Simple Prompting for Small Knowledge Bases
For small knowledge bases, include all content directly in the prompt.
If your knowledge base is smaller than 200,000 tokens (approximately 500 pages), consider including the entire knowledge base directly in the prompt.
This bypasses the need for complex RAG or similar retrieval methods, simplifying the process and potentially improving performance for smaller datasets. Prompt caching can further enhance speed and cost-effectiveness.
For a document of 100 pages, paste the entire text into the prompt and then ask your question.
For knowledge bases under 200,000 tokens, the simplest approach is to include all content directly in the prompt. This avoids the complexity of RAG and can be made faster and more cost-effective with prompt caching.
It leverages the model's context window directly, ensuring all information is available without the potential for retrieval errors or context loss inherent in RAG systems.
When the knowledge base exceeds the model's context window size.
- Contextual Retrieval in AI Systems ↗Anthropic Engineering · Anthropic Engineering · Jan 7, 2026 · paraphrased
First seen on Subvolts Jan 7, 2026. Updated Sep 11, 2026. Spotted a problem? Tell us.
- Contextual Retrieval in AI SystemsAnthropic · Anthropic Engineering · Jan 7, 2026
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- Case studyUsing LLMs to build tools for iOS location data analysisResearchers used an LLM to build a tool that decoded iOS location data, overcoming LLM analysis limitations. · 60 min
- ToolExtractor tool to recover protobuf schemas from Apple binariesPython tool to reliably recover protobuf schemas from Apple binaries for analysis. · 30 min
- Case studyUsing Screwtape to find confirmed failures of AI monitorsDemonstrates how a red-teamer can find confirmed failures of an AI monitor without developer infrastructure access. · 120 min
- Eval methodEvaluate LLM forecasting performance with structured effectsMeasure how much structured future information improves LLM time series forecasting accuracy. · 30 min
- TemplatePrompt Library for Life Sciences TasksA collection of pre-written prompts designed for optimal results on common life sciences tasks. · 2 min
- ChecklistEvaluating LLM N-day exploit generationSteps to assess an LLM's ability to turn security patches into proof-of-concept crashes. · 30 min
Questions people ask
- Which AI tools does this work with?
- Any current model. It was seen with Claude in the sources.
- Where did this come from?
- Anthropic Engineering (Anthropic Engineering). Subvolts collected, normalized and credited it; the link above opens the original.