Best Practices for Iterating on AI Innovations

I think AI agentic workflows will drive massive AI progress this year — perhaps even more than the next generation of foundation models. This is an important trend, and I urge everyone who works in AI to pay attention to it. Today, we mostly use LLMs in zero-shot mode, prompting a model to generate final output token by token without revising its work. This is akin to asking someone to compose an essay from start to finish, typing straight through with no backspacing allowed, and expecting a high-quality result. Despite the difficulty, LLMs do amazingly well at this task! With an agentic workflow, however, we can ask the LLM to iterate over a document many times. For example, it might take a sequence of steps such as: - Plan an outline. - Decide what, if any, web searches are needed to gather more information. - Write a first draft. - Read over the first draft to spot unjustified arguments or extraneous information. - Revise the draft taking into account any weaknesses spotted. - And so on. This iterative process is critical for most human writers to write good text. With AI, such an iterative workflow yields much better results than writing in a single pass. Devin’s splashy demo recently received a lot of social media buzz. My team has been closely following the evolution of AI that writes code. We analyzed results from a number of research teams, focusing on an algorithm’s ability to do well on the widely used HumanEval coding benchmark. You can see our findings in the diagram below. GPT-3.5 (zero shot) was 48.1% correct. GPT-4 (zero shot) does better at 67.0%. However, the improvement from GPT-3.5 to GPT-4 is dwarfed by incorporating an iterative agent workflow. Indeed, wrapped in an agent loop, GPT-3.5 achieves up to 95.1%. Open source agent tools and the academic literature on agents are proliferating, making this an exciting time but also a confusing one. To help put this work into perspective, I’d like to share a framework for categorizing design patterns for building agents. My team AI Fund is successfully using these patterns in many applications, and I hope you find them useful. - Reflection: The LLM examines its own work to come up with ways to improve it. - Tool use: The LLM is given tools such as web search, code execution, or any other function to help it gather information, take action, or process data. - Planning: The LLM comes up with, and executes, a multistep plan to achieve a goal (for example, writing an outline for an essay, then doing online research, then writing a draft, and so on). - Multi-agent collaboration: More than one AI agent work together, splitting up tasks and discussing and debating ideas, to come up with better solutions than a single agent would. I’ll elaborate on these design patterns and offer suggested readings for each next week. [Original text: https://lnkd.in/gSFBby4q ]

In the world of Generative AI, 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹-𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗲𝗱 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻 (𝗥𝗔𝗚) is a game-changer. By combining the capabilities of LLMs with domain-specific knowledge retrieval, RAG enables smarter, more relevant AI-driven solutions. But to truly leverage its potential, we must follow some essential 𝗯𝗲𝘀𝘁 𝗽𝗿𝗮𝗰𝘁𝗶𝗰𝗲𝘀: 1️⃣ 𝗦𝘁𝗮𝗿𝘁 𝘄𝗶𝘁𝗵 𝗮 𝗖𝗹𝗲𝗮𝗿 𝗨𝘀𝗲 𝗖𝗮𝘀𝗲 Define your problem statement. Whether it’s building intelligent chatbots, document summarization, or customer support systems, clarity on the goal ensures efficient implementation. 2️⃣ 𝗖𝗵𝗼𝗼𝘀𝗲 𝘁𝗵𝗲 𝗥𝗶𝗴𝗵𝘁 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗕𝗮𝘀𝗲 - Ensure your knowledge base is 𝗵𝗶𝗴𝗵-𝗾𝘂𝗮𝗹𝗶𝘁𝘆, 𝘀𝘁𝗿𝘂𝗰𝘁𝘂𝗿𝗲𝗱, 𝗮𝗻𝗱 𝘂𝗽-𝘁𝗼-𝗱𝗮𝘁𝗲. - Use vector embeddings (e.g., pgvector in PostgreSQL) to represent your data for efficient similarity search. 3️⃣ 𝗢𝗽𝘁𝗶𝗺𝗶𝘇𝗲 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 𝗠𝗲𝗰𝗵𝗮𝗻𝗶𝘀𝗺𝘀 - Use hybrid search techniques (semantic + keyword search) for better precision. - Tools like 𝗽𝗴𝗔𝗜, 𝗪𝗲𝗮𝘃𝗶𝗮𝘁𝗲, or 𝗣𝗶𝗻𝗲𝗰𝗼𝗻𝗲 can enhance retrieval speed and accuracy. 4️⃣ 𝗙𝗶𝗻𝗲-𝗧𝘂𝗻𝗲 𝗬𝗼𝘂𝗿 𝗟𝗟𝗠 (𝗢𝗽𝘁𝗶𝗼𝗻𝗮𝗹) - If your use case demands it, fine-tune the LLM on your domain-specific data for improved contextual understanding. 5️⃣ 𝗘𝗻𝘀𝘂𝗿𝗲 𝗦𝗰𝗮𝗹𝗮𝗯𝗶𝗹𝗶𝘁𝘆 - Architect your solution to scale. Use caching, indexing, and distributed architectures to handle growing data and user demands. 6️⃣ 𝗠𝗼𝗻𝗶𝘁𝗼𝗿 𝗮𝗻𝗱 𝗜𝘁𝗲𝗿𝗮𝘁𝗲 - Continuously monitor performance using metrics like retrieval accuracy, response time, and user satisfaction. - Incorporate feedback loops to refine your knowledge base and model performance. 7️⃣ 𝗦𝘁𝗮𝘆 𝗦𝗲𝗰𝘂𝗿𝗲 𝗮𝗻𝗱 𝗖𝗼𝗺𝗽𝗹𝗶𝗮𝗻𝘁 - Handle sensitive data responsibly with encryption and access controls. - Ensure compliance with industry standards (e.g., GDPR, HIPAA). With the right practices, you can unlock its full potential to build powerful, domain-specific AI applications. What are your top tips or challenges?

The biggest bottleneck in building a great AI product is iteration speed. And the biggest drag on iteration speed? Generic, off-the-shelf annotation tools. Many teams default to these tools because it seems like the path of least resistance. Counterintuitively, It's often path of most friction. Every second a reviewer spends fighting a clunky UI, switching contexts to find necessary data, or trying to interpret a generic data dump grinds progress to a halt. This is why we often advise teams to build their own custom annotation tools. It's the single most impactful investment you can make in your AI evaluation workflow. I've seen teams that do this iterate up to 10x faster. Why? Two main reasons: 1. Frictionless Review = Exponential Gains: A custom tool is designed for your specific workflow. You can add keyboard shortcuts for common actions, custom filters for your metadata, and bring all the context a reviewer needs from multiple systems into one screen. A tiny reduction in friction for a single review, multiplied by hundreds or thousands of reviews, translates into a massive increase in the volume and quality of feedback you can process. 2. Domain-Specific Rendering: A custom interface lets you render data in a way that's intuitive for the domain. Evaluating AI-generated emails? Render them to look like emails. Reviewing code output? Use syntax highlighting. Assessing a RAG system for medical content? Display the retrieved sources alongside the generated summary in a clear, readable format. When you present data in a product-specific way, your reviewers can give you higher-quality feedback, faster. Below is a screenshot of a custom annotation app one of our students, Christopher Lovejoy, MD built for a medical use case. This is just one of the high-leverage strategies we teach in our AI Evals for Engineers & PMs course. For those interested in the full evaluation toolkit - from error analysis to production monitoring. Get 35% off with code evals-info-url. Next cohort kicks off Oct 6: https://bit.ly/4nahFmu