惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

U
Unit 42
罗磊的独立博客
博客园 - 聂微东
T
The Blog of Author Tim Ferriss
博客园 - 司徒正美
Stack Overflow Blog
Stack Overflow Blog
F
Fortinet All Blogs
A
About on SuperTechFans
腾讯CDC
Apple Machine Learning Research
Apple Machine Learning Research
B
Blog RSS Feed
IT之家
IT之家
V
Visual Studio Blog
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
宝玉的分享
宝玉的分享
C
Check Point Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
Vercel News
Vercel News
爱范儿
爱范儿
Microsoft Security Blog
Microsoft Security Blog
月光博客
月光博客
T
Tailwind CSS Blog
The Cloudflare Blog
Hugging Face - Blog
Hugging Face - Blog

The New Stack | DevOps, Open Source, and Cloud Native News

Agentic development hinges on verification. For cloud-native software, that is a runtime problem. AI agents need infrastructure: Why Europe’s regional cloud strategy matters Transform your AI coding agent into a deterministic Java Spring expert WeAreDevelopers is coming to the US to give unsung developers a bigger voice Cleaner AI training data, fewer bugs: Sonar’s SonarSweep explained Observability overload is drowning engineers Google’s DiffusionGemma is 4x faster than its other Gemma models Fable 5: Guardrails and burn rate are annoying users, who say it’s still better than Opus 4.8 The Anthropic leader who built Claude Code says he ditched prompting — now he just writes loops. AWS can now mathematically prove your VMs are isolated Microsoft pulled 73 GitHub repos after malware attack — but still won’t say who’s compromised Databricks wants to kill the “email me a file” problem for AI agent skills Ramp bets forward deployed engineers can do what off-the-shelf finance AI can’t Git real: AI agents aren’t just for solo developers anymore Anthropic launches Claude Mythos/Fable 5, but you better try it soon This AI agent startup ditched Anthropic for DeepSeek — and says it’s saving millions When your data model is the bottleneck: lessons from Medium’s feature store How long before we stop reading the code? The tokenmaxxing party is over, and Revenium is mopping up How AI is solving the memory crunch it created Microsoft’s pitch to enterprises: Ditch Azure Repos for GitHub, despite its rocky reliability record Claude Code’s biggest upgrade yet ran 5 agents at once — here’s what happened Why Anthropic just doubled Claude Cowork limits at no charge For years, Apache Cassandra handed this work to your team — 6.0 takes it back “A dangerous combination”: The 2 factors that can “corrupt” AI agent workflows With Foundry, Microsoft bets the enterprise AI battle is about reliability, not capability Microsoft unlocks Visual Studio for developers left behind by its own AI AI teams now deploy 1,000 times a month. Your pipeline wasn’t built for that. Microsoft just made the agent runtime free — and kept everything around it “Whoever builds the most joyous product wins”: The agent war begins
Gusto Cofounder: An AI agent that runs payroll, HR, and b...
Adrian Bridgwater · 2026-06-19 · via The New Stack | DevOps, Open Source, and Cloud Native News

Almost every startup or small business today has a wingperson, a principal working partner, or a co-founder. 

When it comes to the core processes needed to make that business operational, having a dynamic working alliance with another person — where business actions often stem from both parties’ unspoken instincts — is what often leads to success.

Eddie Kim, co-founder and CTO of payroll and HR platform company Gusto, tells The New Stack that this fundamental business reality is exactly why his company’s latest software release is called Gusto Cofounder. He drew inspiration from his mother and father, who worked as co-founders of a mom-and-pop shop in Southern California.

“Gusto is a platform for small businesses,” Kim says. “We focus on the back office aspects of what’s needed to keep things operational every day. So that’s functions such as payroll, benefits, human resources, time scheduling and central accounting tasks.”

“Gusto Cofounder isn’t an AI assistant or copilot, nor is it a glorified search engine that works in a basic reactive way i.e. you ask it something and it returns an answer. This is ‘someone’ that business owners can reach out to at any time and actually proactively help with things that will grow the business.”
—Eddie Kim, Gusto.

The original cofounders: mom-and-pop

Looking back to his childhood, Kim describes coming home from school and being left to hang out in the back office of the family business to do his homework. With his dad at the front of the office, his mom was in the back doing payroll, insurance billing, bookkeeping, and appointment scheduling. 

She was also the receptionist and the office manager, a strong woman, the original co-founder in his eyes.

“Gusto Cofounder isn’t an AI assistant or copilot, nor is it a glorified search engine that works in a basic reactive way, i.e., you ask it something, and it returns an answer,” Kim says. “This is ‘someone’ that business owners can reach out to at any time and actually proactively help with things that will grow the business.”

In terms of functions, users can talk to Gusto Cofounder just as they would talk to a human co-founder. Users primarily interact with the software via text messaging or Slack, and it has access to all data that an organization has already entrusted to Gusto.

“Gusto does a lot of things,” explains Kim. “Not just in payroll, but in areas including health insurance, business insurance, workers’ compensation, time scheduling and HR. So, because that means access to sensitive data (people’s salaries and payroll) we have a robust consent framework to enable our platform to securely move billions of dollars every single day, accurately and safely.”

Explicitly secured permission within defined data scopes

To keep entrusted sensitive information safe, Gusto Cofounder’s consent tooling requires “explicit permission” from human users to perform actions, and this stipulation cannot be circumvented. Permissions are deterministically gated through the Gusto codebase, and organizations can set granular permissions for each of the “data scopes” (a technology that defines the boundaries of a dataset) to govern data access.

Once a small business begins to elevate Gusto Cofounder into its business processes, they can start to allow the software to perform its work with more autonomy. Once actions have been reviewed, users can set thresholds so that the software no longer requires permissions to perform its work.

“It’s the best code I’ve written in my whole entire life. It is a really solid product and we’ve built it much faster than I ever thought would have been possible. I think the future of development is not just engineers writing code, it’s everybody, whether you’re an engineer, a product manager, a designer, or a data professional.” – Eddie Kim.

“Gusto Cofounder doesn’t just do things that you do within Gusto,” clarifies Kim. “It will connect to third-party systems, such as Google Workspace, to read data out of an organization’s Google Sheets and perform the necessary calculations (for payroll, or other tasks) in exactly the way a business owner would do it. It then puts that into Gusto and runs the payroll, runs the calculations, and texts the business owner a text saying ‘here’s the payroll numbers for this week’, all neatly done.” 

Eight weeks’ work, with Claude Code

Kim explains that the software itself was built using Claude Code by five people in just eight weeks. 

“It’s the best code I’ve written in my whole entire life. It is a really solid product, and we’ve built it much faster than I ever thought would have been possible,” pledges Kim. “I think the future of development is not just engineers writing code; it’s everybody, whether you’re an engineer, a product manager, a designer, or a data professional.”

Third-party connections and beyond

Looking ahead, Kim wants to add more connectors to third-party applications. He also wants to encourage customers to use the platform to codify their work processes and offer other business functions common to industry-specific use cases. 

“Automations created in – let’s say – a dental practice on the East Coast might share some similarities with what a dental practice needs in the Midest – for example because of compliance reasons, so we want developers to be able to build on top of our platform in the most modular way possible and be able to choose the parts that work best for them in any given customer use case scenario,” concludes Kim.

Would that one day lead us to a point where we talk about the Google Play App Store and the Gusto Cofounder store? Kim is an upbeat kind of guy; he’s not going to say he doesn’t like that idea. 

YOUTUBE.COM/THENEWSTACK

Tech moves fast, don't miss an episode. Subscribe to our YouTube channel to stream all our podcasts, interviews, demos, and more.

Created with Sketch.