Introducing Alex Research: Your AI-Native PM Agent
Meet Alex — the AI research agent that runs structured user interviews, synthesises findings, and feeds insights directly into your Product Graph.
What is Alex Research?
Product managers spend a surprising amount of time on tasks that feel productive but aren't: scheduling interviews, transcribing notes, categorising themes, and writing up findings. Alex Research is designed to take all of that off your plate.
Alex is an AI agent built into Specky that can conduct structured user research sessions on your behalf, synthesise the findings, and write them directly into your Product Graph — the living knowledge base that powers everything else in Specky.
How it works
From the Alex Research view in your workspace, you can:
- Talk to Alex directly: ask it to explore a topic, challenge your assumptions, or help you prepare for a discovery session
- Deploy interview campaigns: send Alex to a segment of your users to run structured interviews at scale
- Review synthesised findings: every session produces a summary that is automatically tagged and stored in your Product Graph
Why this matters
The best PMs we know spend their time synthesising and deciding — not collecting. The research loop has always been the bottleneck: you need more signal to make a confident decision, but gathering that signal is slow and expensive.
Alex changes that equation. It runs while you sleep, interviews users you'd never have time to reach, and surfaces insights you'd likely have missed.
Getting started
Alex Research is available today on all Specky plans. Open your workspace, navigate to Alex Research in the sidebar, and start a conversation. Your first campaign is free.
We'd love to hear what you build with it.
Keep reading
Most "AI Features" Shouldn't Be AI Features. Here's the Test That Tells You.
Most "AI features" shipped in 2026 are rules engines wearing an AI costume. Here's the four-question test to run before you spec one — and what it looks like when a feature fails all four.
The Product Velocity Illusion: Why Shipping Faster Hasn't Made Your Roadmap Better
AI collapsed the time it takes to build a feature, but not the time it takes to decide what to build or validate that it worked. The Three Clocks framework shows product teams where their real bottleneck moved — and how to stop mistaking build speed for progress.
Your Next User Might Not Be Human: A PM's Framework for Agent-Ready Products
Software is quietly picking up a second audience — AI agents acting on a human's behalf. Here's a framework for auditing whether your product actually works for both.