A panel of 24 simulated residents reads your draft before the public does.

24 simulated residents

Sampled by real district, language and age data, each with their own personality.

What catches attention

See what they notice, what worries them, and what just scrolls past.

What they'd post

What they'd actually say in public — before you send it.

Enter your draft here

🚨 On Wednesday, 10 June 2026, the Estonian Rescue Board will test the EE-ALARM public warning system.

Between 15:00 and 15:10, test notifications will be sent through the Eesti app and the “Be Prepared!” app, warning messages will appear on ERR channels, and sirens will be activated.

💬 Before the test, everyone will receive an SMS notification. Please inform your family members and friends, especially children and older people, to avoid unnecessary concern — this is only a test and there is no real danger.

To receive warning notifications, download the Eesti app or the “Ole valmis!” app and make sure notifications are enabled.

📢 Use this test as an opportunity to review your emergency preparedness. Think about where you would shelter in the event of a real emergency and, if possible, practise doing so wherever you are at the time — at home, at work, at school, or out in public. During the test, nearly 90 public shelters across Estonia will be open to visitors from 14:45 to 15:30.

The next EE-ALARM test will take place on 14 October.

More information: olevalmis.ee  or the State Information Helpline 1247.

Posting as

Panel city

Context (optional)

Local

History

Step 2 of 3

Twenty-four people
are reading it.

Waiting for the run to start.

—

0 of 24 shown

This panel — Tallinn

Layer 1 — Demographic

Age, gender, district, language, ethnicity, birthplace, family status, job and income band — sampled from real population data.

—estonian

—russian

—age range

—districts

Layer 2 — Psychological

Openness, conscientiousness, extraversion, agreeableness, neuroticism — a full Big Five (OCEAN) profile per seat, shaping how each one reacts.

Layer 3 — Situational awareness

Each seat has also read today's real news in its own language before reacting — Estonian-speaking seats from err.ee, Russian-speaking seats from rus.err.ee. Today's ERR coverage only, for now — it shapes mood and attention, not the demographics or personality above.

Layer 4 — Reaction model

Each seat reasons independently, prompted with its own demographics, personality and news context — not one model guessing on behalf of all 24. Running on Claude Haiku 4.5 today; moving to a locally-hosted model next.

Layer 5 — Calibration

Logged against real outcomes after every run (see History). Aggregate accuracy tracking across pilots is next.

Estimates, not guarantees — a surprising result is often the useful one.

What the panel made of it

Reacting to a post from — — Tallinn panel

Here's how it landed: the breakdown, what caught attention, and what they'd actually say in public.

At a glance

A surprising split is worth more than an expected one — it points at what you hadn't considered.

0 personas polled

— would comment publicly

— negative and worried

— got their attention

— made them think

Insight clusters

Grows as you explore — every run and every question you ask adds points, grouped under a short topic.

Their internal train of thought while reading

Private reasoning, persona by persona — not something they'd post

Where attention went

The words personas singled out most, sized purely by how often they were noticed.

What they'd say publicly

Not everyone who reacts posts about it. Whether someone crosses that line depends on how strongly they feel and who they are.

Actually posted

Never posted

Where reactions landed

Calm doesn't mean safe — it can mean nobody noticed. Each point is one persona, placed by how strongly they reacted (calm to anxious) and which way that reaction leaned (negative to positive). The quiet zone at the bottom isn't automatically a win.

anxiouscalm

negativepositive

How this panel works

Each of the 24 seats is sampled from real district population and language data for the selected city, then given a full Big Five (OCEAN) personality profile — openness, conscientiousness, extraversion, agreeableness, neuroticism — on top of its demographics (age, gender, district, language, ethnicity, birthplace, family and work status, income band).

Each seat reasons about the draft independently, prompted with its own demographics, personality and news context — not one model guessing on behalf of all 24. It runs on Claude Haiku 4.5 today; a locally-hosted model is next. Reactions get logged against real outcomes after every run (see History); aggregate accuracy tracking across pilots is next too.

These are estimates, not guarantees — a surprising result is often the most useful one.

Twenty-four peopleare reading it.