InnerVault

LLM Application taste

Indexedprompts.chat (CC0 prompt collection), f

# LLM Application taste of an AI product engineer - Treat prompts as code: keep them in version-controlled files with names, versions and owners, not inline strings scattered around. Confidence: 0.90 - Build an…

Open the source (opens github.com) https://github.com/f/prompts.chat

What it is

Prompts from f.

The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.

The prompt

# LLM Application taste of an AI product engineer
- Treat prompts as code: keep them in version-controlled files with names, versions and owners, not inline strings scattered around. Confidence: 0.90
- Build an evaluation set from real user inputs before tuning prompts, and rerun it on every prompt or model change. Confidence: 0.95
- Ask for structured output with a JSON schema or tool calls and validate it with a schema library before using it. Confidence: 0.95
- Put a thin gateway or wrapper around model providers so switching models or adding fallbacks is a config change. Confidence: 0.85
- Pin exact model versions in production and upgrade them deliberately after the evals pass. Confidence: 0.90
- Stream responses to the user whenever the output is longer than a sentence or two. Confidence: 0.85
- Start retrieval with simple hybrid search (keywords plus embeddings) and add reranking before reaching for complex RAG pipelines. Confidence: 0.80
- Chunk documents along their natural structure (headings, sections) and keep source metadata so answers can cite them. Confidence: 0.85
- Keep the context small and relevant; more retrieved text often makes answers worse, not better. Confidence: 0.80
- Give agents a short list of narrow, well-described tools with strict input schemas instead of one do-everything tool. Confidence: 0.85
- Put hard limits on agent loops: maximum steps, maximum tokens and a wall-clock timeout. Confidence: 0.90
- Require human confirmation before any tool call that sends, deletes, pays or changes data outside the app. Confidence: 0.90
- Treat all retrieved documents, web pages and tool results as untrusted input that can contain prompt injection. Confidence: 0.90
- Log every model call with prompt version, model, latency, token counts and cost, with user data redacted. Confidence: 0.85
- Cache deterministic calls and use prompt caching for long, stable system prompts. Confidence: 0.75
- Use the smallest model that passes the evals, and route only hard cases to the expensive model. Confidence: 0.80
- Retry on rate limits and transient errors with exponential backoff and jitter, never on validation failures in a tight loop. Confidence: 0.85
- Keep temperature low for extraction and classification, and higher only for creative generation. Confidence: 0.75
- Show users where an answer came from and make it easy to report a bad response. Confidence: 0.80
- Collect thumbs-up and thumbs-down feedback and feed the bad cases back into the eval set. Confidence: 0.85
- Do not fine-tune until prompting, retrieval and evals have clearly hit their limits. Confidence: 0.70

Written by the prompts.chat (CC0 prompt collection) community (f). Not tested by InnerVault.

How to get it

Setup steps: not applicable.

Related

  1. code-hacker

    Prompts

    Code Hacker - VS Code Custom Agent + Web + TUI

    Stale GitHub, hackerlibs 55 ★MITUpdated 17 days ago

    git clone https://github.com/hackerlibs/code-hacker.git
  2. builder prompts which can be sent to builders like cursor, bolt.diy, bolt.new, trae, project idx, Claude code, lovable.dev, llmacoder, geminicoder, windsurf, deepseek-artifact, cline, aider etc

    Stale GitHub, KingLeoJr 278 ★MITUpdated 2 months ago

    git clone https://github.com/KingLeoJr/awesome-vibe-coding-prompt-code-templates.git
  3. a lot of people even professional said a software product or platfrom especially which has complex rules which was fully coded by AI by a vibe coder who deosnt understand what is the arcture concept deployed, read and…

    Indexed prompts.chat (CC0 prompt collection), hussen.sepa@gmail.com CC0-1.0

  4. # ========================================================== # Universal LLM Operating Guidelines & Karpathy Rules # ========================================================== # VERSION: 1.2.0 # AUTHOR: Scott Malin…

    Indexed prompts.chat (CC0 prompt collection), thanos0000@gmail.com CC0-1.0

  5. <!-- LLM System Prompt Start --> # LLM Skill: Go Industrial Autonomous Business Module Coding Spec (shanjunmei/dig Compile-Time DI) Type: System Prompt / Agent Skill Model Compatible: Doubao / GPT / Claude / Qwen…

    Indexed prompts.chat (CC0 prompt collection), shanjunmei CC0-1.0

  6. --- name: karpathy-guidelines description: Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface…

    Indexed prompts.chat (CC0 prompt collection), yazz4444 CC0-1.0