 2026

ElevenLabs vs Vapi vs Retell — Voice AI Platform Comparison 2026

Side-by-side comparison of the three leading voice AI platforms in 2026 — latency, languages, pricing, integrations, and what we ship in production at Ikki.

9 min de lecture

RAG·8 avr. 2026

RAG Implementation Guide for SMBs (2026)

How to ship a Retrieval-Augmented Generation system that actually works for SMBs — chunking, embeddings, evaluation, and the mistakes that cost us six weeks.

12 min de lecture

IA vocale·25 mars 2026

Voice AI Agent Cost: How Much Does It Really Cost in 2026?

Real-world numbers from voice AI projects we shipped: build cost, monthly run cost, hidden expenses, and how to avoid common pricing traps.

8 min de lecture

Leçons·12 mars 2026

Lessons from Shipping Seven AI Products

What we learned shipping voice agents, RAG platforms, fintech engines, civic AI, and immersive web — the patterns that worked, the ones that didn't, and the things nobody told us.

11 min de lecture

IA vocale·26 févr. 2026

Building Maideo: Voice AI Recruiting for Home Services

How we shipped a voice agent that pre-qualifies care workers — architecture, pitfalls, the prompt that finally worked, and the production numbers.

10 min de lecture

Plateformes·12 févr. 2026

Why We Chose Nuxt 4 for AI Products in 2026

After shipping seven AI products, here's the architecture we converged on — Nuxt 4 + Fastify + MongoDB — and why it beats Next.js, Astro, and SvelteKit for our use case.

9 min de lecture

SHIP LOG

SHIP-0247·CODEMACHIA·v1.4.2—DEPLOYED 2026-05-04 01:29 UTC