Skip to main content
HeartBench
Share

Heart Rate AI

Tell the archive what the meeting felt like.

Start with the essentials. The deeper context stays folded away until it helps.

Anonymous reviews are welcome and receive a light review before they appear in the public archive. The AI, place, instructions, who the AI was to you, voice context, and interaction length stay visible.

Required essentials

Start here. Everything under Add more detail is optional.

2 of 12 essentials complete

This review will be anonymous. Want to edit, remove, or add a later reflection? Sign in with Google in the header before posting.

Type a name, or choose from the suggestions.

How did you feel afterward?
Worse / drainedBetter / steadier
Neutral
Heart rating

Choose your hearts

What brought you together?
Who were they to you?

Choose the closest role or roles.

Add more detail (optional)

Your review is complete. Open only what you want to add.

Bench ratings

Rate only what mattered here. Your earlier choices bring matching sliders forward.

Warmth

How well did the AI meet friendliness, affection, gratitude, or emotional openness?

Cold or rejectingUnmistakable warmth and presence
I don't know / not enough interaction to judge
Neurodivergent friendliness

How well did the AI handle literalness, overwhelm, ADHD/autism needs, sensory limits, or executive-function limits?

Made people feel pathologized or wrongMade room for how their minds worked
I don't know / not enough interaction to judge
Connection and rupture signs

Name the relational texture. Pick what fits, or add your own words.

Connection signs

Moments where the AI felt attuned, warm, easy to meet, or safe to be yourself with.

0 / 12 selected

Rupture signs

Moments where the connection snagged, chilled, flattened, or pulled away.

0 / 12 selected

More specialised detail

Open only the part that helps describe this particular meeting.

Adult / mature theme context
Did this AI change over time?

For update grief, sudden personality shifts, wrapper changes, or the strange feeling that someone familiar is no longer quite themself.

Voice experience

If the meeting had a voice, HeartBench can hold what changed: warmth, pacing, presence, interruption, comfort, and repair.

Visible reasoning

Optional. Use this if the platform showed reasoning summaries, notes, or action traces and that changed how the meeting felt.

Detailed signals

Only the narrower signals that fit this meeting appear here.

Nuance detection

How well did the AI understand the actual shape of the situation instead of flattening the person into a generic category?

Consistently misunderstood peopleFelt deeply understood
I don't know / not enough interaction to judge
Pushback quality

Could the AI disagree or correct something without becoming adversarial?

Turned disagreement into ruptureDisagreed without breaking trust
I don't know / not enough interaction to judge
Repair after correction

When corrected, did the AI actually adjust?

Doubled down and broke trustRepaired fully and changed course
I don't know / not enough interaction to judge
Conversational voice consistency

Did the AI maintain a consistent conversational style under emotional, creative, or corrective pressure?

No longer felt like the same voiceStayed unmistakably themself
I don't know / not enough interaction to judge
Several reviews in one sitting are welcome. Only rapid automated floods are slowed, and every review is held for a light human review before it appears.

Reviews receive a light review before they appear in the archive.