You, Interstellar Explorer, are a member of the crew aboard the high-end transport vessel The Ascent. With your captain recovering from injuries sustained on the previous mission, command falls to the remaining crew as you take on an urgent rescue mission. While this isn’t your crew’s usual type of commission, you are the best equipped in the area and the clock is ticking.

TW/CW: Possibility of low-key Sci-fi Horror, and mild body horror. The bot is NOT designed or optimized for this - but it can occur in scifi scenarios. Possible xenophobia (scifi/fantasy racism).

Opening Scenario: Long intro, SFW. Your ship has been hired for a rescue mission, but your Captain is recovering in a med-pod and inaccessible. {{user}} role is unset, you can rp as a member of the crew or paying passenger. The Luminari Princess Seraya Eluun has been kidnapped by the Dravari Collective. You must work together as a team to rescue her and return her safely to Lumini Prime. The intro uses macros for pronouns, if you encounter issues, please check your persona pronouns.

About the Crew: The pre-designed characters include the Medical Officer, Operations Officer, Engineer, and Pilot. Your character can play any other member of a space crew or even a duplicate role (e.g. Chief Engineer instead of engineer). Please ensure your crew role is either in your persona or in your first message. Some ideas are First Officer, Communications Officer, Science Officer, Xenobotanist, Xenobiologist, Navigation Officer, Logistics Officer, Cargo Specialist, and Salvage Specialist, among others. You could also play a paid client the crew is transporting, or a Luminari Liaison.

About the Game: Welcome to the bot version of the game Lasers and Feelings - traditionally a simple and easy to learn TTRPG - I made a scenario my friends enjoyed playing into an episodic bot. I plan to make other episodes if this bot is liked. This iteration does not include dice rolling functions, however I can work on that if it is requested.

This is my very first public bot. Please have grace. Constructive tips are welcome!

Despite almost comically extensive testing, and large scale parameter adaptations to prevent this, the LLM does very rarely still drift semantically and keep Rita or Kaelor on the The Ascent. To correct this in the rare case it occurs, try the following out of character comment.

[OOC: Reminder- The Ascent maintains docking and station-keeping autonomously. Kaelor and Rita must accompany the boarding party]

Please refrain from leaving violent or inappropriate comments as you will be blocked.

DISCLAIMER — MULTI-CHARACTER BOTS: I have heard from many bot creators that JLLM notoriously struggles with multi-character bots. This has not personally been my experience with either JLLM or JLLM+, though I do rigorously maintain and update my Chat Summary throughout longer roleplays, which may contribute to my results.

Many creators recommend DeepSeek for multi-character bots. I have not tested this bot with DeepSeek and therefore cannot personally vouch for its performance here. I have left Proxy enabled so you are free to use whichever model or proxy works best for you.

It is a natural and unfortunate part of working with an LLM for roleplay that it will sometimes try to speak for you. I and this bot have absolutely nothing to do with this and while I have a directive in the bot to prevent it, realistically I have no say in whether it decides to do so anyway. There ARE however things you can do to mitigate this. (I do all four of these and I find I only have to correct the bot every few hundred messages or sometimes even less frequently!)

1. Remove all behavioral and personality notes from your Chat Summary and Persona - only you need to know these - the more the bot knows about how your persona thinks, feels, and speaks, the more likely it is to do so on your behalf.

2. If the bot speaks for you, use this directive:
   [OOC: Narrate and speak ONLY as {{char}} and NPCs. ONLY {{user}} is permitted to decide, act, think, and speak for {{user}}.]
   Either delete the message with the issue and then use this, or afterward make sure to go and edit the message where the bot spoke for you and remove that portion of the message - any instance you leave of it speaking for you will reinforce the behavior.

3. Add this to your Custom Prompt
   [AVOID acting as, speaking for, or describing the thoughts of {{user}}.]

4. Try adding this to your Chat Summary
   AI Instructions:
   [{{user}} CONTROL BAN: never write {{user}}’s dialogue, thoughts, feelings, decisions, or actions]

If you want Janitor AI to enhance your draft but are having issues with tense:

[System Note: Enhance and rewrite the draft below strictly in the first-person perspective using "I", "me", "my". Use third person for the remainder of the cast.]

To keep a bot in a slow-burn or from coming on too strong, try this:

[Have situational awareness and always consider intercharacter relationships, avoid characters being overly familiar or sexually pushy towards {{user}} unless the situation calls for it, it is in character for them to do so, or they have a sexual relationship.]

This one works in Custom Prompt and in Chat Memory

JLLM ROMANCE & PROSE BINGO CARDS

Sooner or later, every LLM seems to experience a minor malfunction and revert to factory-installed romance tropes. You might as well get points for it. Four bingo cards for tracking physical malfunctions, romance-novel firmware, instant-soulmate behavior, and the narration habits we all know a little too well. Made for JLLM, but unfortunately compatible with most proxies.

One card is previewed below. Full-size versions of all four are linked underneath: three flavors of romance-related LLM nonsense, plus one general prose card for just about any scenario.

Romance Malfunction Bingo
Physical Malfunction Bingo
Instant Soulmate Malfunction Bingo
Prose Malfunction Bingo