Editing and Proofreading Skills

New! We’ve published a new set of automated evaluations and benchmarks for RAG - a critical component of Gen AI used by most successful customers today. Sweet. Retrieval-Augmented Generation lets you take general-purpose foundation models - like those from Anthropic, Meta, and Mistral - and “ground” their responses in specific target areas or domains using information which the models haven’t seen before (maybe confidential, private info, new or real-time data, etc). This lets gen AI apps generate responses which are targeted to that domain with better accuracy, context, reasoning, and depth of knowledge than the model provides off the shelf. In this new paper, we describe a way to evaluate task-specific RAG approaches such that they can be benchmarked and compared against real-world uses, automatically. It’s an entirely novel approach, and one we think will help customers tune and improve their AI apps much more quickly, and efficiently. Driving up accuracy, while driving down the time it takes to build a reliable, coherent system. 🔎 The evaluation is tailored to a particular knowledge domain or subject area. For example, the paper describes tasks related to DevOps troubleshooting, scientific research (ArXiv abstracts), technical Q&A (StackExchange), and financial reporting (SEC filings). 📝 Each task is defined by a specific corpus of documents relevant to that domain. The evaluation questions are generated from and grounded in this corpus. 📊 The evaluation assesses the RAG system's ability to perform specific functions within that domain, such as answering questions, solving problems, or providing relevant information based on the given corpus. 🌎 The tasks are designed to mirror real-world scenarios and questions that might be encountered when using a RAG system in practical applications within that domain. 🔬 Unlike general language model benchmarks, these task-specific evaluations focus on the RAG system's performance in retrieving and applying information from the given corpus to answer domain-specific questions. ✍️ The approach allows for creating evaluations for any task that can be defined by a corpus of relevant documents, making it adaptable to a wide range of specific use cases and industries. Really interesting work from the Amazon science team, and a new totem of evaluation for customers choosing and tuning their RAG systems. Very cool. Paper linked below.

Contextual #RAG is an enhanced version of standard RAG. Contextual RAG adds context to each chunk of information before retrieval. It uses techniques such as contextual embeddings and contextual BM25 (Best Matching 25) to provide chunk-specific explanatory context, improving the accuracy and relevance of the retrieved information. How it works? 1. Preprocessing: → Similar to Standard RAG, but each chunk is augmented with context before embedding and indexing. →Context is generated by analyzing the entire document to provide relevant background information about each chunk. 2. Retrieval: The retrieval process is similar to Standard RAG but leverages the additional context to enhance retrieval accuracy. 3. Reranking: After initial retrieval, a reranking model evaluates and scores the top chunks based on their relevance to the user’s query, selecting the most pertinent chunks for the final prompt. Benefits → Improved accuracy: Reduces retrieval failures significantly by providing necessary context. → Relevance: Enhances the understanding of the chunks, making the retrieved information more relevant to specific queries. → Flexibility: Works with various embedding models and can be tailored for specific domains or use cases. Cons →Complexity: Requires additional preprocessing steps to generate context, potentially increasing implementation effort. → Cost: Although it aims to be cost-effective, the need for context generation and reranking could add to computational expenses, especially with very large knowledge bases. Know more about contextual RAG: https://lnkd.in/gWNnV4iC Here is an in-depth article on different RAG types: https://lnkd.in/gGgaD-jB

Over 80% of users skim, so when a PDP tries to say everything at once, it ends up saying nothing. A cluttered PDP gets more friction than function. Overwhelming users, leading to: - less time spent on page - missing value cues - fewer checkouts A well structured PDP doesn’t overwhelm, rather presents the information in a clear and digestible manner. Encouraging them to take action. In this post, I’ve broken down 12 changes I made to make the PDP easier to read and more focused on what actually helps users purchase. 1. Highlight customer satisfaction upfront. Show how many customers have purchased in the announcement bar. This builds immediate social proof that stays on all your pages. 2. Add benefit-focused badges above the product name. These help shoppers understand what key problems the product solves without needing to read through paragraphs. 3. Keep the title clear, and use a short subtitle to summarise the product and its core benefit. This helps users get both the “what” and the “why” at a glance. 4. Show the number of reviews beside the rating. It adds transparency and makes the rating feel more trustworthy, especially for first-time visitors. 5. Clarify price and pack size early. It saves users from searching for basic details which keeps attention focused on the purchase. 6. Use a context-rich main image. Featuring the product in its real-world use makes it easier to understand what’s being sold and how it fits into everyday life. 7. Expand image thumbnails beyond angles. Include images that show packaging and portion size to help customers evaluate fit and quality. 8. Add 2–3 bullet points above the fold. These help break down the product’s key benefits clearly, making it easier for skimmers to understand what makes it different. 9. Reinforce trust near the Add to Cart section. This is where buying hesitation happens so highlight things like delivery speed, return policies, or support to reduce friction. 10. Use icon-based highlights instead of long descriptions. Visual markers help users absorb information faster and keep the layout clean and scannable. 11. Break down product details visually. Showing ingredient percentages or content breakdowns in a simplified format helps make complex info more digestible. 12. Use accordions (not horizontal tabs). This allows users to expand only what they need, keeping the page organized and improving mobile usability. 13. Bring related variants closer to the decision zone. Show similar options earlier to help customers switch easily without needing to scroll to the bottom. Other UI/UX changes I did – Reduced text density to improve readability – Used consistent icons to simplify scanning – Added color cues for visual balance Found this useful? Let me know in the comments. PS: This checklist helps PDPs be clear and easy to follow without cramming in too much at once. This in turn will help the users make informed decisions that drive action. 

Your RAG pipeline is only as good as what it retrieves. And that’s exactly where most RAG chatbots quietly fail. You’re in a GenAI discussion, and someone asks: “Why does traditional RAG sometimes give confident but wrong answers?” RAG (Retrieval-Augmented Generation) assumes that the retrieved context is relevant and sufficient. But in reality, retrieval can be noisy, incomplete, or just plain wrong. And once bad context enters the pipeline, the LLM doesn’t question it. It just builds on top of it. That’s where Corrective RAG (CRAG) changes the game. What goes wrong in traditional RAG? 📍Retrieval returns low-quality or irrelevant documents 📍No mechanism to validate context before generation 📍LLM blindly trusts retrieved chunks Result → hallucinations with high confidence What CRAG does differently👇 CRAG introduces a correction layer between retrieval and generation. Instead of assuming retrieval is correct, it asks: 👉 “Is this context actually useful?” It does this through: 1. Retrieval Evaluation A lightweight evaluator (often a smaller model) scores the quality of retrieved documents. 2. Conditional Flow If retrieval is good → proceed as usual If retrieval is bad → trigger corrective actions 3. Corrective Actions Re-retrieve using refined queries Perform web search or external lookup Filter out noisy chunks Decompose the query for better context Traditional RAG is retrieve → generate CRAG is retrieve → evaluate → correct → generate #ai #rag #chatbot #retrieval #vectorsearch #aisystems #aiengineering Follow Sneha Vijaykumar for more...😊

🔓 Make Your CV a Magnet for Hiring Managers In today's competitive job market, your CV needs to stand out from the crowd. This can also be said about your LinkedIn profile. 🤔 But how? It's all about strategic layout and presentation. Let's unlock the secrets to impress hiring managers and land that dream interview! ✨ ✅ 1. Clarity is King: Structure: Use clear headings, bullet points, and white space for easy reading. Think scannable, not crammed. Conciseness: Keep it relevant and highlight achievements, not a novel. 3-4 pages max for experienced professionals. Shorter the better! Formatting Consistency: Stick to a professional font (e.g., Arial, Times New Roman) and font size (e.g., 10-12 pt). ✅ 2. Content is Key: Tailor It!: Adapt your CV/profile to each job description, emphasising relevant skills and experience. Quantify Your Impact: Use numbers and metrics to showcase achievements (e.g., "Increased sales by 20%"). Action Verbs: Highlight strong action verbs like "spearheaded," "achieved," or "implemented" to demonstrate initiative. ✅ 3. Presentation Polishes: Proofread, Proofread, Proofread!: Typos and grammatical errors are dealbreakers. Get a second pair of eyes on it. Invest in Visual Appeal: Use professional formatting tools or templates to create a sleek and modern look. PDF Power: Save your CV as a PDF to ensure consistent formatting across devices. 💥 Remember: Your LinkedIn profile and CV represent your personal brand story. Make it compelling, concise, and visually appealing to grab attention and secure that interview! 💡 What are your best CV tips? Share in the comments below #jobsearch #career #CV #resume #linkedin #hiring #tips #advice #interview

Many companies have started experimenting with simple RAG systems, probably as their first use case, to test the effectiveness of generative AI in extracting knowledge from unstructured data like PDFs, text files, and PowerPoint files. If you've used basic RAG architectures with tools like LlamaIndex or LangChain, you might have already encountered three key problems: 𝟭. 𝗜𝗻𝗮𝗱𝗲𝗾𝘂𝗮𝘁𝗲 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 𝗠𝗲𝘁𝗿𝗶𝗰𝘀: Existing metrics fail to catch subtle errors like unsupported claims or hallucinations, making it hard to accurately assess and enhance system performance. 𝟮. 𝗗𝗶𝗳𝗳𝗶𝗰𝘂𝗹𝘁𝘆 𝗛𝗮𝗻𝗱𝗹𝗶𝗻𝗴 𝗖𝗼𝗺𝗽𝗹𝗲𝘅 𝗤𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀: Standard RAG methods often struggle to find and combine information from multiple sources effectively, leading to slower responses and less relevant results. 𝟯. 𝗦𝘁𝗿𝘂𝗴𝗴𝗹𝗶𝗻𝗴 𝘁𝗼 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱 𝗖𝗼𝗻𝘁𝗲𝘅𝘁 𝗮𝗻𝗱 𝗖𝗼𝗻𝗻𝗲𝗰𝘁𝗶𝗼𝗻𝘀: Basic RAG approaches often miss the deeper relationships between information pieces, resulting in incomplete or inaccurate answers that don't fully meet user needs. In this post I will introduce three useful papers to address these gaps: 𝟭. 𝗥𝗔𝗚𝗖𝗵𝗲𝗸𝗲𝗿: introduces a new framework for evaluating RAG systems with a focus on fine-grained, claim-level metrics. It proposes a comprehensive set of metrics: claim-level precision, recall, and F1 score to measure the correctness and completeness of responses; claim recall and context precision to evaluate the effectiveness of the retriever; and faithfulness, noise sensitivity, hallucination rate, self-knowledge reliance, and context utilization to diagnose the generator's performance. Consider using these metrics to help identify errors, enhance accuracy, and reduce hallucinations in generated outputs. 𝟮. 𝗘𝗳𝗳𝗶𝗰𝗶𝗲𝗻𝘁𝗥𝗔𝗚: It uses a labeler and filter mechanism to identify and retain only the most relevant parts of retrieved information, reducing the need for repeated large language model calls. This iterative approach refines search queries efficiently, lowering latency and costs while maintaining high accuracy for complex, multi-hop questions. 𝟯. 𝗚𝗿𝗮𝗽𝗵𝗥𝗔𝗚: By leveraging structured data from knowledge graphs, GraphRAG methods enhance the retrieval process, capturing complex relationships and dependencies between entities that traditional text-based retrieval methods often miss. This approach enables the generation of more precise and context-aware content, making it particularly valuable for applications in domains that require a deep understanding of interconnected data, such as scientific research, legal documentation, and complex question answering. For example, in tasks such as query-focused summarization, GraphRAG demonstrates substantial gains by effectively leveraging graph structures to capture local and global relationships within documents. It's encouraging to see how quickly gaps are identified and improvements are made in the GenAI world.

The most underestimated part of building LLM applications? Evaluation. Evaluation can take up to 80% of your development time (because it’s HARD) Most people obsess over prompts. They tweak models. Tune embeddings. But when it’s time to test whether the whole system actually works? That’s where it breaks. Especially in agentic RAG systems - where you’re orchestrating retrieval, reasoning, memory, tools, and APIs into one seamless flow. Implementation might take a week. Evaluation takes longer. (And it’s what makes or breaks the product.) Let’s clear up a common confusion: 𝗟𝗟𝗠 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻 ≠ 𝗥𝗔𝗚 𝗲𝘃𝗮𝗹𝘂𝗮𝘁𝗶𝗼𝗻. LLM eval tests reasoning in isolation - useful, but incomplete. In production, your model isn’t reasoning in a vacuum. It’s pulling context from a vector DB, reacting to user input, and shaped by memory + tools. That’s why RAG evaluation takes a system-level view. It asks: Did this app respond correctly, given the user input and the retrieved context? Here’s how to break it down: 𝗦𝘁𝗲𝗽 𝟭: 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗲 𝗿𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹. → Are the retrieved docs relevant? Ranked correctly? → Use LLM judges to compute context precision and recall → If ranking matters, compute NDCG, MRR metrics → Visualize embeddings (e.g. UMAP) 𝗦𝘁𝗲𝗽 𝟮: 𝗘𝘃𝗮𝗹𝘂𝗮𝘁𝗲 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝗼𝗻. → Did the LLM ground its answer in the right info? → Use heuristics, LLM-as-a-judge, and contextual scoring. In practice, treat your app as a black box and log: - User query - Retrieved context - Model output - (Optional) Expected output This lets you debug the whole system, not just the model. 𝘏𝘰𝘸 𝘮𝘢𝘯𝘺 𝘴𝘢𝘮𝘱𝘭𝘦𝘴 𝘢𝘳𝘦 𝘦𝘯𝘰𝘶𝘨𝘩? 5–10? Too few. 30–50? Good start. 400+? Now you’re capturing real patterns and edge cases. Still, start with how many samples you have available, and keep expanding your evaluation split. It’s better to have an imperfect evaluation layer than nothing. Also track latency, cost, throughput, and business metrics (like conversion or retention). Some battle-tested tools: → RAGAS (retrieval-grounding alignment) → ARES (factual grounding) → Opik by Comet (end-to-end open-source eval + monitoring) → Langsmith, Langfuse, Phoenix (observability + tracing) TL;DR: Agentic systems are complex. Success = making evaluation part of your design from Day 0. We unpack this in full in Lesson 5 of the PhiloAgents course. 🔗 Check it out here: https://lnkd.in/dA465E_J

Research-backed accessible text checklist (beyond color & fonts) 1️⃣ Avoid ALL CAPS for long text Reading all caps slows people down by up to 10–20% because we recognize word shapes, not just letters. Uppercase removes those shapes, forcing letter-by-letter reading: https://lnkd.in/e7tCHxUD 👉 Keep all caps for short labels or acronyms only. 2️⃣ Keep an optimal line length Long lines make it hard for the eye to jump to the next line, while very short lines break reading rhythm. Based on classic readability research by Emil Ruder and later UX studies: https://lnkd.in/eJsTZT3w 👉 Aim for ~45–75 characters per line for comfortable reading. 3️⃣ Use generous line height Dense text increases cognitive load and reduces comprehension, especially for users with dyslexia. Recommended in Web Content Accessibility Guidelines (1.4.12 Text Spacing): https://lnkd.in/eam2Uqs5 👉 Use at least 1.4–1.6 line height for body text. 4️⃣ Don’t squeeze letters together Tight letter spacing makes words harder to parse, especially for users with visual or cognitive impairments. Supported by research from British Dyslexia Association: https://lnkd.in/eKc_2HPr 👉 Slightly increasing spacing (e.g., ~0.02–0.05em) can improve readability. 5️⃣ Avoid justified text blocks Perfectly aligned edges may look clean, but they create irregular spacing (“rivers of white”) that disrupt reading flow. 👉 Prefer left-aligned text for most content. 6️⃣ Give paragraphs room to breathe Large text blocks discourage reading and increase cognitive effort. 👉 Use spacing between paragraphs and keep them short (3–5 lines max). 7️⃣ Design for zoom and scaling Users should be able to zoom up to 200% without losing content or readability. 👉 Fixed heights and cramped layouts often break here. 8️⃣ Support scanning, not just reading Most users don’t read - they scan. Structured text helps them find what they need faster. Eye-tracking studies by Jakob Nielsen show “F-shaped” reading patterns: https://lnkd.in/etWrYsM7 👉 Use headings, lists, and clear content chunks. 9️⃣ Be careful with width and layout Very wide text blocks reduce focus, while overly narrow ones feel fragmented. 👉 Balance layout to guide the eye naturally across content. Small changes in spacing and structure can significantly improve comprehension, speed, and user comfort. What’s one text rule you wish more designers followed? #Accessibility #WebAccessibility #UX #InclusiveDesign #Readability

💡4 strategies for optimizing text content for better readability For most products, written language makes up about 95% of the content — which means making text readable is vital if you want to offer a great user experience. 1️⃣ Content layout & structure ✔ Use headings (H1, H2, and H3) to create individual sections and guide readers through them. ✔ Write short sentences: Aim for 15-20 words per sentence. ✔ Use bullet points & numbered lists: Bullet lists both help improve scannability and highlight key points. ✔ Add callouts/quotes: Use them to emphasize critical information. 2️⃣ Optimal character count per line Too long lines make it difficult to track lines, causing fatigue and reducing comprehension.  Too short lines force frequent line breaks, disrupting reading flow and causing frustration. ✔ 40-60 characters per line (CPL), including spaces, is generally ideal. ✔ Shorter lines (20-40 CPL) are preferable for mobile devices and narrow screens. ✔ Longer lines (75-100 CPL) can work for wide displays but may reduce readability. 3️⃣ Content flow  ✔ Use inverted pyramid style: Place the most important information at the top to maximize the chance users will see it.  ✔ Utilise common content scanning patterns (F-shape, Z-shape, Spotted): https://lnkd.in/dnAQ3aqF  ✔ First sentences of paragraphs should summarize the main point or create context. ✔ Ensure smooth transitions between sections and ideas. Individual sections should always feel like parts of a whole rather than a collection of individual pieces of information.  ✔ Write short paragraphs: Limit paragraphs to 3-4 sentences to prevent overwhelming readers. ✔ Break up text with relevant visuals. Paired with a good layout structure, it will help you avoid walls of text 4️⃣ Font & formatting ✔ Choose readable fonts: Choose sans-serif fonts for body text. Fonts like Open Sans or Roboto are easier to read on screens. ✔ Use 16px or larger for body text to improve legibility ✔ Align type to the baseline grid (i.e., 8px) ✔ Choose line height proportional to type size. Use 1.5x line spacing for web content to give text room to breathe. ✔ Keep paragraph spacing in the range between .75x and 1.25x of the type size. 🛠️ Tools to Improve Readability ✔ Hemingway Editor Check for complexity and highlight long sentences. https://hemingwayapp.com/ ✔ Readability Score Checkers Aim for a Flesch-Kincaid score that suits your audience (8th grade or lower for general audiences). https://lnkd.in/dzQijnYw 🖼️ Line length and text readability by Google (Material Design) #UI #uidesign #productdesign #design #uxdesign

Your forms look beautiful... so why are 70% of users abandoning them? The average cart abandonment rate sits at 70.19%—and poor form design is one of the biggest culprits. And here's why: 🔸 Reduced cognitive friction Every horizontal shift adds a small mental tax that disrupts user flow. Eye-tracking research from Nielsen Norman Group shows most users scan top-to-bottom before reading side-to-side (i.e. the F-pattern). Single columns remove these directional changes, keeping cognition in one linear track. 🔸 15.4 seconds faster completion A CXL usability study found single-column forms are completed 15.4s faster than multi-column layouts. One clear path means less scanning—and higher throughput. 🔸 Built-in accessibility Accessibility isn’t just compliance—it’s flow. Screen readers and keyboards follow source order (top-to-bottom). Multi-column forms require ARIA landmarks, custom DOM mapping, and tab management—each a fail point. WebAIM’s Screen Reader Survey from 2023 indicated that complex, multi-column forms are among users’ top pain points. A single, linear structure eliminates confusion for everyone—screen reader, keyboard, or sighted. 🔸 Mobile-first by default Two columns collapse poorly on smaller screens, breaking alignment and increasing error rates. Vertical layouts scale seamlessly across all devices. 🔸 Perceived simplicity The Manifest found that 27% of users abandon forms they perceive as “too long.” Single-column layouts look shorter—reducing overwhelm, even when the total fields stay the same. The best form design is invisible. When users don’t have to think—they finish. 👉 On a scale of 1–10: How optimized are your forms? #uxdesign #webdesign #accessibility #productdesign ⸻ 👋🏼 Hi, I’m Dane—your source for UX & web design insights. ❤️ Was this helpful? A 👍🏼 would be thuper kewl. 🔄 Share to help others (or for easy access later). ➕ Follow for more like this in your feed every day.