How Amplitude ships product improvements in 1–2 days with OpenAI
Amplitude's AI agent Wave, powered by OpenAI models, helps teams ship product improvements in 1–2 days instead of a month.Summary
Amplitude, a product analytics company, has developed Wave, a proactive product agent powered approximately 80% by OpenAI models including GPT-6.1 Sol, GPT-6 Luna, and GPT-Image-2.5 Flare. Wave combines Amplitude data, session replays, customer feedback, and code to identify opportunities, develop solutions, and coordinate implementation with humans and coding agents like Codex, then tracks outcomes. This workflow enables teams to ship product improvements in 1–2 days, down from roughly a month. On Amplitude's own homepage, Wave discovered that users bypassed generic suggestion cards—in a sample of 100 session replays, 80 users typed their own questions while only 12 selected a suggestion. Wave proposed personalized cards using recent charts, dashboards, or referring pages, and after A/B testing, messages sent through suggestion cards increased 160% relative to control after one day. Amplitude assigns different OpenAI models to different tasks: GPT-6.1 Sol for deep investigations (scoring 4.06 out of 5 on investigation criteria, leading all alternatives), GPT-6 Luna for high-volume, low-cost tasks, and GPT-Image-2.5 Flare for generating product mockups (scoring 80.3 out of 100 for wireframes). Teams control automation levels, sending bug fixes directly to coding agents while larger features get human review. Among customer-launched experiments, one in four went live the same day Wave surfaced the opportunity, half in under four days, and two in three within a week. CEO Spenser Skates says the ambition is to make self-improving products the way companies build software.
(Source：OpenAI)