UpTrajectory Review
The recent Camp AI event in San Francisco highlighted how AI agents are transforming engineering teams. Various startups showcased their experiences in restructuring processes to integrate AI, revealing both successes and challenges. The discussions emphasized the rapid adoption of AI in engineering roles, with leaders noting that smaller teams can now handle larger projects thanks to AI support.
For small business operators, this shift towards AI-driven engineering is crucial. It suggests that embracing AI can lead to more efficient workflows and potentially reduce team sizes while increasing output. However, the caution around AI-generated code and the need for robust review processes cannot be overlooked. As Paul Klein IV pointed out, the risk of deploying unvetted AI outputs is significant, especially in customer-facing applications. Operators should consider how they can integrate AI responsibly into their workflows to enhance productivity without compromising quality.
““If AI is not doing your whole job it’s a skill issue at this point,” said Klein.” — InfoWorld
Takeaway: Embrace AI to enhance productivity, but prioritize robust review processes to mitigate risks.
From the original item — InfoWorld:
I counted at least 10 events in San Francisco last night aimed at matching AI startups with VCs. Just another Thursday.
But what made Camp AI’s “Agents at Work” event (hosted by Auth0) stand out was its showcase of companies that are in various stages of reorganizing their engineering processes around AI agents. Browserbase, Mastra, Fireworks AI, Drata, Mya, MindFort, and Corridor are all part of the vendor ecosystem trying to enable secure and performant agentic AI, but the most revelatory stories were their own successes and the challenges they faced restructuring their engineering orgs for agents.
Paul Klein IV, founder and CEO of Browserbase, delivered the night’s most memorable line while discussing the speed of AI adoption inside engineering teams. “If AI is not doing your whole job it’s a skill issue at this point,” said Klein.
Abhi Aiyer, founder and CTO of Mastra, said the result is dramatically smaller teams capable of executing much larger scopes of work. “You can have one person run a whole feature project because they have an army of one to infinity AI agents behind them,” said Aiyer.
Several panelists argued that AI systems are now generating software faster than organizations can safely review and operationalize it. Aiyer said that engineering teams are opening significantly more pull requests while review throughput becomes the new bottleneck.
Klein stressed the importance of throttling experimental AI output to appropriately lower risk in deployment environments. “If you are in the critical path and customer facing, no slop,” he said. “If you are not critical path, not customer facing, slop away.”
Speakers repeatedly emphasized observability and accountability as challenge areas for autonomous agents. Rob Ferguson, VP of technology and strategy at Fireworks AI, argued that ownership cannot disappear simply because AI generated the output. “It doesn’t matter if you typed it or prompted it, you own it,” Ferguson said.
Bhavin Shah, VP of AI product at Drata, said enterprise AI systems increasingly require detailed auditability. “The agent is constantly telling the user, here is the action I’m taking, here is what I’ve done,” he said.
Auth0’s demos focused heavily on authentication, authorization, and runtime controls for AI agents interacting with APIs and Model Context Protocol (MCP) servers. The company’s new MCP authentication product, which reached general availability this week, is designed to secure how agents interact with MCP servers and APIs.
Monica Bajaj, SVP of engineering at Okta, emphasized the importance of minimizing risk exposure as agents operate autonomously across enterprise systems. “How do we make sure that those tokens are not long-lived tokens?” she asked, adding “We make sure that the blast radius is minimum.”
Klein argued that many AI limitations today are no longer about the underlying models themselves. “The overhang of AI capabilities is actually an infrastructure problem, not a model quality problem,” he said.
Klein noted that orchestration, tooling, permissions, and training data pipelines increasingly determine whether AI systems succeed in production.
Mya demonstrated an AI program manager that aggregates Slack, Gmail, Jira, GitHub, and meeting notes to automatically track project risk and operational status. MindFort showed autonomous penetration testing agents designed to continuously probe enterprise applications for vulnerabilities during development and runtime. And Corridor demonstrated AI security guardrails that pre index codebases and inject secure coding guidance directly into AI coding workflows.
Mastra discussed redesigning developer documentation and frameworks specifically for AI agents rather than human developers.