Overview
Connections
News
Salaries
Products
People
Growth
Offices
Financials

Overview

Scott Spence is a UK-based product engineer building production AI systems, coding-agent infrastructure, MCP tools, and SvelteKit products.

News

News Scott Spence 3 months ago
Agentic engineering: a practical guide to reliable coding agents
Agentic engineering is the practice of putting coding agents inside an engineering system that makes context, scope, validation, evidence and human review...
Read more
Report
Blog 4 months ago
How I work with LLMs
In November 2025 I wrote the honest version of working with Claude Code. At the time, most of my process involved spotting when Claude was drifting, calling out the bullshit, checking that it understood the task, and restarting the session when the...
Read more
Report
Blog 4 months ago
Coding agent harnesses with my-pi
I have a habit of turning repeated arguments with coding agents into software. If I tell an agent to stay inside five files often enough, eventually I stop asking nicely and build something that blocks the sixth. If I keep asking for validation...
Read more
Report
News Scott Spence 5 months ago
How I Stop LLMs Drifting In Production Codebases
The problem I care about with LLM coding is drift: one plausible shortcut gets copied, then future sessions start treating it as how the app works. I've...
Read more
Report
Blog 6 months ago
Building a SQLite context sidecar for my-pi
Right, so, this started with me looking at , seeing a 98% context reduction claim, and immediately thinking: bull shite. Not because the idea is bad. The idea is good. The bit that made me twitch was the shape of the claim. If you compare a huge...
Read more
Report
Blog 7 months ago
Building my-pi: my own Claude Code alternative with Pi
I have written a few posts now about bits of : adding LSP, adding telemetry, and hardening redaction with evals. What I have not actually done is the obvious one: explain what is, why I made it, and why I have suddenly spent a slightly...
Read more
Report
Blog 7 months ago
Hardening redaction in my-pi with evals and telemetry
Third post in a little run about , my coding agent harness built on top of pi-coding-agent. There's a pile of stuff in I have not written about, but these three felt worth the time: adding LSP, wiring in local SQLite telemetry, and this one, which...
Read more
Report
Blog 7 months ago
Add telemetry to my-pi
keeps growing in the direction of whatever annoyed me most that week. It is the coding agent harness I've been building on top of the excellent pi-coding-agent from badlogic, and I keep bolting things onto it as I need them for real work. Last time...
Read more
Report
Blog 7 months ago
Add LSP to my-pi
This whole thing started with a chat with Kev, (Svelte Society co-founder), after a few beers at the CityJS after-party. I mentioned my-pi to him and his first question to me was "oh! does it have LSP built in?" I was...
Read more
Report
Blog 7 months ago
nopeek - Keep Your Secrets Out of Claude Code
So, here's the situation. I use Claude Code with cloud CLIs daily, AWS, Hetzner, that sort of thing. Claude Code is genuinely the ultimate cheat code for bash though! Need to query an API, parse some JSON, chain a few commands together? Claude does...
Read more
Report
Show more news