Adobe plans to let customers use their preferred AI agents, including ChatGPT, Gemini and Claude, with its creative software, but has not committed to making every feature accessible.
Local Model Context Protocol (MCP) integrations previewed by Adobe will connect outside agents to Photoshop, Illustrator, Premiere and After Effects, with a private beta planned for early 2027. Outside agents will be able to edit native project files on customers' computers while preserving layers, sequences and other editable elements.
Open access
"I can't give you the absolutes right now. This stuff is still sort of well into development. I can give you the intent, which is not to block people or trick people or limit people into only working in certain ways. The nice thing about putting the MCP endpoints in our tools is, if you're using them, you have our tools, right? And you're still our customer. We're still providing you with value," said Ely Greenfield, CTO & SVP Creative Products, Adobe.
"I think the big message today is we are really leaning into that, both with the agents that we are bringing into our tools, but also with how we are bringing creative capabilities, technologies, tools, and workflows to wherever customers are doing their creative work. Whether that's in our tools, whether that's through interfaces they're going to build with Graph, or whether that's through the agentic portals, Gemini, ChatGPT, Claude. Our job has always been to power creatives in their workflows. We still will do that, even though the workflows will start to move out into other places, which is great," said Greenfield.
"And what agents are opening up through vibe coding is the ability for everybody to look at a computer the way a programmer looks at a computer, which is not just a tool to be used, but a tool for building tools," added Greenfield.
Creative judgement
"The big difference between an LLM and an agent is that an agent plans, but most importantly, an agent has a feedback loop. You give it a task, it makes a plan to go do it, and then it tries to accomplish it. It can then look and evaluate what it did and decide: did it do a good job, did it not do a good job, how do you go from there, right? And loop again," said Greenfield.
"But understanding whether a piece of content is good or not for this particular use case or this brand campaign is a very hard task which most humans aren't good at. Our customers are all very good at doing this. Giving them an agent that they would trust to hand this off to, because the agent can make good decisions on its own, is a very high bar. That's the big challenge when it comes to making creative agents that are successful," added Greenfield.
"We're already seeing in some of the work we've done bringing our plugin into these other chats where I'm going to be chatting, but also sometimes it's much easier to point at something or to drag something than it is to describe it. Being able to pop up some interfaces inside of the agent becomes incredibly valuable," said Greenfield.
Research priorities
"We have a much more evolved process by which our product teams work closely with our research leaders, who are the domain experts and the principal investigators. There's a very collaborative process by which our product teams inform the researchers about what problems matter to our customers and therefore to us. Our research leaders inform our customers about what is the bleeding edge, what's possible now, and what could be possible in the future.
"Like any product company, we have an iterative planning process by which we're always checking in, every quarter, month, whatever it is, on what our strategy is, what our roadmap looks like, and adjusting based on what's changed, which seems to be every day now. We do the same thing on the research side, so that then informs our research agenda and our research roadmap, and we check in and figure out what we want to invest in and the right balance between short-term investments, long-term investments, certain investments versus risky investments. A good research lab has a good balance of that. You definitely don't want every project to succeed, or you're not pushing hard enough," added Greenfield.
"We still build our own generative models in order to fill gaps in the market. Originally, the gap was people didn't trust these models. They didn't know what they were trained on. They thought they were going to be sued for it. We had to fill that gap," said Greenfield.
Agent context
"What I think really becomes valuable is that these agents learn more about you and learn about your creative style, your brand, your guidelines, your company, where you work and all of that context. That's the thing that we can really help our customers collect and gather through using our tools, whether it's through an MCP or directly in the UIs that we build. If you think about the value of an agent, it's both its ability to plan and evaluate, and its ability to collect and use that data on your behalf. Those are the things we're investing in," said Greenfield.
"The more the public agents, the common agents, get better at that, that's great. We'll focus on the stuff that they don't do," added Greenfield.