Agentic Data Science Pair Programming With marimo pair

Agentic Architecture: Why Files Aren't Always Enough

What are the limitations of using a file-based agent workflow? Why do massive context windows tend to collapse? This week on the show, Mikiko Bazeley from MongoDB joins us to discuss agentic architecture and context engineering. Mikiko is an applied AI engineer. She helps developers and organizations build AI and ML applications using MongoDB. We dig into the debate of files versus a database. What are some of the limitations of building an agent with just a folder of files? We explore the surprising limitations of massive context windows and strategies for fixing them. Mikiko also shares advice and resources to help you get up to speed on building your own agent skills. Our conversation touches on multiple topics in the current development landscape. This episode is sponsored by SerpApi [https://serpapi.com/?utm_source=realpython&utm_medium=podcast&utm_campaign=q12]. Video Course Spotlight: Building Type-Safe LLM Agents With Pydantic AI [https://realpython.com/courses/building-type-safe-llm-agents-with-pydantic-ai/] Build type-safe LLM agents in Python with Pydantic AI using structured outputs, function calling, and dependency injection. Topics: * 00:00:00 – Introduction * 00:02:31 – Catching up with MongoDB * 00:07:02 – Are the files all you need? * 00:15:14 – What is a workflow agent? * 00:24:43 – Sponsor: SerpApi * 00:25:45 – Model vs harness * 00:29:57 – Context rot and tool loadouts * 00:41:07 – Sharing state and coordination of agents * 00:47:27 – Video Course Spotlight * 00:49:16 – What do dataflows look like * 01:00:38 – The human-in-the-loop & coding agents * 01:10:30 – Resources to explore * 01:17:49 – What are you excited about in the world of Python? * 01:18:38 – What do you want to learn next? * 01:22:54 – Thanks and goodbye Show Links: * The “files are all you need” debate misses what’s actually happening in agent memory architecture - The New Stack [https://thenewstack.io/ai-agent-memory-architecture/] * MongoDB: The World’s Leading Modern Data Platform [https://www.mongodb.com/] * Karpathy shares ‘LLM Knowledge Base’ architecture that bypasses RAG with an evolving markdown library maintained by AI - VentureBeat [https://venturebeat.com/data/karpathy-shares-llm-knowledge-base-architecture-that-bypasses-rag-with-an] * Files Are All You Need: Context, Search, Skills Guide | LlamaIndex [https://www.llamaindex.ai/blog/files-are-all-you-need] * Converged Datastore For Agentic AI - MongoDB [https://www.mongodb.com/company/blog/technical/converged-datastore-for-agentic-ai] * Why Developers Need Vector Search - The New Stack [https://thenewstack.io/why-developers-need-vector-search/] * Why Multi-Agent Systems Need Memory Engineering – O’Reilly [https://www.oreilly.com/radar/why-multi-agent-systems-need-memory-engineering/] * The New Skill in AI is Not Prompting, It’s Context Engineering - Phil Schmid [https://www.philschmid.de/context-engineering] * How Long Contexts Fail - dbreunig.com [https://www.dbreunig.com/2025/06/22/how-contexts-fail-and-how-to-fix-them.html] * How to Fix Your Context - dbreunig.com [https://www.dbreunig.com/2025/06/26/how-to-fix-your-context.html] * AI Agents Need Memory Control Over More Context - arxiv.org [https://arxiv.org/abs/2601.11653] * AINews - Is Harness Engineering real? - Latent.Space [https://www.latent.space/p/ainews-is-harness-engineering-real] * The Model vs. the Harness: Which Actually Matters More? [https://adambaitch.substack.com/p/the-model-vs-the-harness-which-actually-matters-more-59dd3116bb31] * Embeddings and Vector Databases With ChromaDB – Real Python [https://realpython.com/chromadb-vector-database/] * 12-factor-agents: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? [https://github.com/humanlayer/12-factor-agents] * The Twelve-Factor App [https://12factor.net/] * MongoDB Courses and Trainings - MongoDB University [https://learn.mongodb.com/] * mongodb-mcp-server: A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters. [https://github.com/mongodb-js/mongodb-mcp-server] * What is the MongoDB MCP Server? - MongoDB Docs [https://www.mongodb.com/docs/mcp-server/] * mongo-python-driver: PyMongo - the Official MongoDB Python driver [https://github.com/mongodb/mongo-python-driver] * agent-skills: Use the official MongoDB Skills with your favorite coding agent to build faster. [https://github.com/mongodb/agent-skills] * Reachy Mini - Open-Source Desktop Humanoid Robot [https://reachymini.net/] * 👩🏻‍💻 Mikiko B. - LinkedIn [https://www.linkedin.com/in/mikikobazeley/] * Building AI Products From Scratch - Mikiko Bazeley - Substack [https://mikikobazeley.substack.com/] Level up your Python skills with our expert-led courses: * Getting Started With Claude Code [https://realpython.com/courses/getting-started-claude-code/] * Building Type-Safe LLM Agents With Pydantic AI [https://realpython.com/courses/building-type-safe-llm-agents-with-pydantic-ai/] * Using Pydantic to Simplify Python Data Validation [https://realpython.com/courses/pydantic-simplify-data-validation/] Support the podcast & join our community of Pythonistas [https://realpython.com/join]

Declarative Charts in Python & Discerning Iterators vs Iterables

What if you could build charts in Python by describing what your data means, instead of scripting every visual detail? Christopher Trudeau is back on the show this week with another batch of PyCoder’s Weekly articles and projects. We cover a recent Real Python article about the data visualization library Altair. Most tools require you to write detailed boilerplate code to set up the axis and figure. Altair follows a declarative approach where you specify which columns go to which axis, the type of chart or plot, and what should be interactive. We also share other articles and projects from the Python community, including recent releases, clarifying the differences between iterators and iterables, decoupling your business logic from the Django ORM, comparing an LLM-based tool for web scraping against Playwright, a neural network emulator for guitar amplifiers, and a CLI tool to generate ASCII art of the current moon phase. This episode is sponsored by Build Your Own Coding Agent. Video Course Spotlight: Use Codex CLI to Enhance Your Python Projects [https://realpython.com/courses/use-codex-cli-enhance-your-python-projects/] Learn how to use Codex CLI to add features to Python projects directly from your terminal, without needing a browser or IDE plugins. Topics: * 00:00:00 – Introduction * 00:02:38 – Read the Docs Now Supports uv Natively * 00:03:09 – Reverting the Incremental GC in Python 3.14 and 3.15 * 00:04:51 – Altair: Declarative Charts With Python * 00:12:23 – Sponsor: Build Your Own Coding Agent * 00:13:17 – Decoupling Your Business Logic From the Django ORM * 00:19:51 – browser-use vs. Playwright: Which to Pick for Web Scraping? * 00:26:58 – 2048: iterators and iterables - Ned Batchelder * 00:31:31 – Video Course Spotlight * 00:33:00 – Discussion: Jumping back into solo developer mode * 00:46:59 – neural-amp-modeler: Neural network emulator for guitar amplifiers * 00:51:48 – ascii-moon-phase-python: CLI for ASCII art of the current moon phase * 00:53:11 – Thanks and goodbye * 00:54:43 – Appendix: Neural Amp Modeler - Demo News: * Read the Docs Now Supports uv Natively [https://about.readthedocs.com/blog/2026/04/uv-native-support/] – Popular open source documentation site Read the Docs has announced they now support native uv in .readthedocs.yaml for Python dependency installation. Learn how to use it in your configurations * Reverting the Incremental GC in Python 3.14 and 3.15 [https://discuss.python.org/t/reverting-the-incremental-gc-in-python-3-14-and-3-15/107014] * Fixing a Memory “Leak” From Python 3.14’s Incremental Garbage Collection [https://adamj.eu/tech/2026/04/20/django-python-3.14-incremental-gc/] – Adam encountered an out-of-memory error while migrating a client project to Python 3.14. The issue occurred when running Django’s database migration command on a limited-resource server, and seemed to be caused by the new incremental garbage collection algorithm in Python 3.14. Show Links: * Altair: Declarative Charts With Python [https://realpython.com/altair-python/] – Build interactive Python charts the declarative way with Altair. Map data to visual properties and add linked selections. No JavaScript required. * Decoupling Your Business Logic From the Django ORM [https://buttondown.com/carlton/archive/decoupling-your-business-logic-from-the-django-orm/] – Where should I keep my business logic? This is a perennial topic in Django. This article proposes a continuum of cases, each with increasing complexity. * browser-use vs. Playwright: Which to Pick for Web Scraping? [https://codecut.ai/browser-use-ai-browser-agent/] – Follow along in this walk-through building a Hacker News synthesizer with browser-use, then see it fail on a harder Newegg scraping task. Includes a side-by-side comparison with Playwright and a breakdown of when each tool is the right call. * 2048: iterators and iterables - Ned Batchelder [https://nedbatchelder.com/blog/202507/2048_iterators_and_iterables] – Making a terminal based version of the 2048 game, Ned waded into a classic iterator/iterable confusion. This article shows you how they’re different and how confusing them can cause you problems in your code. Projects: * neural-amp-modeler: Neural network emulator for guitar amplifiers [https://github.com/sdatkinson/neural-amp-modeler] * ascii-moon-phase-python: Command line program that outputs ASCII art of the current moon phase [https://github.com/asweigart/ascii-moon-phase-python] Additional Links: * Vega-Altair: Declarative Visualization in Python — Vega-Altair 6.1.0dev documentation [https://altair-viz.github.io/index.html] * Iterators and Iterables in Python: Run Efficient Iterations – Real Python [https://realpython.com/python-iterators-iterables/] * Neural Amp Modeler - Highly-accurate free and open-source amp modeling plugin [https://www.neuralampmodeler.com/] * TONE3000 Official · Neural Amp Modeler (NAM) Profiles and Impulse Responses (IR’s) [https://www.tone3000.com/] Level up your Python skills with our expert-led courses: * Efficient Iterations With Python Iterators and Iterables [https://realpython.com/courses/efficient-iterations-iterators-iterables/] * Use Codex CLI to Enhance Your Python Projects [https://realpython.com/courses/use-codex-cli-enhance-your-python-projects/] * Graph Your Data With Python and ggplot [https://realpython.com/courses/graph-data-with-python-and-ggplot/] Support the podcast & join our community of Pythonistas [https://realpython.com/join]

Agentic Data Science Pair Programming With marimo pair

How do you add agent skills to your data science workflow? How can a coding agent assist with data wrangling and research? This week on the show, Trevor Manz from marimo joins us to discuss marimo pair. Trevor is a founding engineer at marimo, where he’s been working on integrating LLM tools with marimo. We discuss the balancing act of building a skill and determining how to give an agent access to all the variables in a notebook. He shares how they built a specialized reactive REPL that eliminates hidden state and allows the agent to continue constructing a reproducible Python program. We dig into installing and getting started with marimo pair. Trevor also covers several of the tasks an agent can tackle in a data science workflow. Video Course Spotlight: Getting Started With marimo Notebooks [https://realpython.com/courses/getting-started-with-marimo-notebooks/] Discover how marimo notebook simplifies coding with reactive updates, UI elements, and sandboxing for safe, sharable notebooks. Topics: * 00:00:00 – Introduction * 00:02:26 – Trevor’s role at marimo * 00:03:08 – Current AI tools in marimo * 00:06:26 – Describing marimo notebooks * 00:10:11 – What is marimo pair? * 00:18:49 – Building an agent skill * 00:27:34 – Setup & installation * 00:31:16 – Video Course Spotlight * 00:32:42 – Examples of EDA and data wrangling * 00:45:46 – Experimenting inside of a notebook * 00:50:40 – Managing context * 00:53:25 – Accessing additional libraries * 00:57:16 – Recent tools and updates from the marimo community * 00:59:31 – What are you excited about in the world of Python? * 01:01:10 – What do you want to learn next? * 01:02:26 – How can people follow your work online? * 01:03:13 – Thanks and goodbye Show Links: * Introducing marimo pair - marimo [https://marimo.io/blog/marimo-pair] * marimo-pair: Drop agents inside running marimo notebook sessions [https://github.com/marimo-team/marimo-pair] * Marimo pair – Reactive Python notebooks as environments for agents - Hacker News [https://news.ycombinator.com/item?id=47678844] * Episode #230: marimo: Reactive Notebooks and Deployable Web Apps in Python [https://realpython.com/podcasts/rpp/230/] * marimo Pair - YouTube [https://www.youtube.com/watch?v=6uaqtchDnoc] * We gave Claude Access to All Python Variables - YouTube [https://www.youtube.com/watch?v=VKvjPJeNRPk] * Using the marimo editor’s AI features - marimo [https://docs.marimo.io/guides/editor_features/ai_completion/] * ty: An extremely fast Python type checker and language server, written in Rust. [https://github.com/astral-sh/ty] * molab - marimo [https://molab.marimo.io/notebooks] * marimo: A Reactive, Reproducible Notebook – Real Python [https://realpython.com/marimo-notebook/] * Investigating Quasar Data With Polars and Interactive marimo Notebooks – Real Python [https://realpython.com/courses/investigating-quasar-data-polars-marimo-notebooks/] * Blog - marimo [https://marimo.io/blog] * Trevor Manz - LinkedIn [https://www.linkedin.com/in/trevor-manz/] * trevor manz (@manzt.sh) — Bluesky [https://bsky.app/profile/manzt.sh] Level up your Python skills with our expert-led courses: * Investigating Quasar Data With Polars and Interactive marimo Notebooks [https://realpython.com/courses/investigating-quasar-data-polars-marimo-notebooks/] * Getting Started With Claude Code [https://realpython.com/courses/getting-started-claude-code/] * Getting Started With marimo Notebooks [https://realpython.com/courses/getting-started-with-marimo-notebooks/] Support the podcast & join our community of Pythonistas [https://realpython.com/join]

Becoming a Better Python Developer Through Learning Rust

How can learning Rust help make you a better Python Developer? How do techniques required by a compiled language translate to improving your Python code? Christopher Trudeau is back on the show this week with another batch of PyCoder’s Weekly articles and projects. We discuss a recent article by Bob Belderbos titled “Learning Rust Made Me a Better Python Developer.” Bob has been on a journey learning to program in Rust, which has made him rethink how he’s been writing Python. The compiler forced him to confront things he’d been ignoring. We also share other articles and projects from the Python community, including recent releases, a boatload of PEPs, NumPy as a synth engine, firing and forgetting with Python’s asyncio, managing state with signals in Python, a documentation site generator for Python packages, and a tool to explain your Python environment. This episode is sponsored by AgentField. Video Course Spotlight: Using Loguru to Simplify Python Logging [https://realpython.com/courses/using-loguru-to-simplify-python-logging/] Learn how to use Loguru for simpler Python logging, from zero-config setup and custom formats to file rotation, retention, and adding context. Topics: * 00:00:00 – Introduction * 00:02:23 – Python 3.15.0a8, 3.14.4 and 3.13.13 Released * 00:03:01 – Django Security Releases: 6.0.4, 5.2.13, and 4.2.30 * 00:03:38 – DjangoCon Europe 2027 Call for Organizers * 00:04:04 – PEP 803: "abi3t": Stable ABI for Free-Threaded Builds * 00:04:44 – PEP 829: Structured Startup Configuration via .site.toml File * 00:05:18 – PEP 830 – Add timestamps to exceptions and tracebacks * 00:05:44 – PEP 831 – Frame Pointers Everywhere: Enabling System-Level Observability for Python * 00:06:59 – PEP 832 – Virtual environment discovery * 00:10:13 – PyCoder’s Weekly - Submit a Link * 00:11:15 – NumPy as Synth Engine * 00:21:04 – Sponsor: AgentField * 00:22:05 – Fire and Forget at Textual * 00:25:39 – Learning Rust Made Me a Better Python Developer * 00:34:06 – Video Course Spotlight * 00:35:49 – Signals: State Management for Python Developers * 00:40:34 – great-docs: Documentation Site Generator for Python Package * 00:42:32 – pywho: Explain Your Python Environment and Detect Shadows * 00:44:01 – Thanks and goodbye News: * Python 3.15.0a8, 3.14.4 and 3.13.13 Released [https://blog.python.org/2026/04/python-3150a8-3144-31313/] * Django Security Releases: 6.0.4, 5.2.13, and 4.2.30 [https://www.djangoproject.com/weblog/2026/apr/07/security-releases/] * DjangoCon Europe 2027 Call for Organizers [https://www.djangoproject.com/weblog/2026/apr/07/could-you-host-djangocon-europe-2027-call-for-orga/] * PEP 803: "abi3t": Stable ABI for Free-Threaded Builds (Accepted) [https://peps.python.org/pep-0803/] * PEP 829: Structured Startup Configuration via .site.toml Files (Added) [https://peps.python.org/pep-0829/] * PEP 830 – Add timestamps to exceptions and tracebacks [https://peps.python.org/pep-0830/] * PEP 831 – Frame Pointers Everywhere: Enabling System-Level Observability for Python [https://peps.python.org/pep-0831/] * PEP 832 – Virtual environment discovery [https://peps.python.org/pep-0832/] * PyCoder’s Weekly - Submit a Link [https://pycoders.com/submissions] * The Real Python Podcast [https://realpython.com/podcasts/rpp/] Show Links: * NumPy as Synth Engine [https://kennethreitz.org/essays/2026-03-29-numpy_as_synth_engine] – Kenneth has “recorded” a song in a Python script. The catch? No sampling, no recording, no pre-recorded sound. Everything was done through generating wave functions in NumPy. Learn how to become a mathematical musician. * Fire and Forget at Textual [https://mkennedy.codes/posts/fire-and-forget-at-textual/] – In this follow up to a previous article (Fire and forget (or never) with Python’s asyncio [https://mkennedy.codes/posts/fire-and-forget-or-never-with-python-s-asyncio/], Michael discusses a similar article by Will McGugan as it relates to Textual. He found the problematic pattern in over 500K GitHub files. * Learning Rust Made Me a Better Python Developer [https://belderbos.dev/blog/rust-made-me-a-better-python-developer/] – Bob thinks that learning Rust made him a better Python developer. Not because Rust is better, but because it made him think differently about how he has been writing Python. The compiler forced him to confront things he’d been ignoring. * Signals: State Management for Python Developers [https://bui.app/the-missing-manual-for-signals-state-management-for-python-developers/] – If you’ve ever debugged why your cache didn’t invalidate or notifications stopped firing after a “simple” state change, this guide is for you. Signals are becoming a JavaScript standard, but Python developers can use the same patterns to eliminate “forgot to update that thing” bugs. Projects: * great-docs: Documentation Site Generator for Python Packages [https://github.com/posit-dev/great-docs] * pywho: Explain Your Python Environment and Detect Shadows [https://github.com/AhsanSheraz/pywho] Additional Links: * Open Source Gave Me Everything Until I Had Nothing Left to Give - Kenneth Reitz [https://kennethreitz.org/essays/2026-03-18-open_source_gave_me_everything_until_i_had_nothing_left_to_give] * Yeah… this was impressive to see. #tabla - Escalated Quickly - YouTube [https://www.youtube.com/shorts/iDOF4eokTHc] * PyTheory Is Awesome - Kenneth Reitz [https://kennethreitz.org/essays/2026-03-25-pytheory_is_awesome] * PyTheory: Music Theory for Humans – PyTheory 0.42.1 documentation [https://pytheory.kennethreitz.org/index.html] * A Mini DAW in the Python REPL - Kenneth Reitz [https://kennethreitz.org/essays/2026-03-25-a_mini_daw_in_the_python_repl] * Episode #210: Creating a Guitar Synthesizer & Generating WAV Files With Python [https://realpython.com/podcasts/rpp/210/] * Angine de Poitrine - Vidéos [https://anginedepoitrine.com/videos] * Episode #195: Building a Healthy Developer Mindset While Learning Python [https://realpython.com/podcasts/rpp/195/] * Bite‑sized Rust learning, powered by Pybites [https://rsbit.es/] * Episode #214: Build Captivating Display Tables in Python With Great Tables [https://realpython.com/podcasts/rpp/214/] Level up your Python skills with our expert-led courses: * Thread Safety in Python: Locks and Other Techniques [https://realpython.com/courses/thread-safety-locks-other-techniques/] * NumPy Techniques and Practical Examples [https://realpython.com/courses/numpy-techniques-practical-examples/] * Using Loguru to Simplify Python Logging [https://realpython.com/courses/using-loguru-to-simplify-python-logging/] Support the podcast & join our community of Pythonistas [https://realpython.com/join]

Reassessing the LLM Landscape & Summoning Ghosts

What are the current techniques being employed to improve the performance of LLM-based systems? How is the industry shifting from post-training towards context engineering and multi-agent orchestration? This week on the show, Jodie Burchell, data scientist and Python Advocacy Team Lead at JetBrains, returns to discuss the current AI coding landscape. In our last conversation, Jodie covered how LLMs were approaching the limits of scaling laws. This time, we recap last year’s big focus on reasoning models and a post-training method called “reinforcement learning from verifiable rewards” (RLVR). We also cover test-time compute, where models spend more time reasoning through steps and considering multiple approaches to solve a problem. We touch on Agent Context Protocol (ACP), agent orchestration layers, and context engineering. We also share some concerns about the hype cycle, maintaining all that code being generated, and running local models. Course Spotlight: Vector Databases and Embeddings With ChromaDB [https://realpython.com/courses/vector-databases-embeddings-chromadb/] Learn how to use ChromaDB, an open-source vector database, to store embeddings and give context to large language models in Python. Topics: * 00:00:00 – Introduction * 00:02:02 – Build a Language-Learning Agent course * 00:02:55 – Update on the past six months of LLMs * 00:05:32 – Reinforcement Learning From Verifiable Rewards * 00:07:32 – Test Time Compute * 00:08:36 – 2025 and the rise of agents * 00:14:24 – Benchmarks shifting * 00:15:23 – Andrew Karpathy and jagged intelligence * 00:19:16 – Not evolving or growing animals but summoning ghosts * 00:23:34 – Diminishing gains in newer models * 00:24:23 – Context Engineering * 00:35:01 – Multi-agent systems and diversity of models * 00:36:56 – Video Course Spotlight * 00:38:34 – Current generation of coding agents * 00:44:00 – Fast vs deep reasoning * 00:45:18 – Agent Context Protocol * 00:50:19 – Working through the hype cycle * 00:55:43 – Open-source contribution pollution * 00:57:21 – Local models * 00:58:36 – Rick Beato comparing how the music industry failed * 01:08:41 – LLMs are an amazing development * 01:11:33 – Keynote talk on AI summers and winters * 01:12:45 – PyCon US and EuroPython * 01:14:11 – Thanks and goodbye Show Links: * AI Agent Course - Build a Language‑Learning Agent with OpenAI, LangGraph, Ollama & MCP - YouTube [https://www.youtube.com/watch?v=j4sNAwrx3kc&t=86s] * Episode #264: Large Language Models on the Edge of the Scaling Laws [https://realpython.com/podcasts/rpp/264/] * Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs [https://arxiv.org/abs/2506.14245] * Reinforcement learning with verifiable rewards (RLVR) [https://labelbox.com/solutions/reinforcement-learning-with-verifiable-rewards/] * What is test-time compute and how to scale it? [https://huggingface.co/blog/Kseniase/testtimecompute] * Overfitting - Wikipedia [https://en.wikipedia.org/wiki/Overfitting] * 2025 LLM Year in Review - karpathy [https://karpathy.bearblog.dev/year-in-review-2025/] * Animals vs Ghosts - karpathy [https://karpathy.bearblog.dev/animals-vs-ghosts/] * Agent Context Protocols Enhance Collective Inference [https://arxiv.org/abs/2505.14569] * Open source AI we use to work on Wagtail - Wagtail CMS [https://wagtail.org/blog/open-source-ai-we-use-to-work-on-wagtail/] * LLMs for Devs: Model Selection, Hallucinations, Agents, AGI – Jodie Burchell - The Marco Show [https://www.youtube.com/watch?v=iRqpsCHqLUI] * Keynote - Can you trust your (large language) model? - Standard error [https://t-redactyl.io/talks/2025-06-29-can-you-trust-your-large-language-model/] * The Human-in-the-Loop is Tired [https://pydantic.dev/articles/the-human-in-the-loop-is-tired] * How AI Will Fail Like The Music Industry - YouTube [https://www.youtube.com/watch?v=YTLnnoZPALI] * “Yes, AI Is a Bubble. There Is No Question.” - The Ringer [https://www.theringer.com/podcasts/plain-english-with-derek-thompson/2026/03/17/yes-ai-is-a-bubble-there-is-no-question] * Keynote: AI is having its moment … again - Jodie Burchell - NDC Copenhagen 2025 [https://www.youtube.com/watch?v=x5s_gsu9Hgs] * PyCon US 2026 [https://us.pycon.org/2026/] * EuroPython 2026 - July 13th-19th 2026 - Kraków, Poland [https://ep2026.europython.eu/] * Jodie Burchell (@t-redactyl.bsky.social) — Bluesky [https://bsky.app/profile/t-redactyl.bsky.social] * Standard error [https://t-redactyl.io/] Level up your Python skills with our expert-led courses: * Vector Databases and Embeddings With ChromaDB [https://realpython.com/courses/vector-databases-embeddings-chromadb/] * Getting Started With Claude Code [https://realpython.com/courses/getting-started-claude-code/] * Getting Started With Google Gemini CLI [https://realpython.com/courses/getting-started-google-gemini-cli/] Support the podcast & join our community of Pythonistas [https://realpython.com/join]