Opus 4.8 is now available!
- Great for complex analytics investigations
- Better at finding hidden behavioral patterns
- Reads screenshots and graphs too
Happy Thursday!
One of the coolest product demos we've ever launched: Amplitude AI Assistant
A chatbot for your website that can show users how to use your product!
One step closer towards self improving products
We have an opportunity far beyond analytics. Every AI system needs an intelligence layer. We can help AI builders understand, adapt, and continuously improve the behavior of their products.
Check out an early preview: https://t.co/m7lzp5r7xQ
here’s the public repo with our skills:
https://t.co/J7QTB3pzfT
here’s a few new tools in the amplitude mcp server
- get_session_replays
- list_session_replays
- get_session_replay_events
- get_agent_results
- query_agent_analytics_metrics
- query_agent_analytics_sessions
- query_agent_analytics_spans
- get_agent_analytics_conversation
- search_agent_analytics_conversations
- get_agent_analytics_schema
- get_flags
- create_flags
- update_flag
- query_dataset has access to Network Request, Status Code, Error Logged, and Error Click data
- get_feedback_trends
- create_metric
- create_notebook
- edit_notebook
we’ve shipped a bunch of incredible new tools + skills using @Amplitude_HQ's mcp and i wanted to highlight a few killer use cases i’ve been running as a pm/engineer/builder!
/replay-ux-audit + /debug-replay 👀🎥
we added two new session replay tools (list_session_replays and get_session_replay_events) which allows you to more effectively search across your session replays AND provides the agent access to the underlying events and rrweb data.
this allows your agents to query session replays then analyze what’s happening in your replays.
/monitor-ai-quality + /analyze-ai-topics 🤖📊
if you’re using our new agent analytics product, we’ve added mcp tools to query your LLM sessions, spans, conversations, and tagged traces.
this enables your agents to easily browse your agent interactions, synthesize wha the top error categories are or main topics customers are talking to your agents about, then quickly iterate in your ADE/IDE on agent + prompt improvements.
/review-agent-insights 💡
if you’re a heavy amplitude agent user, we’ve added a get_agent_results tool that lets you query all of your amplitude agent previous conversations and the artifacts attached to them.
so if you have a bunch of dashboard and session replay monitors, you can stack workflows on top to triage and fix those issues.
/diagnose-errors 🚨
fun fact: if you’re using autocapture, we track a bunch of rich web vital data like network requests, status codes, logged errors, and error clicks data as different amplitude event types.
so you can automate workflows using an agent to auto-investigate web failures then fix those issues.
get_flags, create_flags, update_flag 👨🏻🔬🧪
if you’re using amplitude for feature flagging, you can create, edit, and retrieve your feature flags all directly via MCP instead of having to manually configure in the UI anymore.
we’ve been using this to scale out the number of experiments we’ve been running internally!
give these a try and lmk if there’s other tools or skills we should be adding! 👀
We’ve been heavily dogfooding Agent Analytics internally to improve our Amplitude Agents. The ability to build evals that automatically enrich traces with tags and connect them to downstream business metrics is incredibly powerful.
Major kudos to @vinaygo for getting the enrichment pipeline stood up in record time!
@spenserskates So thrilled to work on this with @Amplitude_HQ. Combining llm traces with user behavior is incredible context for coding agents, being able to tell which harness update improved user retention will be 🤯🤯
Everyone’s building agents these days, but very few understand whether their agents are actually solving customer pain points. With today’s launch, we’re making it extremely simple for everyone building agents to find out.
2026 will be the year of Agents, and we’re here to help people get real value from them.
Built Agent Analytics to connect what your agent does to the business outcomes you actually care about. Co-developing with a few companies - DM me or sign up using the link in the blog!
big fan of @cursor_ai automations + scheduled tasks for agents ❤️
i’m now running a /daily-brief skill that uses opus or codex to navigate @Amplitude_HQ mcp, review all my product dashboards, active experiments, incoming user feedback, and session replays each morning then push me issues that i can kickoff to coding agents.
sooo crazy to see how the SDLC is evolving on a day to day basis!!
how to 10x agent adoption in your team: get agents into the places where you already work 📈
THE most underrated part of @Amplitude_HQ agent is that you can use it as an expert analyst and have it take actions directly in slack or microsoft teams.
it's like cursor background agents or claude code but across your product data.
tag @ amplitude in slack, ask any question you have about your data, then the agent will come back with analysis and evidence.
it can even execute actions like adjusting rollouts and feature flags, create charts/dashboards async, kicking off guides/surveys, etc.