Insights
Deep dives into voice AI technology, industry trends, and the future of conversational interfaces.
Thirty Seconds, One Attempt: Tool Calls to Business Systems
A tool call is not a background job. It is an HTTP request with a deadline, a single attempt and a human listening to silence. Why retries are wrong on a live call, which lookups may block, and what the agent says while it waits.
Jesper RietbergenAug 14, 202611 min read
Knowing Who Is Calling Before They Say So
Caller recognition fails silently, because the number arriving in E.164 does not match the six ways a human typed it into your CRM. Number normalisation, the search rate limit nobody plans for, and the line between recognised and watched.
Jesper RietbergenAug 14, 202610 min read
The Latency Budget of a Phone Call
Every platform quotes one latency number. A caller experiences a chain of eight stages, only two of which are the model. Where the milliseconds actually go, which ones are physics, and why turn detection usually costs more than time to first token.
Jesper RietbergenAug 6, 20269 min read
Barge-in That Actually Works: Tuning VAD for Phone Audio
Voice activity detection settings tuned on clean studio audio fall apart on an 8 kHz phone line. The two jobs one detector is asked to do, the false barge-in and how to recover from it, and why we moved turn detection back out of the cloud.
Jesper RietbergenAug 6, 202610 min read
EU AI Act Article 50: What Voice Agents Must Disclose
From 2 August 2026 a caller must know they are talking to a machine. What Article 50 actually requires of a phone agent, who carries the obligation, and why proving it is a job for the orchestration layer.
Jesper RietbergenJul 30, 202611 min read
What a Voice AI Agent Really Costs Per Minute
Platform fees are the small half of the bill. A component-by-component breakdown of what a minute of AI phone conversation costs, where the hidden multipliers sit, and how to model it before you commit.
Jesper RietbergenJul 30, 202612 min read
When the Transfer Fails: Handing a Call to a Human
Every voice agent demo transfers to a human on the first try. Production is not a demo. The failure modes of a warm transfer, why silent fallbacks are worse than a refusal, and what to build instead.
Jesper RietbergenJul 30, 202610 min read
Why Voice Agent Calls Fail: Reading the SIP Logs
A dashboard that says 'error' tells you nothing. The four layers a phone call fails at, the SIP response codes and Q.850 causes that name the cause, and a triage order that converges instead of guessing.
Jesper RietbergenJul 30, 202613 min read
Self-Hosted Voice AI: Who Holds the Pager?
Self-hosting a voice stack to escape per-minute pricing is a real strategy with a real bill attached, and the bill is mostly operational. What you take on the day you own the pager, and the three honest ways out.
Jesper RietbergenJul 30, 202612 min read
Gemini Live 3.1 Prompting Guide (Voice Agents)
You can't prompt Gemini 3.1 Flash Live like a text LLM or a TTS engine. A practical prompting guide for native-audio voice agents: instruction design, tone, language, and what quietly fails.
Jesper RietbergenJul 20, 20269 min read
Why Voice AI Needs European Infrastructure
Data sovereignty, latency, and compliance - exploring why European businesses need voice AI infrastructure that stays in Europe.