Skip to main content
Software Engineering Daily

AI at Anaconda with Greg Jennings

49 min episode · 2 min read
·
Greg Jennings

Episode

49 min

Read time

2 min

Topics

Investing, Fundraising & VC, Leadership

AI-Generated Summary

Key Takeaways

  • Context-Aware Notebook Assistant: Anaconda Assistant eliminates copy-paste workflows by automatically injecting notebook context (data frames, columns, variables, errors) into AI prompts, enabling inline code generation and automatic error fixing with over 50,000 active users.
  • Prompt Optimization Over Fine-Tuning: The team achieves reliable code generation through extensive prompt engineering and context injection rather than model fine-tuning, tracking error rates and iteratively adjusting prompts to reduce failures in specific workflows like data visualization.
  • Package Management Evolution: Future package management must expand beyond Python dependencies to include AI models as dependencies, allowing developers to conda install applications with embedded models, agents, and runtime environments through tools like AI Navigator.
  • Evaluation Framework Requirements: Organizations building LLM applications need custom evaluation frameworks based on real user interactions and topic modeling, as even the best models fail unpredictably and require domain-specific testing beyond generic benchmarks to ensure reliability.

What It Covers

Greg Jennings, VP of Engineering and AI at Anaconda, discusses how the company integrates AI assistants into Jupyter notebooks and Excel workflows, enabling context-aware code generation, error fixing, and democratizing data science capabilities.

Key Questions Answered

  • Context-Aware Notebook Assistant: Anaconda Assistant eliminates copy-paste workflows by automatically injecting notebook context (data frames, columns, variables, errors) into AI prompts, enabling inline code generation and automatic error fixing with over 50,000 active users.
  • Prompt Optimization Over Fine-Tuning: The team achieves reliable code generation through extensive prompt engineering and context injection rather than model fine-tuning, tracking error rates and iteratively adjusting prompts to reduce failures in specific workflows like data visualization.
  • Package Management Evolution: Future package management must expand beyond Python dependencies to include AI models as dependencies, allowing developers to conda install applications with embedded models, agents, and runtime environments through tools like AI Navigator.
  • Evaluation Framework Requirements: Organizations building LLM applications need custom evaluation frameworks based on real user interactions and topic modeling, as even the best models fail unpredictably and require domain-specific testing beyond generic benchmarks to ensure reliability.

Notable Moment

Jennings explains that all generative AI models hallucinate, but some hallucinations prove valuable—the key challenge involves helping users validate AI-generated code and data interpretations to avoid subtle errors like incorrect SQL aggregations or statistical misinterpretations.

Know someone who'd find this useful?

Episode Transcript

Anaconda is a software company that's well known for its solutions for managing packages, environments, and security in large scale data workflows. The company has played a major role in making Python based data science more accessible, efficient, and scalable. Anaconda has also invested heavily in AI tool development. Greg Jennings is the VP of engineering and AI at Anaconda. He joins the podcast with Kevin Ball to talk about the tooling ecosystem around AI app development, the Anaconda toolbox, the rapidly evolving role of AI and engineering, and more. Kevin Ball or Kay Ball is the vice president of engineering at Mento and an independent coach for engineers and engineering leaders. He cofounded and served as CTO for two companies, founded the San Diego JavaScript meetup, and organizes the AI in action discussion group through Latent Space. Check out the show notes to follow Keball on Twitter or LinkedIn, or visit his website, keball.llc. Greg, welcome to the show. Hi, Kevin. Very nice to meet you. Yeah. Excited to have you on here. Let's maybe start with a little bit about you. Can you share some of your background and how you got involved with Anaconda? Sure. So I started as a graduate out of physics and material science out of graduate school and went to work at a large consulting organization where we were building sort of complex models and simulations for mostly government organizations to help them do things like figure out complex dependencies and procurement schedules and anticipate what the capabilities that they would gain from picking platform a versus platform b and balancing costs. And so though I hadn't had written mostly simulation code in graduate school, but I started writing a lot more, I guess, user facing code to kind of interact with end users and expose some of those capabilities to end users. So during my time there, I briefly found Python. We were writing things in Java Swing at the time. It was a painful experience. So we grew a team there, then ultimately decided along with a few other colleagues to set out and start to forge our path in a startup world as some people do and started to then explore Python. And so then at that point, stepping away, I really sort of dove into Python much more deliberately and found that I could be way more productive with it. Of course, some people have found that they love type languages for large projects. But for me, I'm trying to move very fast. It was extremely helpful to be writing in Python, and so I started writing a lot of things in Python. Even I found when I started doing consulting work that also leveraged my Java background, I would oftentimes write the algorithm in Python first and then port that algorithm over to Java. And I found that was actually faster to do very often. And the thing that I found that really made it faster to do …

Get the full transcript (8,858 words) + summary by email — free

One-time email with the complete transcript and AI summary of this episode. No account needed.

One email, no spam. We’ll also show you what SignalCast does.

Browse all Software Engineering Daily transcripts →

You just read a 3-minute summary of a 46-minute episode.

Get Software Engineering Daily summarized like this every Monday — plus up to 2 more podcasts, free.

Pick Your Podcasts — Free

Keep Reading

Books, tools, and gear mentioned in this episode

SignalCast may earn commission on purchases via these links.

Tools

  • discusses how the company integrates AI assistants into Jupyter notebooks and Excel workflows
  • by Anaconda

    Anaconda Assistant eliminates copy-paste workflows by automatically injecting notebook context (data frames, columns, variables, errors) into AI prompts, enabling inline code generation and automatic error fixing with over 50,000 active users.
  • AI NavigatorBy guest

    by Anaconda

    developers to conda install applications with embedded models, agents, and runtime environments through tools like AI Navigator.

More from Software Engineering Daily

We summarize every new episode. Want them in your inbox?

Similar Episodes

Related episodes from other podcasts

Explore Related Topics

This podcast is featured in Best Cybersecurity Podcasts (2026) — ranked and reviewed with AI summaries.

Read this week's Investing & Markets Podcast Insights — cross-podcast analysis updated weekly.

You're clearly into Software Engineering Daily.

Every Monday, we deliver AI summaries of the latest episodes from Software Engineering Daily and 192+ other podcasts. Free for one show.

Start My Monday Digest

No credit card · Unsubscribe anytime