Each figure on this site traces to a ledger of sourced claims. A number without a source does not ship.
Evolving since February 2026
A private AI system: one builder, many agents, real consequences.
It remembers from sources, connects small-business workflows, and acts only within explicit permissions. It runs across platforms, swaps models, and lives on hardware that cost less than a laptop.
How this site is made
AI agents made this site. The framework, the judgement calls and the voice are mine.
Since 30 August, every page here has been produced with AI agents I run, mainly Claude Code and Codex, working inside rules and review steps I set: the research, the drafts, the code, the diagrams, a four-minute explainer video and the LinkedIn carousel. I choose the argument, decide which words survive, and sign off on what goes live.
Every release passes an automated gate that refuses anything carrying private notes or internal references.
Each page is mirrored into a document I comment on, and my comments become the next draft.
Decisions go to a panel of advisor personas that disagree with each other before I decide. This section came out of one.
One thing that went wrong
In early October, a file on this site was found listing the paths of my private notes, though not their contents. The release gate above exists because of it.
Seen in the system
It remembers from sources, and the sources are connected.
Facts come from real notes, records and logs rather than from conversational memory. Each answer stays traceable to the file it came from, and the files reference one another.
Every bar in these captures is a deliberate redaction, not a rendering fault. What gets withheld follows a written disclosure rule, decided once, rather than a judgement call made page by page.
Real system recording
The whole knowledge base
-
01
The whole knowledge base
Every dot is a note. Dense clusters are subjects with deep, connected material behind them.
-
02
Zoom into the relevant neighbourhood
Moving closer makes individual pages legible while keeping the relationships around them visible.
-
03
One page, with its connections intact
Selecting a page reveals the frameworks, plans and references around it, so an answer remains traceable.
View the original still captures
Where it works
One operating layer for work and life.
Business work
Commercial strategy, AI visibility, product positioning, and decision support for confidential advisory work.
Creative and web
Websites, diagrams, explainer videos and carousels, built by agents and published after my review. See how this site is made.
Personal administration
Inbox, calendar, tasks, documents, decisions, and project continuity.
Family and travel
Shared planning, groceries, trips, chores, allowance, and family coordination.
Household and finance
Vendors, receipts, payments, shared expenses, and recurring follow-ups.
Connected home
Lights, scenes, sensors, cleaning, watering, alerts, and household routines.
Health
Health records, test results, and history kept connected, organized, and searchable.
Operational evidence
Built for real work, and run with the discipline it requires.
- Supports confidential advisory work in commercial strategy, positioning, AI visibility, and decision support
- Daily use through WhatsApp and Telegram, in English and Hebrew
- Source-backed memory plus connected tools and home systems
- Nightly deterministic self-audits and canary checks
- Fallbacks across AI providers, with outage and recovery alerts
- Nightly offsite backups, a recovery runbook, and an incident log
- Watchers detect critical file replacement, session failures, and intrusion events, repair recoverable states, and alert when attention is needed
- Specialists receive only the tools their job needs
- The chores agent cannot inspect family photos because image access is not available to it
- Long-term memory, usage, and cost are reviewed on a defined rhythm
Multiple models, one governed system
Model choice stays flexible. Usage stays visible.
Requests can move between providers when needed, while usage and cost remain measured by provider and every fallback stays visible. Subscriptions carry the work. Metered API billing is used only where no plan covers the job, which keeps it a deliberate exception instead of the default.
Estimated model cost today
$0.088Primary provider$0.049
Secondary provider$0.038
Trailing 7-day average$0.224 / day
Fallback visible The last request used the backup model.
Usage is measured by provider
View the original redacted report
Seen in the system
It runs the house it lives in.
The connected home is part of the same operating layer, not a separate hobby. This real phone walkthrough moves from the whole house to one room, a shared occasion and the watering system underneath it.
Real phone recording
The whole house at a glance
-
01
The whole house at a glance
Rooms and devices are grouped by floor, so the system understands where an instruction belongs.
-
02
One room, direct control
Lights, blinds, climate and media remain available in one place when direct control is useful.
-
03
A moment, not a device list
Entertaining brings the living room, kitchen, entrance, staircase and gate into one useful view.
-
04
The infrastructure underneath
Watering totals, valve state, flow and missed-run alerts are visible when the family needs the detail.
View the original redacted home captures
Watching and raising the flag when needed
The interface is only half the point.
The system confirms scheduled work, keeps reading the sensors and raises an exception without waiting for someone to inspect a dashboard.
06:03
Morning watering completedSoil moisture increased by 2%
Done
13:03
Afternoon watering completedSoil moisture increased by 2%
Done
13:45
Soil moisture: 98%Still unchanged after both cycles
Watch
Possible leak or stuck waterThe system raised this alert on its own.
The morning cycle completed
View the original redacted alert
Works where the conversation is already happening
It coordinates travel and stays with the group.
There is no new app to learn. The assistant joins the WhatsApp group already in use, so questions, updates and shared decisions stay visible to everyone. It answers questions, writes briefings and keeps watching the bookings.
Choose a real trip story
etgar.ai
✈️ Flight update
According to TriFlight and Trip.com, the current schedule is:
- Departure: 14:30 Dubai time, Terminal 3
- Arrival: 19:45 Colombo time, Terminal 1
The trip file says 15:00, so departure is 30 minutes earlier. The terminals are unchanged.
What happened behind the message
01
Background check
The booking stayed under watch after the planning was finished.
02
Sources compared
Two flight trackers were checked against the time stored in the trip file.
Verified change15:00 → 14:30Terminals unchanged
The booking stayed under watch
Group member
@etgar.ai How difficult is tomorrow's climb, and how high is it?
etgar.ai
Tomorrow's route includes Sigiriya, or Lion Rock. 🦁
Height: about 200 metres above the surrounding jungle, and roughly 350 metres above sea level.
Difficulty: not a hard athletic climb, but it is demanding. Expect around 1,200 steps, including some steep sections with railings.
ℹ️ This difficulty information is general destination knowledge, not from the trip files.
What happened behind the message
01
Source boundary
This was general destination knowledge, not something found in the trip files.
Answer provenanceGeneral knowledgeNot claimed as a trip-file fact
A question arrived in the ordinary group
etgar.ai
🏝️ Tomorrow's trip brief
Base: Havana Club, Uppuveli. We are staying here for a few more days.
🚐 A short drive to Nilaveli for snorkeling.
🐠 Plan: reef snorkeling, colourful fish, and perhaps small, harmless reef sharks. Later: rest, pool and beach. Everything stays flexible with the conditions.
🎒 Bring: swimwear, waterproof sunscreen, water shoes, snorkel masks, beach towels and cash.
Good night. Tomorrow will be beautiful. 🌊
What happened behind the message
01
Plan read
The next day's route, activities and practical details were gathered from the shared plan.
02
Brief prepared
Location, transfer, activities and what to bring were condensed for the group.
Delivered automaticallyTomorrow, readySent the evening before
Tomorrow's plan was read from the trip files
Recreated from real exchanges. Names and personal details have been removed.
Open the original, redacted WhatsApp chats from the trip group
Works where the conversation is already happening
Shared ledgers for chores, budgets, and tasks.
People report chores in the WhatsApp group they already share, where everyone can participate and see the result. The price list is fixed in advance, so what a job is worth is not renegotiated at the end of the week.
Child
@etgar.ai I unloaded the dishwasher and loaded it again. 🍽️ Please add both.
etgar.ai
I matched “Unload the dishwasher,” but “load the dishwasher” is not a standalone task in the fixed chore list.
Did you mean “Clear the sink and load the dishwasher,” or is this a new chore?
Child
Yes. I cleared the sink and loaded the dishwasher. 👍
etgar.ai
✅ Unload the dishwasher: +15 points
Weekly total: 35 points.
✅ Clear the sink and load the dishwasher: +15 points
Weekly total: 50 points. 🎉
What happened behind the conversation
01
Fixed list checked
“Unload the dishwasher” matches. “Load the dishwasher” alone does not.
02
No guessing
An unknown phrase stops the process until the group clarifies it.
03
Exact match
The clarification maps to “Clear the sink and load the dishwasher.”
Ledger updated+15 +15Weekly total recalculated
A child reports two completed chores
Recreated from a real group exchange. Names and personal details have been removed.
Open the original, redacted WhatsApp chat from the shared chores group
Seen in the system
It watches itself, and says so when something is wrong.
A health panel regenerates through the day across both the knowledge base and the machine underneath it. Alerts fire only on red, plus one message when a fault clears, so silence is meaningful.
Trust by design
Private enough to use. Inspectable enough to trust.
The operating system and its readable knowledge base run on a private home server. External AI models are interchangeable services, not the owners of the system or its memory.
Checks, incidents, and fixes remain visible. When a failure repeats, it is turned into a rule or a deterministic tool so the same problem is less likely to happen again.
The idea
Not another chatbot. A personal system that works where life already happens.
This is a working pilot of a private operating system with long-term, source-backed memory. It connects knowledge and actions across the tools a person or family already uses, while keeping the system readable, inspectable, and portable.
I built it for three reasons: to experience first-hand, as an early adopter, how buying changes when AI does the finding, choosing and using; to run my own and my family's work and life on it; and to build differently. I have been a builder many times before. What is new is that I can now write the code: connecting systems and apps that were never connected, and automating processes that could not be automated before. Together with solving discoverability and selectability at Lokalise, it changed how I think product-led and sales-led motions evolve in the age of AI. It is now the platform, a second brain and its agents, that I use to assess where a company's Serviceable Line sits.
How it works
Three ideas make it different.
It remembers from sources
Important facts come from real notes, records, tasks, and logs. They remain traceable to their source instead of disappearing into vague conversational memory.
It coordinates across life
Focused assistants connect personal administration, family and travel, household and finance, the connected home, and the flow of information between them.
It keeps the owner in control
Access is scoped by task. Durable memory requires human approval, sensitive actions keep a confirmation step, and the knowledge remains readable outside any one AI model.
Who is behind it
Built and operated by Etgar Bonar, a commercial executive who chose to learn AI by building and running a working system around real life.
He also built a mobile development workspace so he can inspect, program, and improve the system from anywhere.