Zach Lloyd on Programmable Agents and Automation

The Warp founder discusses a possible path beyond interactive coding assistance.

ZLZach LloydGuest · Warp
Channel
No Priors: AI, Machine Learning, Tech, & Startups
Published
Oct 23, 2025
Video
0:47
Read
1 min
Original
English
Open on YouTube
Scroll to read and the video shrinks to the bottom-right corner. Captions follow your reading language.
Reading languageAvailable in 2 languages
You're reading the original English.
SUMMARY

In 30 seconds

Lloyd imagines agents integrated into developer workflows and argues that automation may have clearer business value.

  1. 1Programmatic useLloyd wants developers to call agents.
  2. 2DocumentationHe proposes an automation example.
  3. 3Business valueHe contrasts automation and productivity claims.

Takeaways

  1. Agents could be called programmatically.
  2. Routine documentation is one proposed use.
  3. Automation may be easier to evaluate.
FULL TEXT

Read the edited text by chapter

Transcript only
01

Programmable agents

Warp founder Zach Lloyd says he is interested in agents that developers can call programmatically, in addition to interactive use.

Warp founder Zach Lloyd says he is interested in agents that developers can call programmatically, in addition to interactive use.

He offers a proposed example: an agent in a continuous-integration workflow could help keep documentation current when code changes.

02

Automation and value

Lloyd argues that automating disliked routine tasks could benefit developers.

Lloyd argues that automating disliked routine tasks could benefit developers.

From a business perspective, he sees complete automation as potentially easier to evaluate than a general productivity improvement, whose return can be difficult to prove.

More from this channel

38:06EN
No Priors: AI, Machine Learning, Tech, & Startups· Oct 29, 2026Podcast · 3 speakersServal’s Jake Stauch on coding agents for enterprise ITGuest Jake Stauch · Host Sarah Guo, Elad GilStauch explains why Serval is challenging ServiceNow, how it approaches permissions and approvals, and why background agents remain difficult to deploy safely.Enterprise AICoding agentsWorkflow automation+2
1:07EN
No Priors: AI, Machine Learning, Tech, & Startups· Oct 27, 2026PodcastGeorge Kurtz on How AI May Change CyberattacksGuest George KurtzThe CrowdStrike CEO describes his assessment of evolving threats.
39:23EN
No Priors: AI, Machine Learning, Tech, & Startups· Oct 15, 2026Podcast · 2 speakersThe Defenders' Window: Greg Brockman on AI-Generated Knowledge, Drug Discovery, and the New Physics of CybersecurityHost Sarah Guo, Elad GilOpenAI's president explains why solving open math problems is a proof point for science, how proactive agents change product form, and why security spending must exceed software spending.Security & safetyAI securitySafety & governance+3
1:04EN
No Priors: AI, Machine Learning, Tech, & Startups· Oct 14, 2026PodcastWalter Goodwin on the Slow Steps in Chip DesignGuest Walter GoodwinA chip founder explains why automation does not remove every computational bottleneck.SemiconductorsAI cost & performance
1:09:44EN
No Priors: AI, Machine Learning, Tech, & Startups· Oct 9, 2026Podcast · 2 speakers10,000 GB300s for Four Weeks: Reflection’s Open-Model LedgerHost Sarah Guo, Elad GilMisha Laskin tells No Priors how Reflection trained Beam, why reinforcement learning outspent pre-training, and why the West needs its own open weights.Open source & communityOpen-weight modelsReinforcement Learning+3
0:39EN
No Priors: AI, Machine Learning, Tech, & Startups· Oct 8, 2026PodcastMichael Lee on Rethinking Organizations with AIGuest Michael LeeA business leader argues that the opportunity goes beyond faster tasks.