Notes from building
agentic onboarding.

PLG solved distribution and left onboarding untouched. Agent-led growth is the attempt to fix what happens after signup.

Chat isn’t replacing the interface. The interface is doing something chat structurally can’t.

It removes the part of the job that was never actually CS to begin with: teaching people how to use the product.

Good agentic onboarding isn’t about what the agent says. It’s about when it says it, and how.

An LLM reasoning in real time about what each user needs to learn and do next — instead of giving everyone the same tour.

Some products are experimenting with going all-in on chat.

A practical guide to URL triggers, event-based messages and real-time session context in Intercom.

How we turned PostHog from an analytics tool into the event backbone for real-time agents.

Introducing the Autoplay Proactive SDK: the missing layer between what your users do and what your agents know.

Why browser agents can navigate but struggle to browse.

The first time you sit in a cockpit, you realise no one is trying to comfort you.

We went there with a clear goal.

And what we can learn from meal delivery services.

Robustness, composability, and the limits of agents.

Why co-pilots need actual UI understanding, not just good language models.

When humans do what the product should.

A story about timing, technology, and intent.

We started Autoplay with a simple question.

What’s faster — clicking around an interface, or prompting an AI to act on your behalf?

A few months ago, the admin work started to slow us down.

When we started Autoplay, the dream was simple: real-time automation in software.

Funnels are great at telling a story that isn’t the real one.

Agents aren’t proving fully reliable yet. Categorization is.

We came back from the Odoo Experience in Brussels with one big takeaway.