Case Study 02

Ask Diogo

A voice agent that knows my experience and interests, and can hold a Product Management conversation on my behalf.

Voice AI Agent // 2026 · askdiogo.com ↗

The What

Ask Diogo is a speech-only voice agent you can call from the browser to talk about Product Management with an AI version of me. It knows my career, the products I've worked on and what I care about, and answers the way I would, in short spoken replies.

Under the hood it's a chained real-time pipeline: speech-to-text, an LLM grounded in my approved career material, and text-to-speech, orchestrated by LiveKit. The agent runs as a container on a small VPS and connects out to LiveKit Cloud, while a Next.js app on Vercel handles the call page, email sign-in and call limits (free calls last 2:30, signed-in visitors get longer).

I treated it like a product, not a demo: behavioral evals judged by an LLM (hallucinations, false premises, follow-ups, prompt injection, AI disclosure), latency measured on every turn, and a deploy script that refuses to ship if the knowledge base is out of date.

Tools: Claude Code, LiveKit, Vercel

The Why

"The future is agents acting on our behalf across many areas of life."

I have been interviewing for Product Management positions, and AI is now a regular part of the process on both sides, candidate and recruiter: automated CV screening, interview transcript analysis, adapting a CV to each role description, even interviews with an AI recruiter.

So I decided to build a voice agent that knows about my experience and interests, and can talk like me. If recruiters are going to use agents, candidates can too.

TECH STACK

graphic_eq

Real-time Voice

LiveKit Agents (Python) on LiveKit Cloud

hearing

Speech to Text

AssemblyAI Universal-3.5 Pro + turn detector and Silero VAD

neurology

LLM

OpenAI GPT-6 Luna with my full career material in the system prompt

record_voice_over

Text to Speech

ElevenLabs v4 Turbo voice

web

Web App

Next.js on Vercel with Better Auth, BotID and Resend sign-in

dns

Hosting

Agent worker in Docker on a Hetzner VPS, no open ports

fact_check

Quality

LLM-judged behavioral evals and per-turn latency logging

Key
Learnings

01

Full context beats retrieval for a small corpus

Swapping per-turn keyword retrieval for my whole career material (~10k tokens) in the prompt took evals from 20/27 to 27/27. Follow-ups like "What was the outcome?" stopped being refused, for about +20 ms of time to first token thanks to prompt caching.

02

Latency is the product in voice

Every turn logs transcription delay, end-of-turn and model timings. Preemptive generation lets the LLM start while the turn detector is still deciding, so answers feel conversational instead of walkie-talkie.

03

Guardrails that don't kill the conversation

A small deterministic guard handles prompt injection and private data. Everything else, including small talk, is left to the model, which is grounded in approved material and always discloses it is an AI.

04

Evals as the approval step

Career material lives in Markdown, compiled into one corpus. The git diff is the review, and LLM-judged scenarios check it never invents numbers, corrects false premises and doesn't present general PM advice as lived experience.

See it live

Visit Project