Ask
Laura Penhaligon

Kesselfeld Software / BB-Demo – Training

Callcompleted

Kesselfeld Software: documents logo Kesselfeld Software: documents · 2026-03-16 09:45

On the 16 Mar 2026 training call, Julia Hartmann brought four customer success colleagues to learn chat, search and pages. She said the brain is already saving time and the team will start building pages this week.

What was said

What this says

Current to 11 Oct 26

On the 16 Mar 2026 training call, Julia Hartmann brought four customer success colleagues to learn chat, search and pages. She said the brain is already saving time and the team will start building pages this week.

What happened: Laura Penhaligon walked through chat, search and pages on the customer's connected CRM, helpdesk, calls and email. Julia asked how her team would repeat queries without help, and Laura pointed to saved pages.

Customer view: Julia compared the nightly refresh favourably with the old weekly exports. She put the manual cost at about twenty ad-hoc questions a week, each taking an hour.

Commercial: This is adoption evidence on the Growth tier, and Laura congratulated Julia on a jump in users. The call does not give user numbers, so any headroom against the included users is not shown.

Watch: Julia leads the use case and nothing yet shows who else will ask questions. Pages are not yet built, so the follow-up depends on her team acting this week.

AI · claude-sonnet-5-5 · 11 Oct 2026

Themes

Current to 9 Oct 26
Theme
adoption training and time saved
Importance
praise
Sentiment
positive
Voice
champion

Who was there

BB-Demo

Them

Follow-up

Next steps

Current to 9 Oct 26
  • Julia Hartmann to have her team try queries and build a first few pages this week, then report back.
  • Laura Penhaligon to send the video guides link and help with the first pages if they prove tricky.

Risks

Current to 9 Oct 26
  • Adoption rests on Julia Hartmann's team building pages, and none were live at the end of the call.
  • The evidence does not show who beyond Julia will ask questions, so key-person dependence is untested.

Opportunities

Current to 9 Oct 26
  • Four customer success colleagues plus a user jump suggest growing use that could be tracked against the Growth user limit.
  • Saved pages such as renewals and customer health views could become the dashboards the team builds on the Growth tier.

Transcript

  1. Laura Penhaligon
    Laura Penhaligon None
    Hi Julia, thanks for joining. How's it going?
  2. Julia Hartmann
    Julia Hartmann None
    Good, good. I've got four people from customer success on the call as well. They're keen to learn how the brain works so we can stop pulling data manually.
  3. Laura Penhaligon
    Laura Penhaligon None
    Brilliant. So today I'll walk through the three core ways to query: chat, search, and pages, and show you some real examples from your data.
  4. Julia Hartmann
    Julia Hartmann None
    Perfect.
  5. Laura Penhaligon
    Laura Penhaligon None
    OK so the brain sits in your Snowflake and reads from all your connected systems. You're connected to your CRM, helpdesk, calls and email, so every night those four sync and get indexed. That means you can ask questions across all of them at once, instead of pulling four exports and merging them in a spreadsheet.
  6. Julia Hartmann
    Julia Hartmann None
    Which is exactly what we've been doing. So this is already saving us time.
  7. Laura Penhaligon
    Laura Penhaligon None
    Right, and the data stays live. You're never more than a day old. So let me show you chat first. This is the natural-language interface. I just type what I want to know. Say, show me all renewals coming up in the next quarter. There. Thirty-eight results with account name, renewal date, CSM, contract value. All live.
  8. Julia Hartmann
    Julia Hartmann None
    How long did that take to query?
  9. Laura Penhaligon
    Laura Penhaligon None
    Maybe a second. Because the data's already indexed in Snowflake, it's just a fast SQL query. Now, search is similar but more structured, you build filters one by one. Say you want to find high-engagement customers. I can filter for: organisations where customer success has asked at least five questions in the last month, on Growth tier, in the healthcare space. And there's your segment, thirteen customers, all active and engaged.
  10. Julia Hartmann
    Julia Hartmann None
    That's useful. My question is, how do my team remember how to build these without coming back to you?
  11. Laura Penhaligon
    Laura Penhaligon None
    Pages. A page is a saved view. You build it once with the columns and filters you want, save it, and anyone on your team just clicks it and it runs with the latest data. So...'Renewals this quarter', 'At-risk customers', 'NPS by segment'. You'd probably have three to five core pages.
  12. Julia Hartmann
    Julia Hartmann None
    And we build those ourselves?
  13. Laura Penhaligon
    Laura Penhaligon None
    You can. The interface is straightforward, you just pick your filters and columns. Or I can help with the first couple if they're tricky. But you already know what you need to see, so it's usually fast.
  14. Julia Hartmann
    Julia Hartmann None
    OK, and the data refresh, that's every night?
  15. Laura Penhaligon
    Laura Penhaligon None
    Every night, all four connectors. So what you're seeing now is current as of last night. If you ever need real-time on something urgent, let me know, but nightly is the standard for Growth and it's working well.
  16. Julia Hartmann
    Julia Hartmann None
    That's good. We've got customers moving fast, so overnight is much better than our old weekly exports. So we'll get my team to start building some pages and using chat for ad-hoc stuff.
  17. Laura Penhaligon
    Laura Penhaligon None
    Exactly. The more people use it, the more questions you'll find. Chat is great for one-offs, like, I wonder how many calls we had last week with French customers. Just type it, get an answer in a second.
  18. Julia Hartmann
    Julia Hartmann None
    Yeah, we do about twenty ad-hoc questions a week that currently take an hour to answer by hand. That time back would be brilliant.
  19. Laura Penhaligon
    Laura Penhaligon None
    That's what it's for. Let me walk through a couple more chat examples and then we can look at some of your actual data.
  20. Julia Hartmann
    Julia Hartmann None
    Great.
  21. Laura Penhaligon
    Laura Penhaligon None
    So the brain understands your business terms. If you say 'segment', it knows that's your industry field. 'Revenue' is contract value. So I can ask, show me healthcare segment revenue by region. And there's healthcare split by country. You can see EMEA is much stronger than North America.
  22. Julia Hartmann
    Julia Hartmann None
    That's the kind of thing we do a lot. Takes forever usually. What about, can I search on fields that aren't in the obvious places? Like, if I want to find customers with a certain property manager type?
  23. Laura Penhaligon
    Laura Penhaligon None
    Yeah, that's a search query rather than chat. Let me show you. You'd add a filter for that field, and the brain will search it. If the field is in any of your connected systems, the brain can reach it.
  24. Julia Hartmann
    Julia Hartmann None
    Nice. OK I think my team's ready to run with this. Are there docs?
  25. Laura Penhaligon
    Laura Penhaligon None
    Yeah, there's documentation in the app, and I'll send a link to some video guides. But the best way is just start playing. Try a few queries, build a page or two. If you get stuck, reach out.
  26. Julia Hartmann
    Julia Hartmann None
    Perfect. I'll get them to do that this week and we'll loop back when we've got some pages live and I've got feedback.
  27. Laura Penhaligon
    Laura Penhaligon None
    Sounds great, Julia. And well done on the user jump by the way, that's brilliant.
  28. Julia Hartmann
    Julia Hartmann None
    Thanks, Laura. Speak soon.
  29. Laura Penhaligon
    Laura Penhaligon None
    Thanks, Julia.

BB-Demo is a fictional company; every organisation and person here is invented. B-Brain is the tool. Built by site/build_site.py from the site tree, data as of Fri 9 Oct 2026. Help & Support

Help & Support

Open as a page

Help & Support

B-Brain is one place to read everything the company knows about its customers: the CRM, calls, emails, support tickets, product usage, invoices, documents, news and HR. Every page is built from those systems and the data is current to Fri 9 Oct 2026.

How to use the site

How to ask

Press Ask Brain in the header. Type a question, or pick one of the examples.

The site itself does not call an AI model; answers in Claude come from the same figures you see here.

What the data covers

DataRecords
Organisations150
People at customers573
BB-Demo staff48
Calls1,382
Email threads2,122
Support tickets789
Documents850
Deals217
Invoices187
Events49
News items84

Data as of Fri 9 Oct 2026. Text marked AI was written by the brain from the records listed in its made-from link; an AI output that cannot cite its evidence is refused and the previous text kept. Where two systems disagree (for example a contract and the CRM), the key facts show both values and mark the difference.

BB-Demo is a fictional company: every organisation, person and figure here is invented for this demonstration. B-Brain is the tool that reads its data.

Who to contact

Email support@b-brain.example or talk to your B-Brain account team. Tell us the page address and what looked wrong; a screenshot helps.

Help

Ask B

B-Brain · read-only