CX Aperitivo — our next London meet-up is Thursday 17 September. Save your spot.

CX Aperitivo — our next London meet-up is Thursday 17 September. Save your spot.

BLOG

Notes from building
agentic onboarding.

What agent-led growth actually means in practice, how teams are wiring real user context into their support agent, and what breaks along the way. Written by the people building it.

Subscribe
LATEST

Fresh off the desk.

AGENT-LED GROWTH · ISSUE 01
27 AUGUST 2026
6 MIN READ

What Is Agent-Led Growth in SaaS?

PLG solved distribution and left onboarding untouched. Agent-led growth is the attempt to fix what happens after signup — and most of the industry is defining it one layer too shallow.

Marie Gouilliard
Co-founder, Autoplay

If you’ve spent any time in SaaS go-to-market circles this year, you’ve heard the term: Agent-Led Growth. It’s being positioned as the successor to Product-Led Growth, the way PLG replaced sales-led motions a decade ago.

There’s no accepted definition yet, which is part of the problem. Here’s mine — and why the conversation is still one layer short.

The core idea

PLG made the product the engine. Sign up, try it, find value without a rep.

Agent-led growth is the layer on top. Instead of the user learning the product well enough to reach value on their own, an agent inside the product works out what they should do next and either shows them or does it for them.

The product should be doing the work of understanding the user and telling them what to do next — not the other way around.

The output is one next best step, personalised to that user. Getting it right means grounding it in three streams, not one:

  • What they do in the UI — the screens they open, the actions they abandon.
  • What they say in the chat — the questions they ask, and the ones they ask twice.
  • What the agent does for them — what it suggested, what it did on their behalf, whether it landed.

Hold all three in one place and you can answer the question that actually matters: given what this person has done, and what they still haven’t, what’s the one thing to put in front of them next?

In the UIIn the chatBy the agentContext layerone connectionNext best steppersonalised
Keep context on what the user is doing in the UI, and what the agent is doing for them. Grounded in what they’ve done — and what they haven’t.

Why “self-serve” stopped being enough

PLG solved distribution. It never solved what happens after signup. Complex B2B tools still hand a new user a dashboard, a settings menu and a blank canvas, and call that self-serve.

At Autoplay we think of it as three walls every user hits:

  • They don’t know what they don’t know. They’re not sure what to ask, or which part of the product matters to them.
  • They don’t ask for help when they’re stuck. The friction never surfaces, because nobody on your team knows it’s happening.
  • They only want guidance that’s relevant to them. A tour that ignores their goal and their progress isn’t help. It’s noise.

Static onboarding hits all three at once. Documentation nobody reads, videos nobody finishes, tours that walk every user through the same steps. It’s built for the average user, and the average user doesn’t exist.

What actually makes onboarding agent-led

The label gets applied loosely — usually to a chatbot bolted onto a legacy UI. Three things have to be true at the same time.

It has to be grounded in the whole context.

Account fields — plan tier, signup date, company size — are guesswork. But live UI behaviour on its own is only a third of the picture. Without the agent’s own history, it can’t tell a step someone skipped from a step it completed for them.

It has to know what “done” means for that user.

Onboarding isn’t one checklist; different users need different subsets of it. The agent needs to know which workflows are finished — by the user’s hand or its own — so it isn’t re-explaining or skipping.

It has to turn that into one next step, at the right moment.

Not a summary of someone’s activity: a single recommendation. And proactive help at the wrong moment reads as intrusive, so is now the right time has to be part of the system, not something bolted onto a chat prompt.

Miss one and you have a chatbot with better marketing. This is the gap agentic onboarding is meant to close.

Where the conversation is still one step behind

Of those three streams, almost nobody builds the third.

The current excitement is about agents generating things for users — a dashboard, a report, a first draft. Useful, but it treats “the agent acted” as the finish line. It isn’t. It’s a new event in the user’s history, and the agent has to be able to read it back.

Without that, you get an agent that repeats a suggestion the user already dismissed, contradicts its own last recommendation, tells someone to go and do a thing it did for them yesterday, and can’t tell a helpful intervention from an ignored one.

Personalisation that reads user behaviour but never reads the agent’s own history isn’t closing the loop. It’s guessing twice.

Open
ObserveSuggestAct
The agent acts, then forgets.
So it repeats itself.
Closed
ObserveSuggestActRecord
The agent acts, then remembers.
So the next step knows about the last.
The loop most agents never close.

What this means if you’re building

  • Behavioural context beats account context — and behaviour means all three streams. Plan tier tells you who someone is. It doesn’t tell you they’ve opened the integrations page three times, asked about SSO twice, and let the agent wire up Slack for them.
  • Completion state is per-user, and it counts both routes. A step the agent finished on someone’s behalf is done, even though they never touched that screen.
  • Agent memory is infrastructure, not a feature. Retrofit it and you’ll be doing it the first time a customer complains the agent keeps repeating itself.

That last one is what I’ll cover next: what it takes to track not just what a user is doing, but what the agent has already done for them — and how that changes what it should suggest.

Agent-led growth: FAQ

What is agent-led growth?
An AI agent inside the product does part of the work of getting a user to value — reading what they do in the UI, what they ask in the chat and what it has already done on their behalf, and using all of it to suggest their next best step.
How is it different from product-led growth?
PLG made the product the acquisition engine but still assumed users would teach themselves. ALG adds a layer that reads live context and intervenes.
Is it just a chatbot in the product?
No. A chatbot answers what’s typed. An agent-led system also sees what the user is doing, knows which workflows they’ve completed by either route, and decides when to step in.
Why isn’t account-level data enough?
Plan tier describes who a user is, not what they’re doing right now. Friction happens at the level of a specific action on a specific screen — including one the agent took for them.
What does most of the industry get wrong?
Treating the agent’s action as the end of the process. Without a record of what it suggested and how the user responded, it repeats itself and can’t tell useful help from ignored noise.
Want to see this working on your own product?
We’ll show you where an agent would step in on your onboarding flow — no generic demo.
Book a demo
THE LIBRARY

Every issue,
in one place.

20 Aug 2026
All Software Is Going to Be Half Chat, Half UI

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

Read it
13 Aug 2026
What Does Agentic Onboarding Mean for the Customer Success Role?

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

Read it
11 Aug 2026
Our Philosophy for In-Product Agentic Onboarding

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

Read it
6 Aug 2026
What Is Agentic Onboarding?

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

Read it
23 Jun 2026
What Happens If You Replace Your Entire Product With a Chat Interface

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

Read it
17 Apr 2026
Making Intercom Chat Proactive with Real-Time Sessions

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

Read it
14 Apr 2026
Why we started with PostHog at Autoplay

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

Read it
13 Apr 2026
Your AI Chatbot Is Waiting to Be Asked

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

Read it
8 Apr 2026
My experience using Claude to book an Airbnb

Why browser agents can navigate but struggle to browse.

Read it
3 Apr 2026
The Cockpit Doesn’t Teach You. It Shows You.

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

Read it
27 Mar 2026
A week in Casablanca with Leyton and Leyton CognitX

We went there with a clear goal.

Read it
4 Mar 2026
Will open-source software replace SaaS?

And what we can learn from meal delivery services.

Read it
8 Jan 2026
What Building with AI Taught Us About Software

Robustness, composability, and the limits of agents.

Read it
19 Nov 2025
The Reason Co-Pilots Keep Getting Complex Products Wrong

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

Read it
5 Nov 2025
The Journey from Sales-Led to Self-Serve

When humans do what the product should.

Read it
29 Oct 2025
The rise, fall (and rebirth) of Microsoft Clippy

A story about timing, technology, and intent.

Read it
22 Oct 2025
From Reactive to Proactive: The Next Leap for Co-Pilots

We started Autoplay with a simple question.

Read it
14 Oct 2025
The making of conversational UI: prompting, clicking or both?

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

Read it
7 Oct 2025
Moving to Odoo: Here’s What Actually Changed

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

Read it
2 Oct 2025
The Autoplay Roadmap: How Our Thinking Evolved

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

Read it
30 Sep 2025
Goals, Not Clicks

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

Read it
26 Sep 2025
AI isn’t just good for automation — it’s amazing for categorization

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

Read it
24 Sep 2025
Why Post-Deployment Adoption Fails in Odoo Projects

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

Read it
Everything else lives on the blog.

New pieces land roughly every other week — the latest one always shows up in full at the top of this page.

Browse the full archive
NEVER MISS ONE
Get each issue in your inbox.
Agentic onboarding, in practice — how teams wire real-time user context into their support agent, and what actually moves activation.
Subscribe