Articles
Writing about platform automation, edge infrastructure, applied security, and AI-assisted engineering.
Reviews of books and papers are filed here too, and collected under Reviews. The full reading log of what I am reading, what is next, and what I have read lives on its own page.
2026
-
articleEvaluation Closes the Loop
A trace shows what an agent did, not whether it was right. This part scores the agent against known cases and fails the build when a passing case breaks.
14 min read · 10 chapters
-
articleThe Behavioural Turn in Software Engineering
Moving from assembly to C changed what we read. Coding agents change whether we read. What psychology learned about black boxes, and what it got wrong.
32 min read · 11 chapters
-
articleThree Parts and No BrainEN中한
What a chess program is made of, and how far a hand-written one gets against the computer opponent on lichess, before any learning starts.
16 min read · 8 chapters
-
articleIT Intelligence: The Missing Data Layer of Enterprise ITEN中한
Business intelligence tells a company how it sells. Nothing tells it how its IT fits together. Why I started building an Enterprise Context Platform.
50 min read · 21 chapters
-
articleThe Original Data CompanyEN中한
Insurers say they are not tech companies. Yet an insurer sells a prediction wrapped in a promise, and has since a 1693 life table: the original data company.
27 min read · 14 chapters
-
articleThe River and the CanalEN中한
Agents explore the rugged world; workflows are what exploration leaves behind. Chess, StarCraft, a factory under the sea, and why I build an engine.
51 min read · 16 chapters
-
articleShiioo, Re-imagined, and the Home AI Lab It Runs On
How I re-imagined Shiioo with what 2026 taught me about agent systems, and why my local setup moves to a Mac Studio and DGX Sparks.
25 min read · 10 chapters
-
reviewWin Everything, Control No OneEN中한
Sebastian Mallaby's biography of Demis Hassabis is the best history of modern AI I know, and an honest study of a man who hates control and exercises it.
17 min read · 10 chapters
-
articleAfter PHP Gate: A Blueprint for the Static Web
Last week's PHP flaws reached every PHP installation serving web requests. My blueprint for sites and apps that run no code per request at all.
27 min read · 10 chapters
-
articleLearning to PlayEN中한
A chess prodigy's handbook, three old games and one laptop: rebuilding the ideas behind game-playing AI in Rust for a browser on my phone, and measuring them.
22 min read · 9 chapters
-
reviewThe Web Was the Training Set
Tim Berners-Lee's memoir is the story of a British engineer at a Franco-Swiss lab giving a protocol away. Read in 2026, it is also the origin story of AI's data supply.
16 min read · 8 chapters
-
articleObservability Is Not Logging
A cost total says nothing about how a run went. This part turns each agent run into a trace: which turn escalated, which tool failed, where the money went.
15 min read · 9 chapters
-
articleThis Site Is Becoming a Map
A blog shows what I wrote last. The new map on raskell.io shows what I keep coming back to, and it is the start of a public second brain.
9 min read · 6 chapters
-
articleThe Bill Is Part of the Loop
Every model response already carries its own bill in the usage field, and the loop throws it away. This post reads that field, prices it against a table, and turns cost into a value the loop can see per turn and act on: a metering decorator that needs no loop change, a running ledger, prompt-cache accounting that moves the number the most, and a budget that degrades before it stops. Part eight of The Agent Platform Handbook.
10 min read · 9 chapters
-
articleThe Model Is a Dependency
Every layer of the harness has existed to put the right tokens in front of one hardcoded model string. This post pulls that string out and makes the model a dependency: why you route a cheap model for easy turns and a strong one for hard turns, what a fallback looks like when a provider is down, and why 'models are commodities' is a claim about your architecture before it is a claim about the market. Part seven of The Agent Platform Handbook.
14 min read · 8 chapters
-
articleThe Bottleneck Is Data, and Europe Is Sitting on It
Frontier AI is running short on public text, not compute. Europe's edge is the high-quality data it never put online. Capturing it needs coordination.
34 min read · 8 chapters
-
articleBrain Emulation, Read as an Infrastructure Problem
An MIT thesis argues brain emulation has crossed into engineering. Read as infrastructure, the numbers describe a workload your AI cluster was not built for.
12 min read · 7 chapters
-
articleMemory Is a Write Path
Retrieval reads context the project authored. Memory is the agent writing context for its own future sessions, and the write is the part that is dangerous. Why session memory comes free from the transcript, why cross-session memory needs a separate write surface, and how to let an agent remember without letting it corrupt its own ground truth. Part six of The Agent Platform Handbook.
19 min read · 14 chapters
-
articleThe Proof You Only Have to Write Once
Generation is cheap, so verification is the bottleneck — and we throw the verification away every time. What if a proof, once written, could be named, shared, and vouched for? A content-addressed commons for verified Haskell, and the move I left for after the semantic-artifact trilogy.
13 min read · 7 chapters
-
articleRetrieval Is a Tool, Not a Layer
Loading the whole .AGENTS/ directory on every turn does not scale. The fix is not a retrieval layer bolted to the side of the agent. It is a search tool in the registry the agent already has. BM25 over project docs, no vector store, and an honest account of when embeddings start to earn their keep. Part five of The Agent Platform Handbook.
16 min read · 11 chapters
-
articleContext Is the Product
Models are commodities. Context is not. The sources of context an agent draws on, why retrieval alone is not enough, and a minimal .AGENTS/ convention that loads context from disk into the same harness we have been building. Part four of The Agent Platform Handbook.
26 min read · 15 chapters
-
articleTools: How Agents Actually Do Things
Function calling is the API between language and action, but the engineering is in the registry. A working four-tool registry in TypeScript on Bun, schema design that survives model drift, parallel tool calls, and the failure modes nobody mentions in the demo. Part three of The Agent Platform Handbook.
13 min read · 10 chapters
-
articleYour Agent Wants Root
An agent with a shell tool is arbitrary code execution with a friendly face. A short tour of why Docker alone is not enough, what Firecracker, gVisor, and Kata actually solve, and a hardened sandbox you can wrap the post-one agent in today. Part two of The Agent Platform Handbook.
16 min read · 9 chapters
-
articleWhat an Agent Actually IsEN中한
AI agent is the most overloaded word in the industry. This is the anatomy, the lineage, and a working implementation in roughly two hundred lines of TypeScript on Bun. Part one of The Agent Platform Handbook.
19 min read · 8 chapters
-
articleThe Field Exists Now
Alasdair Allan's agentlanguages.dev catalogue turns AI-oriented programming languages from a loose set of experiments into a field with camps, disagreements, and testable claims.
7 min read · 6 chapters
-
articleSource Code Is the New Assembly
Closing the trilogy. The artifact you author is no longer source code. It is a typed, verifiable object that carries meaning. Code becomes a lowering target.
27 min read · 15 chapters
-
articlePatents Per Capita Is a Vanity Metric
Switzerland tops the Global Innovation Index for the fifteenth year running. As an engineer, that should make you suspicious of the metric, not proud of the country.
23 min read · 6 chapters
-
articleTraffic Replay as a Security Primitive
WAF tuning is a guessing game because you cannot reproduce the traffic that triggered the rule. Deterministic replay changes that.
12 min read · 8 chapters
-
articleThe Economics of InferenceEN中한
Inference tokens are not API calls. They are a metered resource that is consumed, generates value, and correlates with power draw. The economics of the post-AI world look less like software and more like water, electricity, and gas.
12 min read · 6 chapters
-
articleWhat Comes After the Last Programming Language
If AI generates machine code directly, why are we still running operating systems designed for humans? The answer might be an inference-native OS.
23 min read · 9 chapters
-
articleWhat Sixteen AI Agents Taught Me About Management
What happens when you give sixteen AI agents an org chart, a reporting structure, and a token budget. A story about orchestration, management, and running out of runway.
19 min read · 11 chapters
-
articleWhy We Built a Haskell Package Manager in Rust
hx is a fast, opinionated Haskell toolchain built in Rust, following the playbook astral.sh used to modernize Python.
19 min read · 8 chapters
-
articleThe Last Programming Language Might Not Be for HumansEN中한
Three futures for programming languages as AI becomes the primary author of code, and why I bet on Haskell.
26 min read · 5 chapters
-
articleNotes from RSAC 2026
Third time at RSA Conference, first time as a speaker. What I saw, what I heard, and what I am still processing.
23 min read · 11 chapters
-
articleWhat Zentinel Is Really Optimizing For
Every major proxy was a product of its time. Zentinel is built for this one: safety, operability, and the operator's ability to sleep.
18 min read · 8 chapters
-
articleHow I Work These Days
From Kaggle in 2020 to coding agents in late 2025. The shift that changed how I build and why my routine finally feels right.
10 min read · 9 chapters
-
articleArchipelag.io Is in Open Beta: Here's Why I Built It
From watching Ethereum miners in 2016 to building a decentralized compute network in open beta. Architecture, conviction, and the long road.
23 min read · 11 chapters
-
articleHow AI Makes Bare Metal Viable Again
I migrated two production apps from Kubernetes to a single Hetzner box. The missing piece was not the hardware.
29 min read · 14 chapters
-
articleEdge Systems Are the New Backend
Auth, policy, and business logic are migrating to the edge. The traditional backend is becoming a persistence layer.
30 min read · 9 chapters
2025
-
articleLooking back on 2025
On reading Tim Berners-Lee in Okinawa, and why AI might accidentally save the web from itself.
7 min read · 1 chapters
-
articleMise ate my Makefile
Mise replaced Make, asdf, and a pile of shell scripts with a single TOML file per project. Here is why it stuck.
12 min read · 10 chapters
2024
-
articleDisk space maintenance on Void Linux
Cleaning old kernels, pruning xbps package cache, and reclaiming disk space on Void Linux without breaking your system.
4 min read · 5 chapters
2023
-
articleAll beginning is Haskell
How Haskell shaped the way I think about building systems, and why I am still building Haskell tooling years after writing my first monad.
10 min read · 7 chapters
-
articleMy OpenBSD journey: Getting it virtualized with libvirt (1)
A step-by-step guide to running OpenBSD in a libvirt virtual machine on Void Linux, without needing VirtualBox or VMWare. Part 1 of my OpenBSD journey.
10 min read · 3 chapters
2022
-
articleHello and outlook
The first post on raskell.io. What this site is for and what I planned to write about.
1 min read · 3 chapters
