I build AI tools for support teams, after a decade of answering the tickets myself.
I’m Javier, AI Solutions Lead at Help Scout, in Amsterdam.
The main work
What I spend most of my time on: three tools, built and maintained by me.
Compass, the copilot
2026Claude in the Help Scout sidebar, with permission to call the APIs it needs: the knowledge base, past tickets, customer history, saved replies. It assembles the ten minutes of context a reply usually starts with, and drafts the reply when asked.
Watching AI Answers actually answer
2026A daily check on whether Help Scout’s AI Answers actually answered. Reads every thread, tags the customer’s real signal, sends samples to Claude for scoring. A 1,100-conversation analysis split “Contact helped” into three honest buckets and fed the team’s improvement queue.
Help Scout, in plain English
2026A hosted MCP server that connects Claude, ChatGPT, and Cursor to a Help Scout workspace. Around fifty tools across the full API: conversations, replies, tags, the knowledge base, reports. I built it, and I maintain it.
Over a decade of this now: Geckoboard from 2014 to 2018, Help Scout since. For most of it the job was the conversations themselves: email deliverability, security questionnaires, our public APIs, the cases that don’t get solved by poking at the UI. These days I spend most of my time building, and take only the trickier conversations. Mostly pattern recognition; the best of them a quiet unpicking of something I haven’t seen before.
The building started in the summer of 2025, and the last six months have been the steep part of the curve. Compass, our sidebar copilot, is the most visible piece: it assembles the ten minutes of context a reply usually starts with, then drafts the reply when asked. There’s a hosted MCP server too, a bridge that lets agents like Claude, Cursor, and ChatGPT work directly against a Help Scout workspace; it fell out of an AI evaluator I was building, and I’ve used it on every AI project since. Smaller internal scripts fill in around them.
It adds up to applied AI engineering.
The through-line is that I like getting to the bottom of things. I’m not a developer by training, so a lot of building Compass and the MCP server meant picking up things I’d never touched before (HMAC signatures, JWT validation, prompt-injection hardening) and shipping them anyway. I learn fastest with something real on the line.
Outside of work I spend a lot of time making music. Mostly dark ambient: drones and pads, the kind of sound that rewards careful listening more than clever playing. Reading is the steadiest habit alongside it: AI papers and the inbox during the day, something slower in the evenings.
Drop a line
Write if you work on applied AI, support engineering, or anything in the unglamorous corners of email. I reply within a day or two, sometimes faster if it’s a deliverability puzzle.
Or find me on LinkedIn ↗ · GitHub ↗