Amp extends its AI coding agent to writing, design and voice with OpenAI models

Sign in with ChatGPT targets token costs

Amp is building what it calls a frontier AI agent that helps developers turn ambitious ideas into working software. CEO Quinn Slack says each model improvement lets the agent do more, 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.

As people hand agents more work, token costs can become a constraint. Slack describes some Amp users consuming 10 billion tokens a week. He believes that if people watch every increment of usage, it may keep them from finding out what an agent can do.

To address this, Amp launched a Sign in with ChatGPT integration. According to Slack, it gives Amp users access to more tokens and to OpenAI models, including GPT-6 Astra, and changes how willing they are to let an agent take on a larger task. "Sign in with ChatGPT means that people can have that feeling where they’re not counting every single token," he says.

Marketing, documentation and design handled by an agent

Amp wants agents to help with all the work involved in building and growing a product. Its own 20-person team uses them that way, including in marketing. "We don’t have someone devoted to it, but we have an agent devoted to it," Slack says. The team relies on the agent to improve the experience for new users and to help more people find Amp through search and other channels.

Because that work demands high-quality writing and design, Slack says GPT-6 Astra helps the team produce documentation and design pages that meet Amp's standards. He describes the company's design and writing style as very distinctive and says the team is picky, but has been "really happy with how GPT-6 Astra does."

Slack also experiments at home. He 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 just a couple months ago."

Voice control with Puck and faster responses with Ultrafast

Amp recently announced Puck, a conversational AI assistant built into the product that helps users launch and manage other agents. Users can ask Puck to start an agent to investigate a bug, coordinate several agents, or find a previous conversation about a technical problem.

With Calling Puck, powered by GPT-Live-1, users can talk to Puck in real time, including from a watch. Slack imagines people keeping their agents working while away from their computers, even while out for a run.

Amp has also been testing Ultrafast mode with GPT-6 Astra. Slack says the greater speed changes how people use agents. People often switch between several agent tasks while waiting for each to finish, so faster responses could let them juggle fewer agents, or give agents more time to check their own work before returning a result.

What it means for builders

For Amp, the next step is 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. Slack says users appreciate "the consistency with which OpenAI models have been getting better and better."

The account comes from OpenAI and reflects Slack's own views and Amp's internal use. It points to a shift in which usage-based costs, speed and voice access shape how freely developers delegate work to agents.