← All guides & prompts Download PDF
Starter pack 03
Build an AI that can search everything you've written
A goal-driven build prompt for your coding agent, plus the mistakes and tests that turn a RAG demo into a search tool you can trust with your own notes.
- INPUTYour notes and PDFs
- ON YOUR COMPUTEREmbeddings + Chroma + Ollama
- OUTPUTAnswers with sources
What it teaches
- Embeddings
- Semantic search
- Retrieval (RAG)
Build prompt
GOAL Build a private search engine for the documents folder in this project. I ask a question in my own words and get the passages that answer it, even when my words differ from the words in the file. Then I can ask for a short answer written only from those passages, with a source for every claim. Everything runs locally with Ollama. DONE MEANS For my five test questions, the correct source passage appears in the top five results. Answers cite file name and page or section for every claim. When the answer is not in my files, the app says so instead of guessing. Adding a new file updates the index without rebuilding everything.
Repair prompt
The failed test is [test ID]. I did: [exact steps, including the question I asked]. Expected: [result and the file it should come from]. Actual: [what came back, or the exact error]. Find whether the failure is in extraction, splitting, retrieval or the answer step. Make the smallest repair and rerun this test plus my five test questions. Keep my documents untouched. Update the test log.
How to use
1. Create a new project folder. 2. Open a coding agent that can run commands on your computer (for example Codex or Claude Code). 3. Paste the build prompt as one message. 4. Run the acceptance tests in the PDF before you rely on the tool.