The development environment is undergoing a radical shift at the intersection of software engineering and AI. No longer just about writing clean code, developer experience today is about crafting systems that collaborate with humans and increasingly with AI agents.

This was the central theme of a panel conversation titled “Investing in Dev Tools in the Age of AI” that featured Jesse Robbins (Heavybit), Peter Zakin (Codeium), Kenneth Auchenberg (AlleyCorp), and Ivan Burazin (Daytona) at the Infobip Shift Miami conference.

Speakers first reflected on how developer experience has evolved—from desktop to mobile, from static tools to dynamic, collaborative environments. But as Jesse put it, we’re now entering a new phase where delegation is the new automation.

Traditionally, improving developer experience meant offering excellent documentation, strong community support, clear APIs, and plenty of example code. But today, that’s not enough, Jesse points out:

If you’re building software now, you’re not just designing for humans. You’re designing for agents, too. And they need the same things—documentation, context, and clarity of intent.

Jesse compared the rise of autonomous agents in dev workflows to a new kind of SEO, where developers optimize their tools for discoverability and cooperation with AI agents. Whether it’s delegating tasks, workflows, or entire design processes, success now depends on how well tools can communicate their purpose to humans and machines alike.

Engineers as Fleet Generals

This shift is redefining what it means to be a developer. Kenneth described it in striking terms:

We’re all going from being software engineers writing code to model operators—code composers. It’s like being an art director, hovering over the shoulder of your agents.

He likened the future of development to managing a “fleet” of AI workers, where engineers must learn to orchestrate, debug, and direct multiple agents:

Every engineer is becoming a fleet general. You’re not just an IC anymore—managing autonomous contributors.

That may sound intimidating, but Peter argued that humans will continue to play a central, even irreplaceable role:

What remains when AI removes all the toil—the boring work? Humans are still responsible for the labor. We’re the backstop. We’re the audit log. And that’s not going away.

As the panelists agreed, there’s an emerging class of problems—ethics, oversight, accountability—that only humans can solve. Responsibility remains a human job even in a world run by autonomous agents.

Cursor, Windsurf, and the Agent Race

The latter part of the discussion focused on recent AI-native tools that are transforming the developer landscape—Cursor and Windsurf. Cursor, an enhanced version of VS Code utilizing AI agents, is now valued at $9 billion.

Windsurf, a similar tool, was just acquired by OpenAI for $3 billion. These figures raised a provocative question often heard in investor conversations: “What if AWS or Microsoft builds this?”

Kenneth, who was part of the original 12-person VS Code team, had a candid response:

Cursor and Windsurf aren’t really in the business of building a code editor. They’re using the VS Code base as a shipping vehicle. The real innovation is the agent.

Building an editor like VS Code from scratch is a massive endeavor, one only a few tech giants could undertake. But the opportunity now lies in building the best agent experience on top of that infrastructure, Kenneth points out:

We’re moving toward an agentic future where everyone will have agents on their engineering team. That’s the business. That’s the value.

This paradigm shift means the next battle in dev tools isn’t about IDEs—it’s about who builds the most effective co-pilot.

Open Source as the Foundation

Jesse pointed to the importance of the open-source ecosystem in enabling this transition. He’s an investor in Continue, an open-source plugin integrating VS Code and JetBrains tools to bring AI into developers’ everyday workflows:

Because of this open-source ecosystem, I started writing code again. It felt joyful. This moment in time makes that possible. You get prompted, and you learn.

It’s what I remember loving about development. Experiencing joy in collaborating with tools instead of fighting them may be the most important change of all.

The developer landscape is undergoing a seismic shift, driven not only by breakthroughs in AI but also by developers’ changing roles. Whether through tools like Cursor and Windsurf or evolving team dynamics that blend engineering with product thinking, the panelists painted a future where developers are not just builders but strategic decision-makers.

In an era where AI is both collaborator and competitor, the key challenge remains: staying adaptable, curious, and aligned with long-term value, regardless of whether you’re coding the next billion-dollar product or redefining what it means to build software.

The post The Future of Dev Tools is Autonomous, Engineers Will Become Fleet Generals appeared first on ShiftMag.

“In the past, some VCs would fund popular open source frameworks that said, “we’ll figure out monetization later. While that’s never been our style, the venture market has changed in the last few years. The capital is not as free-flowing, so I expect founders to be more disciplined and have a plan for revenue earlier”, says Jesse Robbins, general partner at Heavybit, the leading investor in developer-first startups.  

As an investor, Jesse looks for products that instantly change the way he thinks about the world from the first moment he sees it, built by founders who have strong opinions, great taste, and authentic community leadership.

But solving an interesting technical problem is not enough; the startup’s solution must credibly solve it in a way that can grow into a real business. A tool can be valuable to developers, but it still may not make a venture-scale business.

My partners and I have to see a path to reach many users and revenue at scale.

I’m looking for clearer answers on “Why is this a big, sustainable opportunity?”.

Does the startup have a plan for product-led growth or an enterprise monetization later on? Founders need to have thought through these questions more rigorously than they might have in 2018.

Beware of “AI Washing”

Not every developer tool must feature AI, but nearly all must consider how it might enhance user experience or efficiency, he says. He points out that developers will only embrace AI-driven features that clearly improve their work and will immediately reject superficial AI integrations that add nothing or create friction.

I’m very wary of “AI washing” – slapping a generative AI label on a tool that doesn’t truly benefit from it. The reality is that AI should be applied only where it meaningfully improves the product.

AI in dev tools should be deeply and seamlessly integrated into the developer experience, not bolted on. That’s where the magic happens! 

Agentic Experience as the New Developer Experience?

We’re not abandoning developer–centric design—rather, we’re extending our design thinking to accommodate these new users. So, Agentic Experience is sort of the new frontier of DX.

Agent Experience means accepting that part of your “user base” is now software acting on behalf of humans.

That means eliminating all the barriers for that software to use your platform: zero-friction APIs, instant provisioning, machine-friendly docs, clear logging of agent actions, and great DX for automation, ultimately loops back to happier developers of all types.

Jesse predicts that AX will become as commonplace as DX in design discussions going forward, especially as AI agents get more capable.

Dev Tool Fatigue is Real

That’s precisely why Heavybit looks for founders with strong opinions, great taste, and authentic community leadership. Those kinds of people build products worthy of attention and find a way to get it.

I don’t care about GitHub stars but active contributors and real positive discussions in Slack or Discord.

Developers Don’t Want to be Sold to

At Heavybit, they proudly say that the founders they have backed have built the future of software from the bottom up. In his experience with over 80 dev tool companies, Jesse says they often live and die by bottom-up adoption.

Developers don’t want to be sold to—they want to discover tools via peers, side projects, open source, and community buzz.

Free tiers, open-source releases, great documentation and authentic engagement in developer communities are standard. When a developer finds a tool they love, it spreads: from side project to team to org to enterprise deal.

The initial growth of a developer-focused startup is usually organic and driven by users as advocates, but that doesn’t mean “no sales” or that you can ignore traditional go-to-market functions. Many successful dev tools evolve to include blended go-to-market strategies, combining bottom-up adoption with enterprise sales once they reach scale.

Many Heavybit portfolio companies have open-source and/or generous free plans:

Instead of paying for ads, you’re letting the product advertise itself.

It does mean you need a plan to convert usage to revenue down the line – usually via paid cloud services, enterprise features like SSO and compliance, or usage-based billing once a team scales up.

There isn’t one single template, he says. Some dev-first companies go broad and viral bottom-up, while others targeting heavy enterprise use-cases need to engage outbound sales early on. It depends on the product’s audience: if your tool is for an individual developer or a small team (like a new JS framework or a CI service), you likely start bottom-up; if it’s aimed at, say, the VP of Engineering solving org-wide problems, it makes sense to blend in targeted sales sooner.

The post What It Takes to Build a Dev Tool Startup in 2025 with Jesse Robbins, Heavybit appeared first on ShiftMag.