Amp is building a frontier AI agent that helps developers turn ambitious ideas into working software. For CEO Quinn Slack, each improvement in the models is an opportunity to expand what the agent can do, from helping developers decide what to build to writing code and designing pages. Amp chooses and recommends models based on what works best for its users, and OpenAI models account for the majority of tokens used in Amp. Slack says OpenAI is transparent about safeguards, which makes the models easy to use, and that users appreciate the consistency with which OpenAI models keep improving.

Because token costs can constrain builders as agents take on larger tasks, Amp launched Sign in with ChatGPT. Slack describes some Amp users consuming 10 billion tokens per week, and says that if people watch every token increment, it may hold them back from discovering what an agent can do. The integration gives Amp users access to more tokens and OpenAI models including GPT-6 Astra, so they can let an agent run with a longer leash. Once users stop counting every token, Slack says they see how much the agent can do in planning, deciding what to build, and continuing work after shipping.

Amp also uses agents for work beyond code. Its 20-person team has an agent devoted to marketing rather than a person, improving the experience for new users and increasing discovery through search and other channels. For that work, writing and design quality matter, and Slack says GPT-6 Astra helps the team produce documentation and design pages that meet Amp‘s exacting standards. Outside work, Slack gave GPT-6 Astra the plans for his house and used it to create a 3D model in Blender, which he and his children turn into games; he says that was not possible a few months ago.

Amp recently announced Puck, a conversational AI assistant built into Amp that helps users launch and manage other agents. With Calling Puck, powered by GPT-Live-1, users can talk to Puck in real time, including from a watch. Amp has also been testing Ultrafast mode with GPT-6 Astra; Slack says the greater speed can change how people use agents, possibly letting people juggle fewer agents or giving agents more time to check their own work. Looking ahead, Amp wants to bring more of the work before and after coding into the agent, so builders can carry an idea further without handling every step themselves.