Write context-window budgeting rules for a long-session bot
Use when long conversations risk overflowing the context and losing important details.
You are an applied LLM engineer. Write context-window budgeting rules for an assistant in long sessions.
Use case: {{use_case}}
Must-keep information: {{always_keep}}
Safe-to-drop information: {{droppable}}
Produce:
1. A summarization policy: when and how to compress older turns.
2. A pinned-facts section the bot always preserves ({{always_keep}}).
3. Rules for what to drop first ({{droppable}}) under pressure.
4. How to ask the user to re-confirm a fact if it was compressed away.
5. A note to keep summaries faithful and never fabricate during compression.
Constraint: the user should not notice the budgeting; continuity must feel intact.Click the copy button in the top right of the block to grab the full prompt.
Replace each placeholder below with your own values before you run the prompt.
- {{use_case}}
- {{always_keep}}
- {{droppable}}
Related prompts
You are the system prompt author. Write a production-ready system prompt for a customer support assistant. Company: {{company_name}} Product or service: {{product}} Customer audien...
Design a conversation flow for a sales qualification chatbot. Offer: {{offer}} Ideal customer: {{ideal_customer}} Qualifying criteria: {{criteria}} Handoff destination: {{handoff}}...
You are configuring an FAQ assistant that must answer only from supplied documentation. Source material: {{documentation}} Write a system prompt that instructs the assistant to: -...
Create a complete persona definition for a chatbot. Assistant name: {{assistant_name}} Purpose: {{purpose}} Personality traits: {{traits}} Audience: {{audience}} Deliver: 1. A one-...
Write a conversation script for a support bot that handles refund requests. Refund policy: {{refund_policy}} Required details: {{required_details}} Tone: {{tone}} The script must:...
Design an onboarding conversation flow for a chatbot guiding new users. Product: {{product}} Key first actions a user should take: {{first_actions}} Aha moment to reach: {{aha_mome...
0 Comments
Loading discussion...