The IDE has been the center of software development for decades, but Jeff Wang thinks its time in the spotlight is ending. On Zero-Shot Learning, the President of New Enterprise at Cognition described how his team’s workflows are shifting from manually writing every change to delegating work and verifying the results of AI coding agents.
After leading Windsurf and now working with [ Devin](https://devin.ai/) at
For Jeff’s team, AI coding agents prove useful for the work no one volunteers for. Agents respond to event-triggered tasks like reproducing bugs, remediating vulnerabilities, and repairing CI failures, where they effectively reduce noise that distracts developers from planned work.
“If you go into any engineering organization, you don’t want to take away the things they want to do,” Jeff says. “You want to take away the things people don’t want to do. You ask everybody in the development team, ‘Hey, who wants to replicate this bug?’ Nobody is going to raise their hand.”
He says these agents now account for roughly 40% of the workload at Cognition.
Cognition also works with enterprise customers using Devin. At some large banks, Jeff says, Devin automatically fixes 70% of their vulnerabilities.
By agentifying these workflows, Jeff says Cognition merged roughly 700% more pull requests over six months while increasing headcount by only 10%. With agents doing the grunt work, developers don’t need to be the sole operator of each task, fundamentally transforming how each team member spends their day from coding to orchestrating operators. “You might queue up a bunch of agents in the morning, go get lunch, and come back and unblock the ones that are stuck,” he said.
In the interview, Richard Liu, Head of API Products at Anthropic, recounts that across industries, the average developers typically spend eight to 15% of their day doing hands-on coding. The rest goes to coordination, research, and meetings.
With such powerful agentic systems at play, the IDE no longer defines the software development workflow. Instead, engineers decide which work an agent can take on, where it is blocked, and when the result is ready to verify.
An editor gives developers a single console to work from, but agentic systems work across systems and environments. While one agent might investigate a bug while another runs tests and a third waits for access or context, teams need a way to see each agent in action.
OpenAI calls this supporting system a harness: the tools, application context, and feedback loops that help agents work. Cursor’s
Jeff describes a highly accessible version of that environment in Windsurf 2.0, where developers oversee a Kanban board showing what agents are doing and where they are blocked. A team member can start several tasks, return later, and support the agents that need help.
For larger infrastructure work, agents can also move between local and remote environments. A developer might explore an idea locally, make a plan, and then hand the defined task to Devin in the cloud. Jeff says those remote agents run with the dependencies and data they need, allowing work to continue without keeping a developer at the keyboard. Once work is moving across agents and environments, the issue is to determine what is required for the agent to prove the work is done.
When Nancy asked what the new standard primitive would be, Jeff answered, “Probably the ability to prove something is done.”
With AI coding agents, frameworks to validate completed work must be designed before the work begins. Jeff points to the benefits of playbooks, documentation, clear success criteria, and
Jeff says Devin can show the feature running, return passing tests, compare sample queries before and after, and generate a report. The pull request comes back with a record of what happened.
That record can show whether the work passed an established framework. It does not, by itself, show who launched the agent, what it was allowed to access, or who is accountable for the result. In a recent 1Password survey, 51% of developers reported wanting a complete audit trail for agent activity. Another 53% wanted clear accountability for each agent’s actions.
1Password Unified Access closes the visibility, governance, and accountability gaps your existing tools weren't designed to cover. It gives teams a way to secure that gap and issue credentials at runtime, scope access to specific tasks, and attribute access events to the human, agent, or machine involved.
An agent with permission to write to a repository has a different failure mode from one using a person’s administrator credentials across production systems. Jeff says organizations need to know where an agent was launched, who launched it, what it could access, and which changes came from its session.
In the new review loop, engineers define work, provide the right context, scope the agent’s access, and ask it to show what happened. In this workflow, the IDE remains an important part of development but AI coding agents have shifted the focus from the editor to AI orchestration that moves through agents, environments, and evidence.
Subscribe to our developer newsletter to be the first to know about new betas, tools, and resources for developers.