Uploaded March 2026 | Updated November 2026, 9 hours ago
The Data Science Lab is a live weekly call. Register at pos.it/dslab! Discord invites go out each week on lives calls. We'd love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Hadley Wickham who uses Posit's new Posit Assistant (not to be confused with Positron Assistant or Databot in Positron) in RStudio to analyze the week's TidyTuesday dataset.
Hosting crew from Posit: Libby Heeren, Isabella Velasquez, Hadley Wickham
Hadley's Blueskey: https://bsky.app/profile/hadley.nz
Hadley's LinkedIn: linkedin.com/in/hadleywickham
Hadley's GitHub: github.com/hadley
Hadley's website: hadley.nz
Resources mentioned in the video and chat:
π Posit AI / Posit Assistant waitlist β posit.co/products/ai
π Tidy Tuesday Dataset β github.com/rfordatascience/tidytuesday/blob/main/data/2026/2026-02-17/readme.md#agricultural-production-statistics-in-new-zealand
π nanoparquet (R package) β nanoparquet.r-lib.org
π Databot β positron.posit.co/databot.html
π wbstats (R package for WorldBank API) β github.com/gshs-ornl/wbstats
π World Bank NZ data β data.worldbank.org/indicator/SP.POP.TOTL?locations=NZ
π Hadley & Joe's posit::conf talk ft. Hadley's demo of ggbot2 β youtube.com/watch?v=tSFHQWGyRzo
π Wikimedia: New Zealand Total Population β commons.wikimedia.org/wiki/Data:New_Zealand_Total_Population.tab
π Posit Conf Talk: James Wade's "Disposable Shiny Apps" β youtube.com/watch?v=smnrmTtoiOM
π Hadley's unhinged {genzplyr} (R package) βgithub.com/hadley/genzplyr
π Simon Couch's blog post on evaluating LLMs β posit.co/blog/python-llm-evaluation
π Garrick Aden-Buie mentioned working on a collection of skills β github.com/posit-dev/skills
π Max Woolf's blog post "Does Offering ChatGPT a Tip Cause it to Generate Better Text?" β minimaxir.com/2024/02/chatgpt-tips-analysis
π Cat Hicks's skill for coding agents that lets you learn from the agent β github.com/DrCatHicks/learning-opportunities (but also see her great thread on bluesky! https://bsky.app/profile/grimalkina.bsky.social/post/3mevvbm3a6s26)
βΊ Subscribe to Our Channel Here: bit.ly/2TzgcOu
Follow Us Here:
Website: posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps of Questions / Topics
00:00 Introduction
01:17 Posit Assistant and using an agents.md file
02:54 Downloading TidyTuesday data using Posit Assistant
04:38 "Why use Parquet files over CSVs?"
07:11 Oops, switching Hadley's mic, sorry!
09:27 Creating a visualization of sheep populations
10:28 "When would you switch models to Opus?"
13:28 "Do we have a Gen-Z human in the loop to verify the syntax?" (We did, folks, we did)
13:54 "How many bow ties does Hadley own?" π π
14:24 Asking the AI to retrieve *real* New Zealand population data
15:25 "Can the Posit Assistant use voice to text so people don't have to type...?"
18:40 "What's the purpose of the agents.md file and what goes in there?"
20:59 "How does posit AI in RStudio compare with the current positron AI assistants?"
22:39 "Will all the code generated by Posit assistant be stored in the session somehow to let somebody review what the agent generated?"
26:08 Having the AI create a Quarto report
26:54 "Does Posit Assistant also support Skills Files?"
27:49 "Were we always able to add agents.md in Positron too?"
28:17 "Did Hadley choose the name agents for agents.md or does each session have an agents file similar to having a README.md?"
29:57 Fixing the AI-chosen plot theme
31:55 "Is any of the stuff that it's put in the report in Gen-Z speak, or is it only what it's returning to you in the chat?"
33:24 "Can Posit Assistant create a renv as well?"
35:39 "Is Claude also the best for Python code?"
36:20 "If you add a behavior or a requirement to agents.md, does it take that new info in on the fly as you continue prompting?"
37:40 "What if you ask the agent *why* something happened?"
40:31 Investigating AI speculations about dairy cattle numbers
41:15 "Do you still need to know how to code in 2026?"
41:42 "Does using caps lock increase the likelihood that the LLM is going to listen to your agents.md file?"
45:47 "Could Hadley have done this faster without an AI?"
47:26 Hadley had AI do text clustering on image descriptions (previous TidyTuesday dataset)
48:41 Hadley had AI make a Shiny app to explore cluster sizes (previous TidyTuesday dataset)
52:53 "If one of the best ways to learn how to read code is to write code, what's gonna happen if we're writing it less?"
54:05 Wrap up and Posit AI waitlist information
The Data Science Lab is a live weekly call. Register at pos.it/dslab! Discord invites go out each week on lives calls. We'd love to have you!
The Lab is an open, messy space for learning and asking questions. Think of it like pair coding with a friend or two. Learn something new, and share what you know to help others grow.
On this call, Libby Heeren is joined by Hadley Wickham who uses Posit's new Posit Assistant (not to be confused with Positron Assistant or Databot in Positron) in RStudio to analyze the week's TidyTuesday dataset.
Hosting crew from Posit: Libby Heeren, Isabella Velasquez, Hadley Wickham
Hadley's Blueskey: https://bsky.app/profile/hadley.nz
Hadley's LinkedIn: linkedin.com/in/hadleywickham
Hadley's GitHub: github.com/hadley
Hadley's website: hadley.nz
Resources mentioned in the video and chat:
π Posit AI / Posit Assistant waitlist β posit.co/products/ai
π Tidy Tuesday Dataset β github.com/rfordatascience/tidytuesday/blob/main/data/2026/2026-02-17/readme.md#agricultural-production-statistics-in-new-zealand
π nanoparquet (R package) β nanoparquet.r-lib.org
π Databot β positron.posit.co/databot.html
π wbstats (R package for WorldBank API) β github.com/gshs-ornl/wbstats
π World Bank NZ data β data.worldbank.org/indicator/SP.POP.TOTL?locations=NZ
π Hadley & Joe's posit::conf talk ft. Hadley's demo of ggbot2 β youtube.com/watch?v=tSFHQWGyRzo
π Wikimedia: New Zealand Total Population β commons.wikimedia.org/wiki/Data:New_Zealand_Total_Population.tab
π Posit Conf Talk: James Wade's "Disposable Shiny Apps" β youtube.com/watch?v=smnrmTtoiOM
π Hadley's unhinged {genzplyr} (R package) βgithub.com/hadley/genzplyr
π Simon Couch's blog post on evaluating LLMs β posit.co/blog/python-llm-evaluation
π Garrick Aden-Buie mentioned working on a collection of skills β github.com/posit-dev/skills
π Max Woolf's blog post "Does Offering ChatGPT a Tip Cause it to Generate Better Text?" β minimaxir.com/2024/02/chatgpt-tips-analysis
π Cat Hicks's skill for coding agents that lets you learn from the agent β github.com/DrCatHicks/learning-opportunities (but also see her great thread on bluesky! https://bsky.app/profile/grimalkina.bsky.social/post/3mevvbm3a6s26)
βΊ Subscribe to Our Channel Here: bit.ly/2TzgcOu
Follow Us Here:
Website: posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps of Questions / Topics
00:00 Introduction
01:17 Posit Assistant and using an agents.md file
02:54 Downloading TidyTuesday data using Posit Assistant
04:38 "Why use Parquet files over CSVs?"
07:11 Oops, switching Hadley's mic, sorry!
09:27 Creating a visualization of sheep populations
10:28 "When would you switch models to Opus?"
13:28 "Do we have a Gen-Z human in the loop to verify the syntax?" (We did, folks, we did)
13:54 "How many bow ties does Hadley own?" π π
14:24 Asking the AI to retrieve *real* New Zealand population data
15:25 "Can the Posit Assistant use voice to text so people don't have to type...?"
18:40 "What's the purpose of the agents.md file and what goes in there?"
20:59 "How does posit AI in RStudio compare with the current positron AI assistants?"
22:39 "Will all the code generated by Posit assistant be stored in the session somehow to let somebody review what the agent generated?"
26:08 Having the AI create a Quarto report
26:54 "Does Posit Assistant also support Skills Files?"
27:49 "Were we always able to add agents.md in Positron too?"
28:17 "Did Hadley choose the name agents for agents.md or does each session have an agents file similar to having a README.md?"
29:57 Fixing the AI-chosen plot theme
31:55 "Is any of the stuff that it's put in the report in Gen-Z speak, or is it only what it's returning to you in the chat?"
33:24 "Can Posit Assistant create a renv as well?"
35:39 "Is Claude also the best for Python code?"
36:20 "If you add a behavior or a requirement to agents.md, does it take that new info in on the fly as you continue prompting?"
37:40 "What if you ask the agent *why* something happened?"
40:31 Investigating AI speculations about dairy cattle numbers
41:15 "Do you still need to know how to code in 2026?"
41:42 "Does using caps lock increase the likelihood that the LLM is going to listen to your agents.md file?"
45:47 "Could Hadley have done this faster without an AI?"
47:26 Hadley had AI do text clustering on image descriptions (previous TidyTuesday dataset)
48:41 Hadley had AI make a Shiny app to explore cluster sizes (previous TidyTuesday dataset)
52:53 "If one of the best ways to learn how to read code is to write code, what's gonna happen if we're writing it less?"
54:05 Wrap up and Posit AI waitlist information






![The one skill AI cant replace | Alexander Schacht | Data Science Hangout
ADD THE DATA SCIENCE HANGOUT TO YOUR CALENDAR HERE: https://pos.it/dsh - All are welcome! Wed love to see you!
We were recently joined by Alexander Schacht, Senior Director at Cytel and Host of The Effective Statistician, to chat about the tensions between technical and executive work, how to increase visibility in your organization, and ethical considerations in data science (specifically regarding patient data).
In this Hangout, we explore the engine vs. wheels analogy for data professionals. Alexander explains that while technical skills (the engine) are vital, they are useless without communication and leadership skills (the wheels) to put that power on the road. He shares advice on how to stop being the p-value police and instead build trust by understanding stakeholders fears, hopes, and business goals.
Resources mentioned in the video and zoom chat:
π The Effective Statistician Podcast β https://theeffectivestatistician.com/podcast/
π Alexanderβs Book: How to be an Effective Statistician β https://theeffectivestatistician.com/book-launch/
π Nonviolent Communication (Book Recommendation from Libby) β https://www.amazon.com/Nonviolent-Communication-Language-Life-Changing-Relationships/dp/189200528X
If you didnβt join live, one great discussion you missed from the zoom chat was about the pressure to look busy versus actually delivering results, sparked by Alexanders advice to decline more meetings. The chat debated the difficulty of doing this in a grind culture and how to prioritize signal over noise. Let us know below if youβd like to hear more about this topic!
βΊ Subscribe to Our Channel Here: https://bit.ly/2TzgcOu
Follow Us Here:
Website: https://www.posit.co
Hangout: https://pos.it/dsh
The Lab: https://pos.it/dslab
LinkedIn: https://www.linkedin.com/company/posit-software
Bluesky: https://bsky.app/profile/posit.co
Thanks for hanging out with us! π
Timestamps:
00:00 Introduction
05:28 What are some of the tensions between technical work and executive type work?
08:56 Do you have any advice for increasing visibility where bias or prejudice exists?
14:26 Have you been able to influence the top down people?
18:31 How do you reconcile with some of the ethical things about work?
23:00 How can I constructively deal with concerns managed upwards towards me as a manager?
30:15 What are some strategies that you use to manage expectations?
34:23 Most valuable skill set to invest in this age where Gen AI can do so much?
40:14 Where would people acquire the niche technical skills without getting experience?
41:57 What is your advice to look for in a prospective employer or manager?
45:34 How do you juggle both [being an employee and a business owner] at the same time?
48:56 Have you experienced stakeholders trusting AI more than they trust experts?
52:19 How do you get a feeling for discussions you need to go to versus things that will work themselves out? The one skill AI cant replace | Alexander Schacht | Data Science Hangout](https://i.ytimg.com/vi/Pa4QEhDU0wQ/mqdefault.jpg)



