Tasks That Code Interpreters can Automate

As Business Analysts, we often juggle between requirement documentation, stakeholder communication, backlog refinement, UAT coordination, and reporting — all within tight timelines. But here's the game-changer 👉 AI isn’t just a buzzword — it’s your new assistant. Let’s break down how BAs can automate their work practically using AI tools, and even create their own custom tools without being a coder. 🚀 ✅ Automate Requirement Documentation Problem: Writing BRDs, user stories, acceptance criteria takes time. AI Tool Solution: Use ChatGPT or Notion AI to convert meeting transcripts or stakeholder notes into structured: Business Requirements User Stories (with Given-When-Then format) Acceptance Criteria Example: Upload a Zoom transcript → Prompt ChatGPT: “Convert this into Epics and User Stories with ACs” → Done in minutes. ✅ Automate Meeting Summaries and Action Items Tool: Fireflies.ai or Otter.ai Use Case: After a JAD session or backlog grooming call, these tools auto-generate: Meeting summary Action items by participant Follow-ups and decisions Value: Saves hours of note-making and improves traceability. ✅ AI-Powered Backlog Refinement Tool: Jira + GPT Plugin or ChatGPT Example: You have 50 user stories written by a junior BA. Prompt: “Review these stories and rewrite them in INVEST format with proper ACs.” You get feedback instantly and ensure quality in your backlog. ✅ Automate SQL Query Generation Tool: Text2SQL tools like AskYourDatabase, AI2sql, or ChatGPT Code Interpreter Use Case: Prompt: “Give me SQL to fetch customers who made more than 3 transactions in last month.” AI writes the query in seconds — especially helpful if you’re not a SQL expert. ✅ AI-Based Wireframe & Workflow Generation Tool: Uizard, Visily, Figma + GPT plugins Use Case: Type in: “Design a mobile screen for loan application with fields for name, income, loan amount.” AI generates a wireframe instantly, saving design iterations with the UX team. ✅ Custom AI Agents for Business Analysis Tasks You can now create your own AI Agents without coding, tailored to your workflow. Tools to Build: Flowise (visual agent builder) Zapier AI Agents Microsoft Power Automate + Azure OpenAI Custom GPTs from ChatGPT Pro Examples of Custom BA Agents: A “StoryRefiner Bot” that takes raw notes and outputs refined user stories. A “Glossary Builder” that extracts and defines domain terms from BRDs. A “UAT Tracker Agent” that tracks test cases, identifies blockers, and notifies testers. You define the prompts, logic, and inputs. These agents work in your workflow, 24/7. ✅ Automate KPI Reporting and Dashboards Tool: Power BI + Copilot, Tableau GPT Use Case: Ask: “Show me monthly trends for user adoption split by geography.” It dynamically generates the charts and gives insights with natural language prompts. Create your own AI Agent through this guide: https://lnkd.in/eb8t2Ye3 https://topmate.io/diwakar BA Helpline

𝗜𝗳 𝘆𝗼𝘂’𝗿𝗲 𝗱𝗼𝗶𝗻𝗴 𝘀𝗼𝗺𝗲𝘁𝗵𝗶𝗻𝗴 𝗺𝗼𝗿𝗲 𝘁𝗵𝗮𝗻 𝘁𝗵𝗿𝗲𝗲 𝘁𝗶𝗺𝗲𝘀, 𝗼𝗿 𝗶𝘁 𝘁𝗮𝗸𝗲𝘀 𝗺𝗼𝗿𝗲 𝘁𝗵𝗮𝗻 𝘁𝘄𝗼 𝗵𝗼𝘂𝗿𝘀 — 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗶𝘁. That’s the mantra we’ve adopted for product managers at Databricks. ⚙️ 𝗔𝘂𝘁𝗼𝗺𝗮𝘁𝗲 𝗬𝗼𝘂𝗿𝘀𝗲𝗹𝗳: 𝗛𝗼𝘄 𝗣𝗠𝘀 𝟭𝟬× 𝗧𝗵𝗲𝗶𝗿 𝗣𝗿𝗼𝗱𝘂𝗰𝘁𝗶𝘃𝗶𝘁𝘆 Product managers have always been system thinkers. We design not only products, but also the processes that bring them to life — how we discover, synthesize, and act on truth. At Databricks, we’ve built strong systems for 𝗵𝘆𝗽𝗼𝘁𝗵𝗲𝘀𝗶𝘀-𝗱𝗿𝗶𝘃𝗲𝗻 𝗱𝗶𝘀𝗰𝗼𝘃𝗲𝗿𝘆 and 𝗳𝗶𝗿𝘀𝘁-𝗽𝗿𝗶𝗻𝗰𝗶𝗽𝗹𝗲𝘀 𝘁𝗵𝗶𝗻𝗸𝗶𝗻𝗴. But there’s another layer of the job that can be surprisingly time-consuming: • Coordinating customer outreach for discovery • Polishing and sharing customer notes • Synthesizing insights into reports • Filing bugs from interviews • Tracking growth and churn • Sending weekly business updates • The day-to-day operations of running the business behind the product. Since our Vibe Coding Bootcamp, PMs across Databricks have started using Claude Code and Cursor to automate these tasks — to literally 10× themselves. Here are two of my favorite examples 👇 1️⃣ 𝗖𝘂𝘀𝘁𝗼𝗺𝗲𝗿 𝗖𝗮𝗹𝗹 “𝗢𝗦” PMs used to spend 7–10 hours a week tracking growth and churn, emailing account teams, collecting notes, and writing reports. Now, with vibe-coded automations, PMs have built systems that: • Runs SQL queries to surface top growth/churn accounts • Emails account teams automatically with personalized summaries and charts • Rewrites customer notes in a consistent format • Consolidates bi-weekly reports (all with human review before send-off) • ⏱ Result: 1.5 hours of effort per week instead of 10+. 2️⃣ 𝗨𝘀𝗲𝗿 𝗝𝗼𝘂𝗿𝗻𝗲𝘆 𝗔𝘂𝗱𝗶𝘁𝘀 & 𝗕𝘂𝗴 𝗕𝗮𝘀𝗵𝗲𝘀 PMs built vibe-coded Playwright scripts to simulate users completing tasks with our docs. • These automations flag broken steps, missing links, and confusing flows — even propose doc fixes automatically. • ⏱ Result: We can now measure how easy (or painful) our UX/docs really are, continuously. The results go beyond efficiency. By automating the repetitive work, PMs spend more time thinking strategically — and, interestingly, they’re generating better insights too. At Databricks, PMs don’t just manage products...they design the systems (and now, the automations!) that make building them possible. Would love to hear how others are using AI to automate the operational side of product management!

Burnout in Tech: It’s Not Just the Late Nights 💻🔥 If you work in tech, you’ve likely experienced burnout. But it’s not always from the long nights or tight deadlines. A more silent form of burnout comes from repetitive, non-creative tasks—think bug fixes, managing legacy code, or running the same tests over and over. 😩 The Repetitive Rut 🔄 As technology professionals, we thrive on creativity and problem-solving. But when you’re stuck doing repetitive tasks, it feels draining and prevents you from reaching your full potential. The solution? Job crafting—restructuring your role to focus on what excites you. And here's where Generative AI steps in to help automate the mundane and free you up for more creative work. 💡 Why Build Your Own Tools? 🛠️ While there are plenty of pre-built AI tools available, they often don’t meet all your needs. What’s more, building custom tools to suit your specific tasks has never been easier. With open-source models and platforms, you can quickly develop AI solutions tailored to your workflow. Here’s how: Examples of Tasks & Models to Automate Them 🤖 1. Automating bug report creation from logs : Model/Framework: GPT-3/4, fine-tuned for bug report generation 2.Automating repetitive code writing or refactoring : Model/Framework: Codex (GitHub Copilot), Tabnine 3. Code Review Automation : Model/Framework: DeepCode, SonarQube AI Documentation Generation 4. Automatically generating project documentation:Model/Framework: GPT-3, OpenAI Codex, BERT 5.Generating and running unit tests :Model/Framework: Hugging Face Transformers, PyTorch for custom test scripts 6.Sentiment Analysis on User Feedback :Model/Framework: BERT, RoBERTa, VADER Sentiment Analysis 7.Feature Request Categorization :Model/Framework: spaCy, Hugging Face Transformers 8.Automatically summarizing meeting transcripts : Model/Framework: Otter.ai, Deepgram, Whisper (OpenAI) 9.Automating project task prioritization based on urgency and resources Model/Framework: Haystack, Scikit-learn 10.Automating product roadmap updates from team discussions : Model/Framework: Rasa, spaCy for dialogue flow and workflow automation Here’s a quick process to get started: -Spot the Drain: Identify the task you dread the most. ⏳ -AI It: Build a custom solution using open-source models to automate it. 🧠 -Craft It: Use the time saved to focus on high-value work—whether it’s innovating new features or solving complex problems. 💡✨ Burnout isn’t something we should accept—it’s a signal that we need smarter workflows. Let’s reclaim our time, focus on creativity, and make our workdays more fulfilling. 🙌 #TechBurnout #GenerativeAI #AItools #OpenSourceAI #JobCrafting #ProductivityHacks

Many people I talk to have heard of coding agents and are interested in using them, but don't know: 1. What current coding agents can do 2. How users can prompt agents effectively To help out with this, I wrote a blog on 8 use cases for coding agents, with example prompts: https://lnkd.in/gdizhYMX The first two use cases are familiar ones, (1) fixing bugs and (2) adding features. This is the common "resolve github issue" usecase tested in benchmarks like SWE-Bench. One nice thing about good agents is that they can implement a change and test it. Here's an example prompt. Another thing people are using agents for a bit is (3) creating new apps from scratch. Here's are two examples for a frontend app and email sending script that I successfully created with OpenHands. In this case I prompt about some design decisions, like what framework to use. The next three are actually my favorites: (4) fixing failing CI tests, (5) fixing merge conflicts, and (6) writing docs. These tasks every developer needs to do but noone wants to do. It's been a huge boost to be able to ask the agent to resolve these issues for me; it generally works well! Coding agents can also (7) help with deployments by spinning up cloud resources. Obviously you need to carefully supervise the agent to make sure that it doesn't break anything, but with careful credentialing and review of infrastructure as code it can make deployment much easier! Finally, I have been using coding agents a lot for (8) data analysis tasks. I asked OpenHands to create a script to monitor commit activity on our repo, and the resulting graph is in the blog. One final easter egg, I actually asked OpenHands to make the header figure at the top of this thread too! I asked it: * Download appropriate from fonts-awesome * Arrange them 2 rows and 4 columns center-justified with the text * Make them rainbow colored * Write to png If any of these use cases sound interesting, I'd encourage you to read the blog and try out OpenHands, a general software development agent that can help with these tasks: * Download now: https://lnkd.in/g4VhSi9a * Sign up for the web app: https://lnkd.in/gJ-_SFv2

AI coding assistants are changing the way software gets built. I've recently taken a deep dive into three powerful AI coding tools: Claude Code (Anthropic), OpenAI Codex, and Cursor. Here’s what stood out to me: Claude Code (Anthropic) feels like a highly skilled engineer integrated directly into your terminal. You give it a natural language instruction, like a bug to fix or a feature to build and it autonomously reads through your entire codebase, plans the solution, makes precise edits, runs your tests, and even prepares pull requests. Its strength lies in effortlessly managing complex tasks across large repositories, making it uniquely effective for substantial refactors and large monorepos. OpenAI Codex, now embedded within ChatGPT and also accessible via its CLI tool, operates as a remote coding assistant. You describe a task in plain English, it uploads your project to a secure cloud sandbox, then iteratively generates, tests, and refines code until it meets your requirements. It excels at quickly prototyping ideas or handling multiple parallel tasks in isolation. This approach makes Codex particularly powerful for automated, iterative development workflows, perfect for agile experimentation or rapid feature implementation. Cursor is essentially a fully AI-powered IDE built on VS Code. It integrates deeply with your editor, providing intelligent code completions, inline refactoring, and automated debugging ("Bug Bot"). With real-time awareness of your codebase, Cursor feels like having a dedicated AI pair programmer embedded right into your workflow. Its agent mode can autonomously tackle multi-step coding tasks while you maintain direct oversight, enhancing productivity during everyday coding tasks. Each tool uniquely shapes development: Claude Code excels in autonomous long-form tasks, handling entire workflows end-to-end. Codex is outstanding in rapid, cloud-based iterations and parallel task execution. Cursor seamlessly blends AI support directly into your coding environment for instant productivity boosts. As AI continues to evolve, these tools offer a glimpse into a future where software development becomes less about writing code and more about articulating ideas clearly, managing workflows efficiently, and letting the AI handle the heavy lifting.

The best KPI for automation and AI in an engineering team isn’t “how much code it generated,” but “how much the release cycle got shorter.” Because the team goes through the same chain every time: idea → ticket → code → tests → review → release → monitoring → fix. And this is exactly where the real value isn’t in generic AI chats, but in generative and automated tools for engineering team tools that plug into the SDLC and take routine work off people’s hands. Here are 3 practical ways to speed up Delivery in 2026 👇 1) Generative coding tools: faster development and more consistent maintenance What to delegate: - generating boilerplate and repetitive blocks - refactoring without changing behavior - writing documentation for modules/endpoints - preparing a pull request (PR) descriptions (what changed, why, and how to test) 💡 Tools: GitHub Copilot, Cursor, Codeium 2) Automated delivery tools: from task to pull request in small iterations This speeds up not just “coding”, but the entire workflow. What to delegate: - breaking down requirements + drafting clarifying questions for the ticket - an implementation plan with a risk assessment - splitting work into subtasks and creating a readiness checklist - creating a PR with a structured description 💡 Tools: ChatGPT / Claude / Gemini + agentic integrations with your repo / IDE 3) Generative tools for QA/DevOps: tests, triage, and fewer incidents A lot of teams “speed up coding” but still get bottlenecked by testing and releases. Automation can make a very noticeable difference here. What to delegate: - generating tests. - analyzing logs and drafting a root-cause analysis (RCA) - security checks and fix suggestions - release notes, runbooks, and checklists 💡Tools: Testlum for dynamic testing, and SonarQube + Snyk for static analysis. The most common mistake teams will make in 2026 is adding automation as just another tool without changing the process. To make generative and automated tools truly accelerate delivery, think of it this way: not “we’re adding AI,” but “we’re implementing a specific use case within the SDLC.” 💭 Share in the comments what generative or automated tools you are already using in your team today, and for what exactly (code/PRs/tests/releases/monitoring)? ♻️ Save this post to try all the tools later. Share it with others who may find these helpful.