Uploaded November 2026 | Updated November 2026, 4 days ago
Data practitioners and coding experts can act as bridge-builders to subject matter experts and empower them by helping them use the right tools and methods! They can get involved early on to guide, collaborate, and facilitate.
ADD THE DATA SCIENCE HANGOUT TO YOUR CALENDAR HERE: https://pos.it/dsh - All are welcome! We'd love to see you!
This week's guest was Florent Bled, Biostatistician at the Florida Fish and Wildlife Conservation Commission (FWC). Florentβs goal is to ensure scientists have access to the strongest data analysis tools possible. He gets to work on a wide array of projects, encounter bears, manatees, deer, panthers, gators, and have fun with Shiny apps and Quarto. He is also the author of Prelude in R!
Florent on LinkedIn: linkedin.com/in/florent-bled-b3a2a0210
Florent's GitHub: github.com/fbled
Prelude in R: preludeinr.com
MarineQuest at FWC: myfwc.com/research/about/marinequest
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
00:00 Introduction
04:45 "Could you talk to us a little bit about your education?"
08:02 "What is the image behind you? It's so beautiful."
09:43 "What does a typical day or a week look like for you? What areas do you split your time between?"
16:13 "Can you tell us about an example of a problem you solved?"
20:19 "What are challenges that are unique to working as a data scientist in the public sector versus other domains? What are the pros, cons?"
26:30 "What kinds of data do you use in your work? Like remote sensing data, satellite imagery, input from biologists in the field, citizen scientists, collected information, etcetera. And how do you manage all of that?"
30:47 "How does AI play into your research flow? Do you guys actually use that for research purposes?"
32:32 "Favorite and least favorite animal?" (wow, we all agreed ticks and mosquito suck)
36:08 "How do you deploy shiny apps internally? Do you containerize? Do you use Docker? Stuff like that."
40:37 "How are ongoing challenges handled with invasive species and habitats?"
40:46 "Which project has been most rewarding for you?"
45:57 "Do you have a piece of career advice for people? Something you wish you knew when you were getting started or something that might help somebody else entering maybe the biostats space?"
51:41 "if you could wave a magic wand and solve a day-to-day problem, what problem would you solve?" (In which we all agree dates and times are the worst haha)
Data practitioners and coding experts can act as bridge-builders to subject matter experts and empower them by helping them use the right tools and methods! They can get involved early on to guide, collaborate, and facilitate.
ADD THE DATA SCIENCE HANGOUT TO YOUR CALENDAR HERE: https://pos.it/dsh - All are welcome! We'd love to see you!
This week's guest was Florent Bled, Biostatistician at the Florida Fish and Wildlife Conservation Commission (FWC). Florentβs goal is to ensure scientists have access to the strongest data analysis tools possible. He gets to work on a wide array of projects, encounter bears, manatees, deer, panthers, gators, and have fun with Shiny apps and Quarto. He is also the author of Prelude in R!
Florent on LinkedIn: linkedin.com/in/florent-bled-b3a2a0210
Florent's GitHub: github.com/fbled
Prelude in R: preludeinr.com
MarineQuest at FWC: myfwc.com/research/about/marinequest
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
00:00 Introduction
04:45 "Could you talk to us a little bit about your education?"
08:02 "What is the image behind you? It's so beautiful."
09:43 "What does a typical day or a week look like for you? What areas do you split your time between?"
16:13 "Can you tell us about an example of a problem you solved?"
20:19 "What are challenges that are unique to working as a data scientist in the public sector versus other domains? What are the pros, cons?"
26:30 "What kinds of data do you use in your work? Like remote sensing data, satellite imagery, input from biologists in the field, citizen scientists, collected information, etcetera. And how do you manage all of that?"
30:47 "How does AI play into your research flow? Do you guys actually use that for research purposes?"
32:32 "Favorite and least favorite animal?" (wow, we all agreed ticks and mosquito suck)
36:08 "How do you deploy shiny apps internally? Do you containerize? Do you use Docker? Stuff like that."
40:37 "How are ongoing challenges handled with invasive species and habitats?"
40:46 "Which project has been most rewarding for you?"
45:57 "Do you have a piece of career advice for people? Something you wish you knew when you were getting started or something that might help somebody else entering maybe the biostats space?"
51:41 "if you could wave a magic wand and solve a day-to-day problem, what problem would you solve?" (In which we all agree dates and times are the worst haha)

![querychat in R: Query Your Data with Natural Language | Shiny + LLMs | Veerle van Leemput
Learn how to use querychat, an R package that lets users query data using natural language instead of predefined filters. Perfect for data scientists who want to build flexible, interactive Shiny dashboards without anticipating every possible user question.
In this tutorial, youll discover:
- How querychat translates natural language to SQL using LLMs
- Setting up querychat in seconds with your data
- Building custom Shiny interfaces with reactive data frames
- Why its reliable, transparent, and safe for production use
- Enterprise deployment with Azure, AWS Bedrock, or Google Vertex AI
Key Features:
β Drop-in Shiny component
β Works with any DBI-compatible database
β Read-only by design for data safety
β Full SQL transparency for reproducibility
β Supports Claude, GPT, Gemini via ellmer
Resources:
- querychat Documentation: [https://posit-dev.github.io/querychat/py/index.html]
- Blog Post: Where Questions Become Queries [https://shiny.posit.co/blog/posts/querychat-python-r/
- Github repo: [https://github.com/posit-dev/querychat/tree/main/pkg-r]
Perfect for R users working with Shiny, data exploration, and interactive analytics.
Timestamps
00:00 - Introduction: The Dashboard Problem
00:50 - Why Dashboards Cant Answer Every Question
01:47 - What is querychat?
02:46 - Getting Started (Installation & Setup)
03:08 - API Key Setup (Claude, GPT, Gemini)
03:20 - First querychat App in 5 Lines of Code
04:04 - Live Demo: Querying Data with Natural Language
05:01 - How querychat Works Under the Hood
06:44 - Four Key Benefits (Reliability, Transparency, Reproducibility, Safety)
07:37 - Tool Calling & DuckDB Integration
08:46 - Building Custom Shiny Interfaces
09:01 - Customizing querychat Behavior (Greetings, Data Descriptions, Instructions)
11:00 - Creating Custom Dashboards with Reactive Data Frames
12:00 - Complete App Structure Walkthrough
13:10 - Safety & Security Deep Dive
14:00 - Enterprise Deployment (Azure, AWS, Google Vertex AI)
15:12 - Resources & Documentation querychat in R: Query Your Data with Natural Language | Shiny + LLMs | Veerle van Leemput](https://i.ytimg.com/vi/EQjr0p25KS8/mqdefault.jpg)








