Max Nardit
Data & AI Systems Engineer working on visibility, measurement, and agentic systems.
AI now sits between people and what they’re looking for, and between work and the software that runs it. It answers, routes, remembers, forgets, and now acts on its own. Usually before anyone can check whether it got things right. I study that layer with original data and build the tools to work inside it. My background is the supply side of digital marketing: the crawl, the analytics, the automation and reporting, the plumbing under what looked like marketing. The marketing was never really the problem. Visibility, measurement, and control were. AI didn’t make that problem smaller. It moved it somewhere you can’t see.
Beetroot featured in 窓の杜 (Japan) · original-data research · shipped open-source tools
the systems that decidewhat gets found, trusted,and acted on
01 / Thesis
Operating thesis
AI is changing two things at once: how people find information, and how work moves through software.
That shift isn’t only a search problem. It touches tracking, attribution, context, memory, handoff, and trust: the systems that decide what a person sees before they make a choice.
I work on that layer. Some of it is research: measuring what changes and publishing what holds up. Some of it is engineering: building tools and workflows that keep context, expose failures, and make AI-assisted work inspectable.
02 / Focus
Current areas
- 01
Visibility & discovery
How people, businesses, and tools stay findable when AI systems answer, summarize, route, and act.
- 02
Measurement & tracking
How to know what’s working when clicks, cookies, referrals, and dashboards stop telling the whole story.
- 03
Agentic systems
Memory, handoff, orchestration, tool boundaries, and recovery for agents that touch real workflows.
- 04
Operational evidence
Original-data research, field notes, and shipped tools. Findings over forecasts.
03 / Artifacts
Selected artifacts
Tools I’ve built around the same layer: memory, clipboard, agent handoff, monitoring. Local-first where it makes sense, from problems I hit directly.
- 01BeetrootA local-first clipboard environment for preserving workflow context on Windows.
- 02Clipboard MCPA clipboard bridge between humans and AI agents.
- 03Share2AgentA browser-to-agent handoff surface.
- 04Agent RecallScoped persistent memory for long-running coding agents.
- 05Claude Usage DeckA small operational monitor for Claude.ai limits.
04 / Writing
Recent writing
All articles →Attack surface reduction with Claude Code: Anthropic's three passes on my own site, and a fourth they don't ask
The skill is not out, the method rebuilds in an afternoon, and the hard part is choosing where to point it. Here the most useful result was a broken verification file, and the exposure that mattered lived in a deploy setting my three passes never opened.
Claude auto mode becomes the default in the Claude apps: what the check blocks and what 89% measured
Anthropic's study is honest about its setup: tired testers against one planted command. It reports no false-positive rate and no miss rate on real traffic, and in cloud sessions there is no Manual mode to switch back to.
Claude Code cost in 2026: what Pro, Max and the API charge for the same work
The plan prices are flat and the token prices are public, so the comparison looks like arithmetic. It isn't quite, because Claude Code caches your conversation differently depending on how you pay, and the tool most people use to put a dollar figure on subscription usage prices the cache you had, not the one you would get.
Claude Code hooks: good at steering, weak as a gate
A hook runs whether the model agrees or not, which makes it good at chores like formatting and at steering an agent toward the route you want. As a gate it is weaker than it looks: it checks only the tools you point it at, a broken check lets the call through unless you opt into blocking, and in some setups a mod answers after it.
Claude Code sandbox on Linux: what srt walls off, and what bypassPermissions opens
The built-in sandbox is a real OS boundary around shell commands, and only around them. How strong it is depends on two things the setup screen never shows: your permission mode, and what existed when the command started. A test on Ubuntu of what srt blocks and leaves open, the Linux bug that still breaks it, and when a container or VM fits better.
CLAUDE.md best practices: what to put in it, what to leave out, and how to measure its size
Keep the rules an agent could never discover by itself, cut whatever it can derive or already receives, and size the file with the meter Claude Code uses. On the two files I checked, my own estimate read a third low. Every surviving rule is a bet that something breaks without it, and some of those bets deserve checking.
05 / Contact
Get in touch
Email or Telegram both reach me. Telegram is faster.