Amplitude has announced a range of autonomous AI agents designed to help brands continuously monitor customer behaviour, identify friction and act on insights in real time.
The agents detect meaningful metric shifts within hours, analyse session replays to quantify revenue impact, automatically design and launch experiments, and turn unstructured customer feedback into clear product recommendations.
For retail and customer experience teams under pressure to improve conversion and lower acquisition costs.
Since a test-launch in June last year, early customers, including AskNicely and AirDNA, are already seeing measurable gains, cutting hours of manual reporting, accelerating analysis, and delivering smarter insights to leadership faster.
“We’re entering a new era of analytics – one where AI can monitor your product around the clock, and free up your team to focus on the experience,” said Spenser Skates, co-founder and CEO at Amplitude. “Today we’re launching the first fully autonomous analytics agent. It’s going to reinvent how product decisions get made.”
As part of the launch, Amplitude announced a Global Agent, four specialised Agents, and MCP updates that bring data to where people already work—such as tools from Anthropic, OpenAI, Cursor, Figma, Lovable, Notion, and GitHub. Combined, they make it possible for companies of all sizes to move from insight to action in minutes instead of months.
With Global Agent, teams can ask complex questions in plain language and get instant answers. The agent analyses data, builds dashboards, investigates root causes, and explains what’s driving changes across funnels, experiments, segments, and customer journeys. It then recommends what to do next and takes action directly in Amplitude.
Four specialised agents – focused on monitoring dashboards, reviewing user sessions, running experiments, and processing feedback – handle the tasks that typically bog product teams down.
- Dashboard Monitoring Agent: Detects meaningful metric changes within hours, investigates why they happened, and delivers insights and recommended actions via Slack or email.
- Session Replay Agent: Reviews hundreds of user sessions continuously, spots hidden friction, quantifies revenue impact, and recommends specific fixes.
- Web Experimentation Agent: Designs and launches experiments, analyses results, and makes rollout or iteration decisions, all while keeping a human in the loop.
- AI Feedback Agent: Turns unstructured feedback from surveys and support tickets into actionable insights by mapping themes to actual user behaviour.
According to Amplitude, the agents not only understand data, but context too.
- AI Assistants: Ask Claude or ChatGPT to summarise user behaviour, pull charts, and answer product or campaign questions using Amplitude data.
- Development: Validate, debug, and track impact with product context inside Cursor or Claude Code. Add behavioural context to GitHub pull requests. Build and ship AI features with integrated product insights in AWS Kiro.
- Design & Prototyping: Validate and refine Lovable concepts with product performance and feedback. Identify user friction and generate data-backed prototypes in Figma Make.
- Product & Collaboration: Analyse and surface product opportunities with Notion agents. Make Amplitude charts and analytics searchable in Atlassian Rovo.
- Sales & Engagement: Personalise messaging and targeting in Outreach with behavioural signals.
And early customers and partners are already seeing impactful results with the agentic AI analytics platform.
“Amplitude has helped NTT DOCOMO scale self-serve analytics to more than 1,000 active users and significantly reduce the time required to analyse campaign effectiveness,” said Takashi Suzuki, SVP and GM of the data platform department at NTT DOCOMO. “With Amplitude AI Agents, our teams can streamline analysis directly from existing dashboards, helping us move faster while improving conversion rates and lowering cost per acquisition.”
“Increasing our users required more than just access to data. It required structure and automation,” added Matias Caratti, product shipping supervisor, Mercado Libre.
“Dashboards provided a single source of truth, and AI Agents enabled us to find data on our own. We didn’t have to rely on manual reports, and we were provided with automatic insights on funnel performance, countries with the best conversion, and fluctuations in contact rate.”
“Amplitude MCP and Skills bring user insights directly into agent context in Cursor,” said Joshua Ma, engineering lead at Cursor. “This allows teams to quickly ship features, measure impact, and build smarter experiments for the next release.”
