Hilary Mason, CEO of Hidden Door, works with agents across software development and creative projects. Drawing on Richard Hamming’s distinction between science and engineering, she describes agents as “bringing the science back into the engineering and the engineering back into the science.”
When you can build and test more ideas, how do you decide which ones are worth keeping? A plausible analysis still needs scientific judgment, creative output needs taste, and a chart needs to preserve its meaning when an agent revises it.
In this second episode of Show Us Your Agent Skills, Thomas Wiecki & I were joined by Hilary Mason (Hidden Door), Eric Ma (Moderna), Bryan Bischof (Theory Ventures), and Tomasz Tunguz (Theory Ventures). They walk us through the skills, workflows, and setups they use, from protein engineering and creative agents to charting evals, local models, and memory.
You can also find the full episode on Spotify, Apple Podcasts, and YouTube.
👉 Build your own Agentic Software Factory with Eleanor Berger and me. Learn to direct agents that build useful software, check their work, and keep working while you’re away. No coding experience required, and we provide starter projects.
Very early-bird pricing is $750 until January, then early-bird pricing is $850 until February. Use SKILLS2FACTORY10 for 10% off. Every student also gets $500 in Modal credits to run agents in the cloud, experiment with open-weight models, or host what they build. See the next cohort and join us here, or explore all our AI courses and workshops. 👈
In This Episode
* Agentic data science in a reactive notebook. Eric uses marimo pair to explore protein engineering data, connecting mutation effects to a 3D structure while retaining responsibility for the question and interpretation.
* Taste, variation, and creative evals. Hilary explains how context, constraints, and meaningfully different candidates help creative agents produce something worth keeping.
* Charts that survive a follow-up. Bryan shows how agents can break legends, axes, and color semantics across turns, and how bbplot eval turns those failures into improvements to the tool and its documentation.
* Local models and the cost of waiting. Tomasz discusses Pi, Qwen, and the tradeoffs around latency, privacy, offline use, and a minimal agent harness.
* Parallel agents with enough context to help. Dividing the work also means deciding what each agent needs to know and preserving the decisions it makes.
* Memory beyond a single session. Project history, skills, and traces raise questions about security, ownership, onboarding, and offboarding when teams use agents.
Resources
* Show Us Your Agent Skills companion repo
* Cursor context usage breakdown
* Building Agents That Build Themselves
Guest Dossiers
Explore each guest’s field notes, skills, workflows, timestamps, and demo artifacts:
* Eric Ma
How You Can Support Vanishing Gradients
Vanishing Gradients is a podcast, workshop series, blog, and newsletter focused on what you can build with AI right now.
If you want to help keep it going:
* Share this post with a builder who’d find it useful
* Subscribe to the Vanishing Gradients YouTube channel
* Join another Vanishing Gradients workshop
👉 Build your own Agentic Software Factory with Eleanor Berger and me. Learn to direct agents that build useful software, check their work, and keep working while you’re away. No coding experience required, and we provide starter projects.
Very early-bird pricing is $750 until January, then early-bird pricing is $850 until February. Use SKILLS2FACTORY10 for 10% off. Every student also gets $500 in Modal credits to run agents in the cloud, experiment with open-weight models, or host what they build. See the next cohort and join us here, or explore all our AI courses and workshops. 👈
