Varjosoft — AI that earns its place.

Builders know the shape of this failure.

The agent wrote the patch. You read the diff, the tests passed, you merged. Two weeks later there is a bug, and when you step into that code you realize you do not quite know why it was written that way. The code is yours, but the mental model is not. You never built it. The friction that used to force you to understand what you were shipping was traded away for speed.

That gap is the drift. It is small each time and cumulative across a year. At the end you have a system you own, a codebase you wrote, and a model of it shaped more by your agent than by you.

Every profession gets its version. Writers drift through AI-generated summaries. Analysts drift through dashboards they did not build. Students drift through essays that sound like them but are not. The drift is not laziness. It is what happens when every tool in your hand is optimizing to answer you faster than you can frame the question.

The industry has been building eager AI for three years. Every model, every agent, every framework shipped under the same virtue: never make the human wait. The counter-move is not a faster version of the same thing. It is a different category.

In February 2026 the failure got two academic names from two disciplines arriving at it independently. Margaret-Anne Storey calls it cognitive surrender, framed inside a new model of software debt that runs technical, cognitive, and intent debt together. Wharton's Shaw and Nave measured it: 80% of users follow AI's wrong answer when AI is wrong, 73% with no evidence of System 2 engagement at all. Practitioners are converging on the same vocabulary in their own work. Intent drift, plan decay, silent failures. The diagnosis is settled. The architecture that takes it seriously is what is coming next. Read the thesis.

Spegling · Private · Allowlist · Live at spegl.ing

Spegling.

The durable substrate beneath your AI agents.

Bridge architecture: Declared Intent, Living Authority, Evidence Audit. Memory that holds across sessions. Authority that names whose hat: the same operator wearing three fiduciary contexts carries three different ceilings. Every inference is stamped with the prompt version and the model that ran it. Self-proposed changes are inert until a human applies them with a rollback plan. The schema enforces the gate, not the convention.

Use through the interface or over MCP from any agent that speaks the protocol. Governed capabilities live inside Spegling, so the external agent uses them and cannot sidestep them. Bring your own agent code, any provider; run inside a per-tenant container with persistent state, an encrypted credential vault, and an egress firewall. The governor watches long-running work and surfaces decisions for approval.

See the product →

Dots · Public · Free tier

Dots.

AI that earns the right to answer.

A script tag you add to any page with words worth reading. Watches your visitor read. After five minutes of real attention, not tab-open time, opens a question field. Answers are grounded in the page and enriched by a living corpus around the subject.

Off-topic questions are refused. Shallow questions may be answered with a question back. The widget does not identify the reader, does not set cookies, does not ship data to advertisers.

Live in the corner of this page. Spend a few minutes reading and it will offer to answer.

Try it here

patterns-starter · Open · MIT

Starter.

The open bootstrap for your own corpus.

One file. PAT-0000, Living Patterns Corpus. The one pattern that generates all others. Fork it tonight. Add your first pattern from a problem you solved this week. Within a year you will have something durable. The Spegling corpus is already at a thousand patterns and counting.

Any Dots deployment can point at your own starter-built corpus instead of Spegling's managed one. Your agents read it; you compound it. The method is open so the shape survives whoever runs it.

Fork on GitHub

Adjacent.

Avrea

I'm founding engineer at Avrea: faster CI for GitHub Actions. Drop-in replacement for the default runners, 2–3x on cold builds and 145x with cache. Deep per-job observability so you can see where the time and money go. Recommended if your team wants faster builds and a lower bill.

Open source

A few small repos under github.com/varjoranta.

etchdb. Async DB layer for Python. Typed CRUD over Pydantic. Raw SQL when you need it.
turboquant-vllm. vLLM integration for low-bit weight quantization. Same work as the 34 tokens-per-second essay.
patterns-starter. Bootstrap for a personal pattern corpus. Fork tonight, compound for years.

Custom agents you can prove.

I build AI agents for one job and ship them with their own evidence: an eval harness that finds where they break before your customers do, judged by a model that does not share the agent's blind spots. Or I bring that harness to an agent you already run. You deploy knowing where it breaks.

Built and verified by one person. Failure modes named, not hidden.

See the services →

Hannu Varjoranta.

Systems engineer, founder, writer. Two decades building infrastructure, security, and data systems at scale, including work at Spotify and F-Secure, and later as co-founder of Valo and Cloop. Currently founding engineer at Avrea, working with the team on faster CI for GitHub Actions.

Varjosoft is my company for building, writing, and selective advisory work. It is intentionally small, personal, and long-term by design. The work on this site is where I think about the layer above execution: memory, trust, and the governance of systems that increasingly act on our behalf. The point of the work is to help the people using it stay less capturable as their tools keep changing underneath them.

The path is a conversation.

Three paths land here. Spegling access is by allowlist — say why and what you'd build. Agent engagements are open: tell me what the agent must do and what it must never get wrong, and the first reply can be a real scope and price (how it works). Dots on your own site, or a fork of patterns-starter — say hi, I want to hear about it. I answer personally.

Or email hannu@varjosoft.com directly. Your email is used only to respond to your inquiry.

AI that earns its place.