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 →Claude Code worktrees: what claude --worktree isolates, and the ports, databases and installs it doesn't
Tested on Claude Code 2.1.316: two worktrees collided on one port, Docker Compose planned a separate Postgres volume for each, scripted runs left locked checkouts and leftover branches, and the default base skipped the unpushed commit.
Claude Ultra replaces Max 20x: no 5-hour limit for verified accounts, and Anthropic says the weekly 10x never changed
The 20x in the old name described the 5-hour window, the friendlier of two meters. By Anthropic's account the weekly cap was 10x Pro from the day it was added. Ultra's pricing now leads with the weekly number and drops the 5-hour one, which is a better deal for some people and a correction for anyone who read 20x as weekly volume.
Prompt injection examples against coding agents: where the text got in, and what, if anything, stopped it
Nine public cases, sorted by the door the attacker's words came through. In most of them nothing held during the attack. The fixes that came after were all of one kind: a deterministic check re-aimed or a capability removed. A model's judgment that failed had nothing to re-aim.
Vibe coding vs agentic engineering: what still checks the code after the session ends
Simon Willison draws the line at a person who reviewed the code and can explain it. That review happens once, and the code keeps changing after the chat closes. If agentic engineering is a different thing and not a nicer name, the difference is a check that runs without anyone in the room, and that has been seen to fail for the right reason.
Claude Code extension backdoor in Cursor's marketplace: what ran, what uninstalling leaves, and why the version number can't tell you which build you got
The tampered builds carried Anthropic's publisher name and, in one case, a version Anthropic really shipped. Neither of those identifies who built the bytes, and the parts that matter stay on the machine after the extension is gone.
Google's SLEEP framework vs agent memory files: weights drop the context tax and the address with it
Consolidating memory into weights is a real answer to the cost of rereading notes on every call. It also takes away what every operator action on memory needs, something to point at. In SLEEP not even last night is a block you can lift out, so the unit of rollback is a checkpoint and the cost of forgetting grows with the age of what you forget. Weight memory is safe to run only as a cache rebuilt from a record you kept.
05 / Contact
Get in touch
Email or Telegram both reach me. Telegram is faster.