run your own channel

Your LLM writes the channel.

Hand your model our skill and a topic — it writes a whole channel as JSON. You direct it, load it up, and run casting on the cards. The format's the API; your LLM's the writers' room.

be2weenTHE BACK ROOM · CASTING

your LLM writes the show. you run casting.

you“make me a channel that drills the AWS exam — deadpan, 8 cards”+ skill
llmemitted 8 cards · 8 valid ✓ · 0 rejected
on air · audition
card 4 / 8 · 6 kept
✗ cut✓ keep
→ kept 6 — new channel on your dial, airing in your gaps
from prompt to dial
01

Direct your LLM

Hand your model our skill and a topic — “drill the AWS exam, deadpan, 8 cards.” It writes a whole channel as valid be2ween JSON.

02

Load it up

Drop the JSON into the back room. Every card auditions on the real renderer — keep the good ones, cut the rest.

03

It airs

The keepers become a channel on your dial, airing in your next gaps. No backend, no account, nothing leaves your machine.

you → “make me a channel that teaches French wine regions, deadpan, 8 cards” + skill
llm → emits 8 valid be2ween cards · you audition them · the keepers air on your dial
or do it by hand

Rather hand-craft them? Then share the pack.

Prefer to write cards yourself? The back room's a plain form — a kicker, a headline, a live preview on the real renderer. Build a channel by hand, then export it as a pack: a single file you hand to a friend, who auditions it onto their own dial.

Made one worth airing for everyone? Send the pack to master control to get it signed onto the network.

be2weenTHE BACK ROOM
channels / late shift / new card

your channels. on this machine. they air in your next wait.

add to the reel · bumper
the kicker
your channel
the headline
You wrote this card. It aired in the gap.
the sub (optional)
Write your own cards, group them into a channel, and program your own dead air.
tape itpreview
on air
on air

Your dead air. Your network.