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 "Don't ask again" and settings.local.json: how to find the passwords in your allow rules, and what to change
On the current Claude Code release the prompt turns most of a command into a wildcard before it saves the rule, and a password written in front of the program still survives. The session transcript keeps the whole command, and the cleanest fix is a command line that never holds the secret.
Claude Code slash commands: the built-ins worth knowing, and why your custom /command is a skill now
Treat the commands folder as code Claude can call, not as macros. Audit which files leave model invocation on, check the turn count in scripted runs instead of trusting the exit code, and put the guarantees for anything with side effects in permissions and hooks rather than in an invocation flag.
Claude Code vs Gemini CLI: seven ways developers split the work, and which ones survived June 18
The 2025 setups that paired the two tools leaned on a free Google login and a bigger context window. The login went to another tool in June, and Claude Code caught up on the window. What decided which setups survived was the account behind each call, not the tools themselves.
Spec-driven development with AI agents: Spec Kit's own repository ignores its specs
Keeping a spec after the session is the cheap part. A spec earns its keep at delivery, as the one artifact a person read and corrected before any code existed. After the merge it is a document nothing runs on its own, and the honest choices are to mark it as history, to keep a check pointed at it, or to move what must last into the constitution and the tests, which is the choice Spec Kit's documentation describes for its own repository.
Anthropic's components of agent memory in Claude Code: audit MEMORY.md, keep the transcripts, run your own dreaming pass
Claude Code keeps the notes and the startup index indefinitely, sweeps the transcripts behind them after 30 days by default, and ships no pass that checks one against the other. Anthropic's results show why that check is worth having, so here is a way to run it locally and read the result before any of it lands.
Claude Code and your email in a User-Agent: what the privacy mod checks, and what a hook and an allowlist add
Nobody built a feature that mails your address to websites. The model finds it in its context, meets a site that asks scripted clients for a contact, and helps. Every fix on offer filters that address on its way out, so rank the filters by what the model cannot argue past, and know which routes each one leaves open.
05 / Contact
Get in touch
Email or Telegram both reach me. Telegram is faster.