n\nWhen using structured input, be aware that each LLM family has their own preferences. Claude prefers `` while GPT favors Markdown and JSON. With XML, you can even pre-fill Claude’s responses by providing a `` tag like so.\n\n```\nmessages=[\n {\n \"role\": \"user\",\n \"content\": \"\"\"Extract the , , , and from this product description into your .\n The SmartHome Mini is a compact smart home assistant available in black or white for only $49.99. At just 5 inches wide, it lets you control lights, thermostats, and other connected devices via voice or app—no matter where you place it in your home. This affordable little hub brings convenient hands-free control to your smart devices.\n \"\"\"\n },\n {\n \"role\": \"assistant\",\n \"content\": \"\"\n }\n]\n```\n\n### 1.1.3 Have small prompts that do one thing, and only one thing, well[](https://applied-llms.org/#have-small-prompts-that-do-one-thing-and-only-one-thing-well)\n\nA common anti-pattern / code smell in software is the “[God Object](https://en.wikipedia.org/wiki/God_object)”, where we have a single class or function that does everything. The same applies to prompts too.\n\nA prompt typically starts simple: A few sentences of instruction, a couple of examples, and we’re good to go. But as we try to improve performance and handle more edge cases, complexity creeps in. More instructions. Multi-step reasoning. Dozens of examples. Before we know it, our initially simple prompt is now a 2,000 token Frankenstein. And to add injury to insult, it has worse performance on the more common and straightforward inputs! GoDaddy shared this challenge as their [No. 1 lesson from building with LLMs](https://www.godaddy.com/resources/news/llm-from-the-trenches-10-lessons-learned-operationalizing-models-at-godaddy#h-1-sometimes-one-prompt-isn-t-enough).\n\nJust like how we strive (read: struggle) to keep our systems and code simple, so should we for our prompts. Instead of having a single, catch-all prompt for the meeting transcript summarizer, we can break it into steps:\n\n* Extract key decisions, action items, and owners into structured format\n* Check extracted details against the original transcription for consistency\n* Generate a concise summary from the structured details\n\nAs a result, we’ve split our single prompt into multiple prompts that are each simple, focused, and easy to understand. And by breaking them up, we can now iterate and eval each prompt individually.\n\n### 1.1.4 Craft your context tokens[](https://applied-llms.org/#craft-your-context-tokens)\n\nRethink, and challenge your assumptions about how much context you actually need to send to the agent. Be like Michaelangelo, do not build up your context sculpture—chisel away the superfluous material until the sculpture is revealed. RAG is a popular way to collate all of the potentially relevant blocks of marble, but what are you doing to extract what’s necessary?\n\nWe’ve found that taking the final prompt sent to the model—with all of the context construction, and meta-prompting, and RAG results—putting it on a blank page and just reading it, really helps you rethink your context. We have found redundancy, self-contradictory language, and poor formatting using this method.\n\nThe other key optimization is the structure of your context. If your bag-of-docs representation isn’t helpful for humans, don’t assume it’s any good for agents. Think carefully about how you structure your context to underscore the relationships between parts of it and make extraction as simple as possible.\n\nMore [prompting fundamentals](https://eugeneyan.com/writing/prompting/) such as prompting mental model, prefilling, context placement, etc.\n\n1.2 Information Retrieval / RAG[](https://applied-llms.org/#information-retrieval-rag)\n--------------------------------------------------------------------------------------\n\nBeyond prompting, anothe

What We’ve Learned From A Year of Building with LLMs – Applied LLMs

Podcast Information

Roles

Scripts