Launching today
Poth Labs
The customer brain for your company
299 followers
The customer brain for your company
299 followers
Customer knowledge isn't a collection of documents. It's a network of relationships. Poth builds a living model of your customers before answering questions, so Ask Poth can reason across all your company knows instead of summarizing isolated sources. That unlocks questions no single source can answer, from what's driving churn to why customers adopt or abandon features. Every conclusion is grounded in evidence. If the answer isn't there, Poth launches adaptive surveys to collect what's missing.
Poth Labs
@mojmir_horvath The version of this I've actually needed is one place that remembers context so success and sales stop asking customers the same questions. In practice the blocker is always integrations. Which systems do you pull from on day one, and how do you handle it when the CRM and support tool disagree about the same account?
@mojmir_horvath @artem_fedorovich Hi Artem! Fair question, integrations are usually the blocker. Day one, we pull from the systems most teams already have: call recordings (Clari/Fireflies/Granola), product analytics (PostHog/Amplitude/Mixpanel), CRM and support tools, and we build anything customer-specific ourselves during onboarding rather than making you wait on a roadmap. On our platform, we surface both supporting and contradicting evidence, leaving the human end user to make the judgement call!
Alex is pointing at the real hole. I would go one step further.
Staleness never throws an error because absence of data and absence of change look identical to any system built from ingested artifacts. No ticket, no call, no email. The graph reads that as a quiet, healthy account. It is usually the opposite.
We learned that expensively once, with a customer who was signed, warm in every conversation, and had not used the thing a single time. Every source we had said green. The only honest signal was usage, and nobody was looking at it.
So: does Poth model silence as evidence? Not "no data on this account" but "this account has gone quiet in a pattern that has preceded churn before."
And on Artem's question, when the CRM and the support tool disagree, does Poth pick one or surface the disagreement? The disagreement is usually the actual finding.
@rabnoor_s On silence: Poth ties the graph to behavior, not just ingested artifacts, so an account going quiet is visible rather than invisible. What we don't do yet is the learned version: "this quiet pattern preceded churn before," but that's where this is headed.
On the disagreement, I mentioned in my reply to Artem but we surface both supporting and contradicting evidence leaving the human user to make the judgement call!
Churn in developer communities doesn't show up in the CRM first. It shows up in Discord going quiet, GitHub issues tapering off, forum activity slowing down weeks before anyone cancels or even thinks about it. Does Poth connect to sources like that, or is the knowledge graph limited to CRM and support integrations? That gap is the one I'd actually want closed.
@hazy0 Not out of the box today, current sources are more product analytics, calls, and CRM/support. But Poth doesn't care where activity comes from, it's all behavioral signal. We build integrations customer-by-customer during onboarding, and Discord + GitHub activity for devtools is exactly the kind we'd build first. Totally agree that's where dev churn shows up before anyone cancels.
Good to know the integration layer is open ended. If Discord and GitHub are on the near term roadmap for devtools, the question becomes the latency on that data. Community signals go stale fast. Is the ingestion close to real time, or is it a daily batch?
Poth Labs
@hazy0 We let customers choose based on the data source and their infrastructure. Some prefer near real time via webhooks or streaming, while others are happy with scheduled syncs every few hours or day. Poth is designed to work with either, depending on the use case and the capabilities of the underlying system.
relationships rather than documents is the right framing. the hard bit is that a relationship goes stale without ever throwing an error, nobody files a ticket when a champion quietly leaves, so the graph keeps looking healthy right up until the renewal.
@alex_watson2110 Agreed, nobody announces they've gone quiet. That's why our graph tracks behavior, not just documents. A champion leaving looks like silence in the activity data, and silence is a signal if you're watching for it.
Really like the idea of reasoning over relationships instead of just retrieving documents. Curious - do you see Poth staying focused on customer intelligence or is that just the first step toward becoming a broader knowledge layer for product, marketing and other teams?