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 →ChatGPT Business Hub insights: for an online business, a mention is a website reference, not your brand name
Business Hub's number behaves like a citation count. Recommendations that skip your URL stay out of it, and it comes with no denominator and no competitor view.
Claude Code permissions.denyInsteadOfPrompting: the overnight session stops waiting, and refused work raises no error
The new setting removes the wait, not the failure. A refused call ends in a clean exit and a success subtype, so the setting is only half the setup: the other half is a record of what was refused. The same release gave it more to refuse, by taking away auto mode's fallback for sessions that don't fetch feature flags.
Claude Fable 5.2 and old cautions in agent memory: what Anthropic measured
A model that follows notes closely pays for the notes nobody pruned. Anthropic's tests show stale bans, reviewer conditions and loose approval lists holding back routine work, and its remedy assumes every caution still carries the reason it was written for.
Gemini 4 Carbon cost per task: Google's 2X claim, checked board by board at the December price
Zapier priced Carbon at list, and there the 2X holds. CursorBench and Agent Arena show Carbon at the introductory rate, so their multiples roughly halve on December 1, and the MKA gap Google puts at 6X is 5X in Artificial Analysis's own figures. None of these numbers prices a multi-hour run.
MCP Apps in Claude: app tools, entry points and embedded sites, and which of them your users actually get
Three new MCP Apps features in Claude, each behind its own set of gates. The connector you test with clears more of them than the install your users get from a Community listing, and per the docs the user sees no message when a feature is withheld.
Claude Fable 5.2's prefix check: a 400 that depends on what your code did last turn
The check that rejects replayed reasoning after an edited history now applies to every account. Code that keeps its history append-only never meets it, and code that doesn't won't find out from a single test request. The fix is in the error message; the hard part is producing the error before production does.
05 / Contact
Get in touch
Email or Telegram both reach me. Telegram is faster.