Automating Repetitive Tasks with LLMs

LLMs are the single fastest way to make yourself indispensable and give your team a 30‑percent productivity lift. Here is the playbook. Build a personal use‑case portfolio Write down every recurring task you handle for clients or leaders: competitive intelligence searches, slide creation, meeting notes, spreadsheet error checks, first‑draft emails. Rank each task by time cost and by the impact of getting it right. Start automating the items that score high on both. Use a five‑part prompt template Role, goal, context, constraints, output format. Example: “You are a procurement analyst. Goal: draft a one‑page cost‑takeout plan. Context: we spend 2.7 million dollars on cloud services across three vendors. Constraint: plain language, one paragraph max. Output: executive‑ready paragraph followed by a five‑row table.” Break big work into a chain of steps Ask first for an outline, then for section drafts, then for a fact‑check. Steering at each checkpoint slashes hallucinations and keeps the job on‑track. Blend the model with your existing tools Paste the draft into Excel and let the model write formulas, then pivot. Drop a JSON answer straight into Power BI. Send the polished paragraph into PowerPoint. The goal is a finished asset, not just a wall of text. Feed the model your secret sauce Provide redacted samples of winning proposals, your slide master, and your company style guide. The model starts producing work that matches your tone and formatting in minutes. Measure the gain and tell the story Track minutes saved per task, revision cycles avoided, and client feedback. Show your manager that a former one‑hour job now takes fifteen minutes and needs one rewrite instead of three. Data beats anecdotes. Teach the team Run a ten‑minute demo in your weekly stand‑up. Share your best prompts in a Teams channel. Encourage colleagues to post successes and blockers. When the whole team levels up, you become known as the catalyst, not the cost‑cutting target. If every person on your team gained back one full day each week, what breakthrough innovation would you finally have the bandwidth to launch? What cost savings could you achieve? What additional market share could you gain?

Building useful Knowledge Graphs will long be a Humans + AI endeavor. A recent paper lays out how best to implement automation, the specific human roles, and how these are combined. The paper, "From human experts to machines: An LLM supported approach to ontology and knowledge graph construction", provides clear lessons. These include: 🔍 Automate KG construction with targeted human oversight: Use LLMs to automate repetitive tasks like entity extraction and relationship mapping. Human experts should step in at two key points: early, to define scope and competency questions (CQs), and later, to review and fine-tune LLM outputs, focusing on complex areas where LLMs may misinterpret data. Combining automation with human-in-the-loop ensures accuracy while saving time. ❓ Guide ontology development with well-crafted Competency Questions (CQs): CQs define what the Knowledge Graph (KG) must answer, like "What preprocessing techniques were used?" Experts should create CQs to ensure domain relevance, and review LLM-generated CQs for completeness. Once validated, these CQs guide the ontology’s structure, reducing errors in later stages. 🧑⚖️ Use LLMs to evaluate outputs, with humans as quality gatekeepers: LLMs can assess KG accuracy by comparing answers to ground truth data, with humans reviewing outputs that score below a set threshold (e.g., 6/10). This setup allows LLMs to handle initial quality control while humans focus only on edge cases, improving efficiency and ensuring quality. 🌱 Leverage reusable ontologies and refine with human expertise: Start by using pre-built ontologies like PROV-O to structure the KG, then refine it with domain-specific details. Humans should guide this refinement process, ensuring that the KG remains accurate and relevant to the domain’s nuances, particularly in specialized terms and relationships. ⚙️ Optimize prompt engineering with iterative feedback: Prompts for LLMs should be carefully structured, starting simple and iterating based on feedback. Use in-context examples to reduce variability and improve consistency. Human experts should refine these prompts to ensure they lead to accurate entity and relationship extraction, combining automation with expert oversight for best results. These provide solid foundations to optimally applying human and machine capabilities to the very-important task of building robust and useful ontologies.

I've been using AI coding tools for a while now & it feels like every 3 months the paradigm shifts. Anyone remember putting "You are an elite software engineer..." at the beginning of your prompts or manually providing context? The latest paradigm is Agent Driven Development & here are some tips that have helped me get good at taming LLMs to generate high quality code. 1. Clear & focused prompting ❌ "Add some animations to make the UI super sleek" ✅ "Add smooth fade-in & fade out animations to the modal dialog using the motion library" Regardless of what you ask, the LLM will try to be helpful. The less it has to infer, the better your result will be. 2. Keep it simple stupid ❌ Add a new page to manage user settings, also replace the footer menu from the bottom of the page to the sidebar, right now endless scrolling is making it unreachable & also ensure the mobile view works, right now there is weird overlap ✅ Add a new page to manage user settings, ensure only editable settings can be changed. Trying to have the LLM do too many things at once is a recipe for bad code generation. One-shotting multiple tasks has a higher chance of introducing bad code. 3. Don't argue ❌ No, that's not what I wanted, I need it to use the std library, not this random package, this is the 4th time you've failed me! ✅ Instead of using package xyz, can you recreate the functionality using the standard library When the LLM fails to provide high quality code, the problem is most likely the prompt. If the initial prompt is not good, follow on prompts will just make a bigger mess. I will usually allow one follow up to try to get back on track & if it's still off base, I will undo all the changes & start over. It may seem counterintuitive, but it will save you a ton of time overall. 4. Embrace agentic coding AI coding assistants have a ton of access to different tools, can do a ton of reasoning on their own, & don't require nearly as much hand holding. You may feel like a babysitter instead of a programmer. Your role as a dev becomes much more fun when you can focus on the bigger picture and let the AI take the reigns writing the code. 5. Verify With this new ADD paradigm, a single prompt may result in many files being edited. Verify that the code generated is what you actually want. Many AI tools will now auto run tests to ensure that the code they generated is good. 6. Send options, thx I had a boss that would always ask for multiple options & often email saying "send options, thx". With agentic coding, it's easy to ask for multiple implementations of the same feature. Whether it's UI or data models asking for a 2nd or 10th opinion can spark new ideas on how to tackle the task at hand & a opportunity to learn. 7. Have fun I love coding, been doing it since I was 10. I've done OOP & functional programming, SQL & NoSQL, PHP, Go, Rust & I've never had more fun or been more creative than coding with AI. Coding is evolving, have fun & let's ship some crazy stuff!

Focusing on AI’s hype might cost your company millions… (Here’s what you’re overlooking) Every week, new AI tools grab attention—whether it’s copilot assistants or image generators. While helpful, these often overshadow the true economic driver for most companies: AI automation. AI automation uses LLM-powered solutions to handle tedious, knowledge-rich back-office tasks that drain resources. It may not be as eye-catching as image or video generation, but it’s where real enterprise value will be created in the near term. Consider ChatGPT: at its core, there is a large language model (LLM) like GPT-3 or GPT-4, designed to be a helpful assistant. However, these same models can be fine-tuned to perform a variety of tasks, from translating text to routing emails, extracting data, and more. The key is their versatility. By leveraging custom LLMs for complex automations, you unlock possibilities that weren’t possible before. Tasks like looking up information, routing data, extracting insights, and answering basic questions can all be automated using LLMs, freeing up employees and generating ROI on your GenAI investment. Starting with internal process automation is a smart way to build AI capabilities, resolve issues, and track ROI before external deployment. As infrastructure becomes easier to manage and costs decrease, the potential for AI automation continues to grow. For business leaders, identifying bottlenecks that are tedious for employees and prone to errors is the first step. Then, apply LLMs and AI solutions to streamline these operations. Remember, LLMs go beyond text—they can be used in voice, image recognition, and more. For example, Ushur is using LLMs to extract information from medical documents and feed it into backend systems efficiently—a task that was historically difficult for traditional AI systems. (Link in comments) In closing, while flashy AI demos capture attention, real productivity gains come from automating tedious tasks. This is a straightforward way to see returns on your GenAI investment and justify it to your executive team.

I spent the weekend testing Claude’s new Skills framework, and it might just be the missing link between prompt-engineering and an agent infrastructure. For those who haven’t tried it yet - Skills are basically persistent instructions/code/resources that Claude can load when it needs them. Once you install a Skill, Claude just knows how to do that thing across all your conversations. 𝗛𝗲𝗿𝗲'𝘀 𝘄𝗵𝘆 𝘁𝗵𝗶𝘀 𝗳𝗲𝗮𝘁𝘂𝗿𝗲 𝗺𝗮𝘁𝘁𝗲𝗿𝘀: Claude Skills take everything complex about MCP: protocol layers, context bloat, and host-client gymnastics, and compress it into something beautifully minimalist: a folder, a Markdown file, and maybe a helper script. It’s elegant because it works with what LLMs already do best: read, reason, and infer from text, no manual orchestration required. 𝗧𝗵𝗲 𝗮𝗿𝗰𝗵𝗶𝘁𝗲𝗰𝘁𝘂𝗿𝗲 𝗶𝘀 𝗰𝗹𝗲𝗮𝗻: SKILL.md = The “how”: your procedures and reasoning. References/ = Context and documentation that guide decisions. Assets/ = Files or templates used in outputs. Scripts/ = Code for deterministic actions when text isn’t enough. This design externalizes organizational knowledge. MCP tried to make LLMs network-aware; Skills make them work-aware. They capture how your team operates, not just what it knows, in composable, shareable snippets. Think of it as institutional memory that’s machine-readable and token-efficient. 𝗧𝗵𝗲 𝗶𝗺𝗽𝗹𝗶𝗰𝗮𝘁𝗶𝗼𝗻: We’ve had “LLM automations” before: Custom GPTs, Copilot Agents, and Gems, but they force you to manage the power they give you manually. Every time you want to use one, you have to name it, remember what it does, and tell the model which one to apply. Claude Skills remove that maintenance layer. They sit quietly in the background until a task calls for them. When you ask Claude to do something that matches a Skill’s purpose, it loads that folder automatically, bringing in just the right context and tools. You stop remembering what to use and start orchestrating workflows that happen naturally. 𝗣𝗿𝗮𝗰𝘁𝗶𝗰𝗮𝗹 𝗮𝗰𝘁𝗶𝗼𝗻 𝗳𝗼𝗿 𝗯𝘂𝗶𝗹𝗱𝗲𝗿𝘀: Start by writing one simple Skill for your workflow, like a LinkedIn_Growth_Engine – a Skill that drafts, formats, and schedules your weekly LinkedIn content. It reads your brand tone from a reference file, uses recent post analytics to refine hooks, and pulls fresh insights from saved articles or PDFs. One command: consistent, on-brand content that sounds like you every time. The bigger picture? This is how we move from AI tools to AI teammates, where knowledge lives beside the model, not inside the prompt.

Will LLMs control Computers in the future? Yes, a new Case Study with Anthropic Claude 3.5 suggests a promising future where LLMs can control computers via a GUI using textual and visual inputs to generate actions. 👀 Computer Use: In Computer Use, the LLM receives instructions and screenshots of the computer interface. It analyzes the screenshot to understand the interface and simulates human actions such as moving the cursor, clicking buttons, and typing text to execute the desired operations. This is repeated until the task is completed or further user input is required. Case Study Tests 1️⃣ Web Search: Navigate websites, search for items, and add to cart based on specific criteria. 2️⃣ Productivity Tasks: Document processing, spreadsheet manipulation, and document editing. 3️⃣ Workflow Management: Handle file operations and system navigation, Installation of Apps 4️⃣ Entertainment/Gaming: Interactions and playing of video games like Hearthstone. Insights 💡 LLMs like Claude will be able to automate complex tasks, increasing productivity using existing GUI 🥇Claude already solves 16 from 20 test cases. 📈 Better Planning Errors (PE), Action Errors (AE), and Critic Errors (CE) required for production use 🖥️ Performance is influenced by screen resolution (800x600 for Claude) ⚠️ Struggles with human-like behaviors such as natural scrolling and browsing 📝 Released the test cases and code on GitHub to reproduce 🆕 We need new datasets that reflect real-world complexities and are multimodal Paper: https://lnkd.in/eR2YVC2J Github: https://lnkd.in/eA5-9CUm I am eagerly waiting for the first open datasets to replicate compute use capabilities! 👀

Most companies overcomplicate AI implementation. I see teams making the same mistakes: jumping to complex AI solutions (agents, toolchains, orchestration) when all they need is a simple prompt. This creates bloated systems, wastes time, and becomes a maintenance nightmare. While everyone's discussing Model Context Protocol, I've been exploring another MCP: the Minimum Complexity Protocol. The framework forces teams to start simple and only escalate when necessary: Level 1: Non-LLM Solution → Would a boolean, logic or rule based system solve the problem more efficiently? Level 2: Single LLM Prompt → Start with a single, straightforward prompt to a general purpose model. Experiment with different models - some are better with particular tasks. Level 3: Preprocess Data → Preprocess your inputs. Split long documents, simplify payloads. Level 4: Divide & Conquer → Break complex tasks into multiple focused prompts where each handles one specific aspect. LLMs are usually better at handling a specific task at a time. Level 5: Few Shot Prompting → Add few-shot examples within your prompt to guide the model toward better outputs. A small number of examples can greatly increase accuracy. Level 6: Prompt Chaining → Connect multiple prompts in a predetermined sequence. The output of one prompt becomes the input for the next. Level 7: Resource Injection → Implement RAG to connect your model to relevant external knowledge bases such as APIs, databases and vector stores. Level 8: Fine Tuning → Fine tune existing models on your domain specific data when other techniques are no longer effective. Level 9 (Optional): Build Your Own Model → All else fails? Develop custom models when the business case strongly justifies the investment. Level 10: Agentic Tool Selection → LLMs determine which tools or processes to execute for a given job. The tools can recursively utilise more LLMs while accessing and updating resources. Human oversight is still recommended here. Level 11: Full Agency → Allow agents to make decisions, call tools, and access resources independently. Agents self-evaluate accuracy and iteratively operate until the goal is completed. At each level, measure accuracy via evals and establish human review protocols. The secret to successful AI implementation isn't using the most advanced technique. It's using the simplest solution that delivers the highest accuracy with the least effort. What's your experience? Are you seeing teams overcomplicate their AI implementations?

Can large language models make Data Scientists more productive? I've been experimenting lately with large language models (LLMs) for #datascience and wanted to share some thoughts on how they can support a Data Scientist's day-to-day work: 🚀 Literature Review - LLMs can quickly summarise, synthesise and extract key insights from lots of research papers. This helps Data Scientists stay on top of the state-of-the-art algorithms, techniques or datasets. 🧠 Code Generation - LLMs can generate viable code to explore, clean, process and model data. This significantly speeds up what's usually a manual, trial and error process. 💡 Code Explanation - LLMs can automatically add comments explaining what each section of code is doing in plain language. This is invaluable when documenting code or understanding inherited codebase! 🛠️ Code Refactoring - LLMs can inspect code to suggest improvements in structure, efficiency and style. This allows Data Scientists to improve and optimise their code. ⚙️ Task Automation - LLMs can automate repetitive coding tasks like data loading, cleaning, processing, etc. by turning them into functions and scripts. This frees up Data Scientists to focus on value-add activities. 📃 Report Generation - LLMs can generate data analysis reports, documentation and even README files. Say goodbye to mundane and time-consuming documentation tasks! 📊 Results Presentation - LLMs can create stories to convey results and insights to different audiences. LLMs can also provide independent, critical opinion of Data Scientists’ content. The key takeaway? LLMs have considerable potential to enable Data Scientists to be more productive, insightful and impactful. However, Data Scientists shouldn’t blindly follow outputs from LLMs. Instead, Data Scientist should view LLMs as assistants that can augment intelligence, rather than replace it. What are your thoughts on how LLMs can best support Data Scientists? Please let me know in the comments below. #ai #llm #augmentedintelligence #productivity Disclaimer: The opinions expressed in this post are my own and do not represent the views of my employer.