Think inside your AI world.

Pendo through Unl

Pendo can tell you how many accounts touched a feature this week. Whether that counts as adopted is a question only your own ratified threshold can answer.

Pendo through Unl reads feature and event usage against the adoption threshold you have ratified, so 'has this feature been adopted?' comes back adoption: not proven with the condition it hasn't met.

What Pendo holds

Pendo through Unl can genuinely read:

  • Visitor and account metadata, so a query can be scoped to a real segment rather than 'everyone'.
  • Page, Feature and Track event data, down to when and how often a given feature was actually touched.
  • Event-level aggregation queries across recent usage windows, so counts aren't a guess.
  • Visitor activity and engagement patterns over time, not just a single snapshot.
  • Application analytics and user behaviour across the products Pendo is installed on.

What the naked read gives you

Ask Pendo directly and it will tell you, accurately, that 240 accounts triggered the new export feature last month, that usage is trending up week over week, and which segments are driving the volume. That's real telemetry, pulled straight from event data Pendo has always tracked well, and for a lot of questions it's exactly what's needed.

The frame judges the data it is given; it does not verify the source’s accuracy.

What changes when Pendo is read measured

The Head of Product ratified that a feature only counts as adopted once 25% of active accounts use it in three consecutive weeks, because a single spike after a launch email proves curiosity, not habit.

'Has the export feature been adopted?' returns, measured: adoption: not proven - usage touched 18% of active accounts in week one and has fallen every week since, short of the three-week habit bar in the ratified rule. Pendo supplied the event counts; your ratified rule supplied the adoption threshold.

And back again

That answer doesn't vanish once it's given. Next time someone asks about the export feature, whether in a roadmap review, a QBR or an investor update, Unl produces the same verdict from the same ratified rule, so the story about adoption stays consistent even as the raw Pendo numbers keep moving underneath it.

The answer comes back measured against what you already decided, and why.

The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.

Questions people ask

What happens to the verdict once usage keeps climbing?

It moves. Unl re-reads Pendo's event data at each read, asked or unprompted, so once the export feature clears three consecutive weeks at 25% of active accounts, the same question returns adopted. The rule doesn't change; only the numbers feeding it do.

How do I connect Pendo to Claude?

Through Pendo's own MCP server. An admin turns on MCP for the organisation inside Pendo, then you connect it as an MCP source in Unl. Unl reads through Pendo's existing permissions, so nobody sees data they couldn't already see in Pendo.

Does connecting Pendo let Unl change anything inside it?

No - the link runs one way. Unl queries Pendo's visitor, account and event data purely to test it against your ratified adoption rule. It has no ability to create guides, edit segments or touch anything inside Pendo itself.

What this is

Think inside your AI world — you stay in command

Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.

It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.

Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:

Alpha is invite-only · free at launch.