# Data analysis Data analysis is the systematic process of inspecting, cleaning, transforming, and modeling data to extract information, identify patterns, and support decision-making. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Automating EDA With fg-data-profiling DevFeed: [Automating EDA With fg-data-profiling]() Original publisher: [Read original article]() Author: Real Python Published: 2026-09-15T14:00:00Z Content type: tutorial Language: en Sources: [Real Python]() Topics: [Data analysis](), [pandas](), [Python](), [Data Quality](), [Statistics](), [HTML](), [JSON]() Tags: [data-analysis](), [data-quality](), [pandas](), [python](), [statistics](), [tutorial]() ### AI overview A video course on automating exploratory data analysis with fg-data-profiling. It covers generating interactive reports from DataFrames, exporting them to HTML or JSON, analyzing time series, and comparing datasets. ### Source excerpt Automate exploratory data analysis by transforming DataFrames into interactive reports with one command from fg-data-profiling. ## Beyond the data: what a Business Analyst does at Nubank DevFeed: [Beyond the data: what a Business Analyst does at Nubank]() Original publisher: [Read original article]() Author: Nubank Editorial Published: 2026-09-15T12:14:41Z Content type: opinion Language: en Sources: [Nubank]() Topics: [Data analysis](), [decision-making](), [dashboards](), [Tech Lead](), [User Experience](), [Finance]() Tags: [analysts](), [business-analyst](), [dashboards](), [data](), [data-analysis](), [data-analytics](), [data-science-machine-learning](), [decision-making](), [experimentation](), [meetings](), [tech-lead](), [user-experience]() ### AI overview This article explains how Business Analysts at Nubank connect data analysis, business context, and experimentation to product decisions. It describes their work in multidisciplinary squads, including investigating metrics, evaluating trade-offs, and making decisions under uncertainty. ### Source excerpt Understand how Business Analysts at Nubank use data, context, and experimentation to guide product decisions. The post Beyond the data: what a Business Analyst does at Nubank appeared first on Building Nubank. ## Beyond the data: what a Business Analyst does at Nubank DevFeed: [Beyond the data: what a Business Analyst does at Nubank]() Original publisher: [Read original article]() Author: Nubank Editorial Published: 2026-09-15T12:14:41Z Content type: opinion Language: en Sources: [Nubank]() Topics: [Data analysis](), [decision-making](), [context](), [Tech Lead]() Tags: [adoption](), [business-analyst](), [data](), [data-analysis](), [data-analytics](), [data-science-machine-learning](), [decision-making](), [manager](), [tech-lead](), [user-experience]() ### AI overview A first-person account of the Business Analyst role at Nubank, describing how BAs connect data analysis, context, and experimentation to product and business decisions. The article emphasizes clarifying trade-offs, investigating metrics, and collaborating with product and technical roles. ### Source excerpt Understand how Business Analysts at Nubank use data, context, and experimentation to guide product decisions. The post Beyond the data: what a Business Analyst does at Nubank appeared first on Building Nubank. ## How an MIT research project became a global programming language DevFeed: [How an MIT research project became a global programming language]() Original publisher: [Read original article]() Author: Zach Winn | MIT News Published: 2026-08-31T04:00:00Z Content type: news Language: en Sources: [MIT AI News]() Topics: [The Julia Language](), [Programming language](), [Data Science](), [Complex Systems](), [Data analysis](), [Open Source]() Tags: [ai](), [ai-platform](), [alan-edelman](), [analysis](), [applications](), [artificial-intelligence](), [chris-rackauckas](), [complex-systems](), [computer-science-and-artificial-intelligence-laboratory-csail](), [deshpande-center](), [jeff-bezanson](), [julia-programming-language](), [juliahub](), [language](), [mit-schwarzman-college-of-computing](), [open-source](), [programming](), [programming-language](), [software](), [startups](), [stefan-karpinski](), [viral-shah]() ### AI overview An MIT research project created Julia, a free and open-source programming language for scientific research, data analysis, and complex-systems modeling. The article describes Julia's adoption by researchers, engineers, companies, and universities, and introduces JuliaHub's Dyad 3.0 AI platform. ### Source excerpt With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more. ## Run Massive-Scale UMAP in Minutes Using Multiple GPUs--Without Losing Accuracy DevFeed: [Run Massive-Scale UMAP in Minutes Using Multiple GPUs--Without Losing Accuracy]() Original publisher: [Read original article]() Author: Tanya Lenz Published: 2026-08-18T16:48:08Z Content type: article Language: en Sources: [NVIDIA Developer](), [NVIDIA Technical Blog]() Topics: [Data analysis](), [GPU](), [Graphs](), [datasets](), [RAPIDS](), [Nvidia]() Tags: [accelerate](), [analysis](), [cuda-x](), [data-analytics-processing](), [data-center-cloud](), [data-science](), [datasets](), [feature](), [featured](), [gpu](), [graphs](), [multi-gpu](), [nvidia](), [post](), [scale](), [simulation-modeling-design](), [training](), [vector](), [visualization]() ### AI overview This article explains how multi-GPU UMAP scales dimensionality reduction to datasets containing tens to hundreds of millions of vectors. A feature in NVIDIA cuML and cuVS 25.06 distributes all-neighbors kNN graph construction across multiple GPUs, enabling workloads of several hundred gigabytes to run in minutes while preserving nearest-neighbor relationships and accuracy. ### Source excerpt Uniform Manifold Approximation and Projection (UMAP) is a dimensionality reduction technique widely used for visualization and feature extraction. Applications... ## Use the Axe Monitor MCP integration within your preferred AI assistant to accelerate issue prioritization DevFeed: [Use the Axe Monitor MCP integration within your preferred AI assistant to accelerate issue prioritization]() Original publisher: [Read original article]() Author: Kate Spalla Published: 2026-07-30T11:57:11Z Content type: article Language: en Sources: [Deque]() Topics: [axe monitor](), [Accessibility](), [Model Context Protocol](), [Data analysis]() Tags: [a11y-for-developers](), [accessibility](), [agentic-ai](), [axe-monitor](), [company-news-and-updates](), [efficiency](), [integration](), [mcp](), [selectors]() ### AI overview The article explains how the Axe Monitor MCP integration works with a preferred AI assistant to help accessibility program managers compare scan results, identify changes, prioritize remediation, and create actionable sprint plans using natural-language prompts. ### Source excerpt Now, by using our new Axe Monitor MCP integration within your preferred AI assistant, you can use natural language prompts to dramatically speed up the process of creating and comparing scans, prioritizing fixes, and building and delivering actionable accessibility sprint plans. The post Use the Axe Monitor MCP integration within your preferred AI assistant to accelerate issue prioritization appeared first on Deque. ## Using OxCaml to implement type-safe reference counting between OCaml and Python DevFeed: [Using OxCaml to implement type-safe reference counting between OCaml and Python]() Original publisher: [Read original article]() Author: Nicolas Trangez Published: 2026-06-15T00:00:00Z Content type: tutorial Language: en Sources: [Jane Street]() Topics: [OCaml](), [Python](), [Programming language](), [Programming](), [Data analysis](), [Machine learning]() Tags: [compiler](), [gc](), [memory](), [memory-management](), [ocaml](), [parallelism](), [programming-language](), [python]() ### AI overview Jane Street describes using OxCaml extensions to implement type-safe reference counting between OCaml and Python. The approach addresses delayed deallocation when objects cross the language boundary, including for large data frames and scarce resources such as GPU memory. ### Source excerpt Jane Street is known for being an OCaml shop, but for years now Python has been our second major programming language, acting as the primary tool for data analysis and (especially importantly these days) machine learning. Most of our traders and researchers think and write in Python, even as the majority of our infrastructure is written in OCaml. ## How engineers at Nextdoor use Codex to build without limits DevFeed: [How engineers at Nextdoor use Codex to build without limits]() Original publisher: [Read original article]() Published: 2026-06-09T12:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [codex](), [systems](), [debugging](), [Rust](), [Back end](), [Front end](), [Data analysis](), [Kubernetes]() Tags: [agent](), [backend](), [codex](), [data](), [debugging](), [engineering](), [frontend](), [kubernetes](), [productivity](), [rust](), [systems]() ### AI overview Nextdoor engineers use Codex for outcome-focused product development, enabling individual engineers to build features end to end across mobile, frontend, and backend systems. The article also describes using Codex to debug difficult issues involving embedded Rust databases, race conditions, Kubernetes pods, and data analysis. ### Source excerpt How engineers at Nextdoor use Codex with GPT-5.5 to investigate hard-to-reproduce issues, build across platforms, and focus on product outcomes. ## Get reliable answers to business questions with Bits Data Analysis DevFeed: [Get reliable answers to business questions with Bits Data Analysis]() Original publisher: [Read original article]() Author: Jonathan Morin; Jonathan Parisot; Harel Shein Published: 2026-06-09T00:00:00Z Content type: article Language: en Sources: [Datadog | The Monitor blog]() Topics: [Data analysis](), [data observability](), [semantic-layer](), [SIEM, Security, Observability](), [Model Context Protocol](), [ai-coding]() Tags: [ai](), [ai-coding](), [analytics](), [bits-ai](), [data-analytics](), [data-engineering](), [data-observability](), [digital-experience-monitoring](), [mcp](), [observability](), [root-cause-analysis](), [semantic-layer]() ### AI overview Bits Data Analysis, now in Preview, helps teams answer business questions with governed context from their data stack and Datadog telemetry. It uses metric definitions, lineage, freshness, quality signals, application telemetry, and source code to select appropriate data and provide confidence indicators with links to the definitions and tables used. ### Source excerpt Learn how Bits Data Analysis answers business questions using governed data context from Datadog. ## Codex is becoming a productivity tool for everyone DevFeed: [Codex is becoming a productivity tool for everyone]() Original publisher: [Read original article]() Published: 2026-06-02T02:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [codex](), [Artificial Intelligence](), [Data analysis](), [workflow automation](), [Automation]() Tags: [ai](), [analysis](), [automation](), [codex](), [content](), [data](), [global-affairs](), [productivity](), [tools](), [work](), [workflow-automation]() ### AI overview OpenAI describes Codex as expanding beyond coding into a productivity tool for knowledge work. The article highlights its use for research, data analysis, workflow automation, content creation, and lightweight tool building, alongside growing adoption among knowledge workers. ### Source excerpt The Next Era of Knowledge Work report explores how Codex is transforming productivity through AI-powered research, data analysis, workflow automation, and content creation. ## Building Reliable AI Products in the Agentic Era DevFeed: [Building Reliable AI Products in the Agentic Era]() Original publisher: [Read original article]() Author: Dinesh Murthy Published: 2026-05-29T21:30:04Z Content type: article Language: en Sources: [DigitalOcean]() Topics: [Artificial Intelligence](), [Generative AI](), [Large Language Model](), [Data analysis]() Tags: [2026](), [agentic](), [ai](), [ai-agents](), [community](), [data-analysis](), [generative-ai](), [llm]() ### AI overview A DigitalOcean Deploy 2026 panel explores how founders build dependable AI products when teams can access the same frontier models through APIs. The discussion focuses on reliability, human oversight, production-scale agent behavior, model selection, and creating differentiation beyond the underlying model. ### Source excerpt Getting your hands on a capable AI model is the easy part now. Every team can reach the same frontier models through an API, so a strong model is not what sets a product apart. What separates a working product from a demo is everything around the model. You have to measure whether the agent is actually doing its job, then keep grinding on reliability until it stops making expensive mistakes in front of real users. I moderated a panel on exactly that at DigitalOcean's Deploy 2026 conference in San Francisco, a forty-minute conversation with four founders on what they've learned shipping AI products that people depend on: Angela Hoover, co-founder and CEO of Andi AI, an ad-free consumer search engine that pairs generative AI with live web data to give people direct answers instead of a page of ad-heavy links. Alex Mashrabov, co-founder and CEO of Higgsfield AI, a platform that lets creators and agencies produce cinematic video without any physical production. Hovsep Seraydarian, co-founder and CTO of LawVo, a Canadian legal platform that pairs hundreds of AI agents trained in specific legal areas with human lawyers who verify their accuracy. Peter Elias, founder of Probably, a data analysis agent that lets non-technical people query their data in plain English and runs calculations on a local engine instead of an LLM so it can decline to answer when the data does not support a clear result. The discussion got into what each founder underestimated once their agents had to run at scale, how they choose models from a field that keeps growing, what "agentic" actually means in production, and where a real moat comes from when everyone builds on the same foundation. Watch the full session from Deploy 2026: View YouTube video Making agents work in production When the founders were asked what they underestimated once their agents had to run in production, none of them pointed to the model. You need creative DNA Higgsfield spent a year on R&D without traction. What finally mov ## Leading design through the AI shift DevFeed: [Leading design through the AI shift]() Original publisher: [Read original article]() Author: andyacevedo Published: 2026-05-21T16:47:34Z Content type: opinion Language: en Sources: [Slack Design]() Topics: [Artificial Intelligence](), [AI-assisted coding](), [Code](), [Data analysis](), [Low-Code / Internal Tools](), [Tooling](), [ui]() Tags: [agents](), [ai](), [ai-tools](), [coding-agents](), [data-analysis](), [figma](), [internal-tools](), [ui](), [uncategorized](), [workflow]() ### AI overview A Slack Design leader describes how AI is changing the team's design workflow, including the use of coding agents for data analysis and rapid prototyping, code-based demos, and designer-built internal tools. The article emphasizes combining AI tools with human judgment and taste while acknowledging increased stress, uncertainty, and ethical questions. ### Source excerpt AI has eaten the technology industry. What started as a slow, hallucination-prone chatbot has become something much harder to ignore. As a designer, it can feel like the ground is shifting under your feet, quietly at first, then all at once. Every week, something new disrupts your workflow, your toolset, your expectations about what's possible. [...] The post Leading design through the AI shift appeared first on Slack Design. ## View Operational Insights Within the GraphOS Platform API DevFeed: [View Operational Insights Within the GraphOS Platform API]() Original publisher: [Read original article]() Author: Nick Marsh Published: 2026-04-13T13:34:36Z Content type: tutorial Language: en Sources: [Apollo Blog]() Topics: [GraphOS](), [Platform API](), [GraphQL](), [Data analysis](), [Latency]() Tags: [analysis](), [engineering](), [format](), [graphos](), [graphql](), [latency](), [monitoring](), [platform-api]() ### AI overview The article explains how to use the GraphOS Platform API to analyze GraphQL usage and performance. It covers point-in-time operation reports and time-series insights for operations, subgraphs, and fields, including metrics such as request counts, latency percentiles, and error rates. ### Source excerpt Query GraphQL usage with the GraphOS Platform API: point-in-time operation reports plus timeseries data for operations, subgraphs, and fields. ## Analyzing data with ChatGPT DevFeed: [Analyzing data with ChatGPT]() Original publisher: [Read original article]() Published: 2026-04-10T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [Data analysis](), [datasets](), [CSV](), [dashboards]() Tags: [analysis](), [chatgpt](), [dashboards](), [data](), [datasets](), [executive](), [explore](), [generate](), [google](), [how-to](), [insights](), [learn](), [openai-academy](), [product](), [tools](), [work]() ### AI overview Learn how to use ChatGPT to explore datasets, analyze CSV or Excel files, create visualizations, identify anomalies, and turn findings into clear, actionable insights. ### Source excerpt Learn how to explore datasets, generate insights, create visualizations, and turn findings into actionable decisions with ChatGPT. ## Financial services DevFeed: [Financial services]() Original publisher: [Read original article]() Published: 2026-04-10T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [OpenAI](), [Prompt Engineering](), [Data analysis]() Tags: [ai](), [analysis](), [data](), [explore](), [financial-services](), [guides](), [openai](), [openai-academy](), [policy](), [resources](), [scale](), [search](), [tax](), [tools](), [workflows]() ### AI overview A curated collection of OpenAI resources for financial services organizations, covering AI evaluation, adoption, deployment, and scaling in regulated environments. It includes prompts and guidance for financial analysis, research, policy and tax interpretation, document analysis, data extraction, and business workflows. ### Source excerpt Explore AI resources for financial services, including prompt packs, GPTs, guides, and tools to help institutions deploy and scale AI securely. ## Learn ChatGPT workflows for finance teams DevFeed: [Learn ChatGPT workflows for finance teams]() Original publisher: [Read original article]() Published: 2026-04-10T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [ChatGPT](), [Data analysis](), [DRIVE](), [CSV]() Tags: [analysis](), [business](), [chatgpt](), [communication](), [data](), [drive](), [finance](), [learn](), [openai-academy](), [tools](), [workflows]() ### AI overview This article explains how finance teams can use ChatGPT to structure messy inputs, analyze spreadsheets and CSV files, draft clear financial communication, and standardize recurring work such as variance commentary, forecasts, and close updates. It emphasizes that ChatGPT supports finance judgment rather than replacing it. ### Source excerpt Learn practical ChatGPT workflows for financial analysis, reporting, planning, and decision-ready communication. ## Where wild things roam: Identifying wildlife with SpeciesNet DevFeed: [Where wild things roam: Identifying wildlife with SpeciesNet]() Original publisher: [Read original article]() Published: 2026-03-06T17:59:38Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Earth AI](), [Artificial Intelligence](), [Google](), [Open Source](), [Deep learning](), [Data analysis](), [data](), [migration]() Tags: [ai](), [ai-models](), [analysis](), [climate-sustainability](), [data](), [datasets](), [deep-learning](), [earth-ai](), [generative-ai](), [google](), [migration](), [open-source](), [open-source-models-datasets](), [sustainability]() ### AI overview Google Research describes SpeciesNet, an open-source AI model that identifies nearly 2,500 animal categories in camera-trap images. Trained on 65 million labelled images, it is being used by research groups worldwide to support wildlife monitoring, conservation, and analysis of animal populations and patterns. ### Source excerpt Climate & Sustainability ## Pharmacy late-night opening hours analysis featured in the Financial Times DevFeed: [Pharmacy late-night opening hours analysis featured in the Financial Times]() Original publisher: [Read original article]() Author: Robin Wilson Published: 2026-02-04T14:10:37Z Content type: article Language: en Sources: [Robin Wilson]() Topics: [Data analysis](), [geospatial](), [Geographic Information System](), [Python](), [pandas]() Tags: [academic](), [analysis](), [article](), [data](), [data-analysis](), [geospatial](), [gis](), [pandas](), [python]() ### AI overview The article describes an analysis of NHS data on community pharmacy opening hours in England. It reports that the number of pharmacies open past 9pm on weekdays fell by approximately 95% between 2022 and 2025, leaving large areas without late-night pharmacy access. The analysis used Python, pandas, geospatial tools and mapping libraries, and was featured in the Financial Times. ### Source excerpt Some data analysis I've done has been featured in the Financial Times today - see this article (the link may not work any more unless you have a FT subscription - sorry). The brief story is that I had terrible back pain over Christmas, and spoke to an out-of-hours GP on the phone who prescribed [...] ## Zero-ETL lakehouses for Postgres people DevFeed: [Zero-ETL lakehouses for Postgres people]() Original publisher: [Read original article]() Author: George MacKerron Published: 2026-01-12T18:43:54Z Content type: article Language: en Sources: [Blog -- Neon Docs]() Topics: [Data analysis](), [data-processing](), [datasets](), [Databases](), [databricks](), [API](), [Ruby](), [Linux]() Tags: [analysis](), [api](), [data-processing](), [database](), [databases](), [databricks](), [linux](), [postgres](), [ruby]() ### AI overview An explanation of data lakehouses and enterprise data tooling for readers familiar with Postgres. It contrasts OLTP transactions with OLAP analysis, describes composable lakehouse stacks, and discusses tools that move or analyze data across Postgres and lakehouses. ### Source excerpt Neon is made by Postgres people. Since Neon became part of Databricks, we Postgres people also find ourselves part of a larger organisation of enterprise data people. This post is about what I've learned as a result. It aims to explain 'data lakehouses' and related enterprise-dat... ## One in a million: celebrating the customers shaping AI's future DevFeed: [One in a million: celebrating the customers shaping AI's future]() Original publisher: [Read original article]() Published: 2025-12-22T00:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [OpenAI](), [ChatGPT](), [codex](), [API](), [coding](), [Data analysis]() Tags: [agents](), [ai](), [api](), [chatgpt](), [codex](), [coding](), [customers](), [data-analysis](), [design](), [developers](), [images](), [openai](), [platform](), [products](), [video](), [voice](), [workflows]() ### AI overview OpenAI celebrates more than one million customers using its products to support teams and create new opportunities. The article describes organizations deploying ChatGPT for writing, coding, research, data analysis, and design; building agents to automate workflows; using Codex to accelerate development; and creating new products with the OpenAI API across voice, video, images, and other modalities. ### Source excerpt More than one million customers around the world now use OpenAI to empower their teams and unlock new opportunities. This post highlights how companies like PayPal, Virgin Atlantic, BBVA, Cisco, Moderna, and Canva are transforming the way work gets done with AI. ## Mob Programming: Smells Like Team Spirit DevFeed: [Mob Programming: Smells Like Team Spirit]() Original publisher: [Read original article]() Author: Dmytro Kurets Published: 2025-12-04T00:00:00Z Content type: article Language: en Sources: [Trivago]() Topics: [Programming](), [Code](), [pull-requests](), [Back end](), [Front end](), [Data analysis](), [Refactoring]() Tags: [back-end](), [code](), [collaboration](), [data-analysis](), [engineering](), [engineering-culture](), [front-end](), [keyboard](), [pairing](), [programming](), [review](), [team]() ### AI overview The article explains mob programming as structured, shared-focus collaboration with one driver, rotating typing roles, and navigators guiding the work. It describes a trivago team experimenting with collaborative review and coding changes to address pull requests piling up and slowing delivery. ### Source excerpt Mob programming often sparks hot takes. "It's counter-productive." "One person could do it faster." "Why waste five people on one keyboard?" If that's what it looks like in your head--one senior ... ## Run Product Analytics on Your Neon Data Using Fabi.ai DevFeed: [Run Product Analytics on Your Neon Data Using Fabi.ai]() Original publisher: [Read original article]() Author: Marc Dupuis Published: 2025-11-14T18:24:08Z Content type: tutorial Language: en Sources: [Blog -- Neon Docs]() Topics: [Data analysis](), [Databases](), [AI Chat]() Tags: [ai](), [business-intelligence](), [community](), [dashboards](), [data](), [database](), [how-to](), [product-analytics](), [sql](), [workflows]() ### AI overview A tutorial showing how to connect a Neon Postgres database to Fabi.ai, use its AI Analyst Agent to query product data in plain English, and turn the results into dashboards and automated workflows. ### Source excerpt You're already using Neon, so chances are you've got valuable application data sitting in your Postgres database that reflects how people interact with your product. This data can tell you a lot about your customers and help guide product decisions, whether you're an engineer, a... ## An Ethos for Using AI Coding Tools: Ownership and Exploiting High-Value Opportunities DevFeed: [An Ethos for Using AI Coding Tools: Ownership and Exploiting High-Value Opportunities]() Original publisher: [Read original article]() Published: 2025-09-15T00:00:00Z Content type: opinion Language: en Sources: [Tim Kellogg]() Topics: [Artificial Intelligence](), [ai-coding](), [Software Engineering](), [Data analysis](), [future of software]() Tags: [ai](), [ai-coding](), [coding](), [data-analysis](), [future-of-software](), [software-engineering]() ### AI overview The author describes an ethos for using AI coding tools, centered on owning and understanding the generated code. They also argue that effective AI coding involves finding opportunities where limited AI effort can produce substantial value, such as proof-of-concept work and rapid data analysis. ### Source excerpt A few people have asked me how I use AI coding tools. I don't think it's a straightforward answer. For me it's not really a procedure or recipe, it's more of an ethos. ## Jupyter Agents: training LLMs to reason with notebooks DevFeed: [Jupyter Agents: training LLMs to reason with notebooks]() Original publisher: [Read original article]() Author: Baptiste Colle; Hanna Yukhymenko; Leandro von Werra Published: 2025-09-10T00:00:00Z Content type: article Language: en Sources: [Hugging Face - Blog]() Topics: [Jupyter Notebook](), [Data analysis](), [Data Science](), [LLMs](), [Fine-tuning](), [Open Source Models & Datasets](), [Benchmark](), [Human-AI evaluation](), [smolagents](), [qwen](), [ide]() Tags: [agents](), [analysis](), [benchmark](), [cursor](), [data](), [data-science](), [datasets](), [evaluation](), [fine-tuning](), [jupyter](), [llm](), [llms](), [qwen](), [research](), [smolagents]() ### AI overview The article presents Jupyter Agent, a system that executes code inside Jupyter notebooks to support data analysis and data science workflows. It describes a pipeline for generating training data, fine-tuning smaller models, and evaluating them on the DABStep benchmark, with examples involving Qwen models and smolagents. ### Source excerpt We're on a journey to advance and democratize artificial intelligence through open source and open science. [Next page]()