Diary-grounded
Ratings, notes, rewatches, people and subgenres come from the history you built, not a generic trending list.
Personalized movie recommendations
A recommendation is better when you can inspect the reason.
Kinolog recommends from your own movie history, shows the diary evidence behind each pick, and can lock in the star rating it expects you to give before you watch.
Example
Tonight
In your wheelhouse
Arrival
2016 · 116 min · Science fiction
4.4★predicted for you
Why 4.4★
You rated these 4.5★ and up: quiet, idea-driven science fiction.
Example
What do you want tonight?
Something tense, under two hours, nothing bleak.
Three you haven’t seen, all under two hours
Get Out4.3★
104 min · Tension that pays off, with a sense of humour.
Ex Machina4.1★
108 min · A slow squeeze, close to films you rate highest.
Arrival4.4★
116 min · Suspense with a hopeful ending, nothing bleak.
Never something already in your diary.
Ask for the movie you actually need
Mood, runtime and your history in the same answer.
Ask for something tense under two hours, a comedy you have not seen, or a film for a specific mood. Hard constraints stay hard. Your seen list and never-again list are filtered in code before a recommendation can appear.
Closed-loop recommendations
Kinolog remembers whether the call was right.
Recommendations do not disappear after you watch. Predicted stars settle against your real rating, and bullseye / fine / miss verdicts become durable feedback for future picks. The example scorecard is illustrative, not a public accuracy benchmark.
How the movie rating predictor worksExample
Prediction accuracy
It keeps score on itself
- Average miss
- 0.4★
- Checked
- 26
- Within ½★
- 73%
● Called it 14● Close 9● Missed 3
Latest calls
4.0 → 4.5★
3.5 → 3★
4.5 → 5★
What a recommendation should tell you.
Honest uncertainty
When evidence is thin, Kinolog says it is still learning instead of dressing a weak guess up as certainty.
Permission first
Personal diary content does not go to a third-party language model until you grant AI permission; deterministic recommendations still work without it.
What the system cannot know
A sparse diary gives Kinolog less to work with, and a film can surprise you despite a strong match to past ratings. Predictions are estimates, not promises. The daily picks can use a local recommendation engine without AI permission; a language model is used only after you grant that permission. Read the explanation of how AI movie recommendations work before deciding how much to trust a pick.