Lewis Kerr

Clonvara Insurance Services / BB-Demo – Demo

Callcompleted

Clonvara Insurance Services: documents logo Clonvara Insurance Services: documents · 2025-08-26 09:00

Demo for Clonvara Insurance Services on a sample extract. Siobhán Dunne and Cian Farrell liked the one-click source trail and honest uncertainty. They asked for a longer second demo covering dashboards and connectors.

What was said

What this says

Current to 11 Oct 26

Demo for Clonvara Insurance Services on a sample extract. Siobhán Dunne and Cian Farrell liked the one-click source trail and honest uncertainty. They asked for a longer second demo covering dashboards and connectors.

What happened: Hannah Lowe demoed search and chat on a sample extract with sensitive fields removed. Siobhán asked whether underwriters can trust the answers and Cian asked for answers with their source.

Customer view: Siobhán liked that the brain flags uncertainty and does not correct source records. She said the open-claims-by-broker view would save her an evening a week.

Commercial: Siobhán asked for a longer second demo covering dashboards and connectors, and wants Brendan to see the broker view. Lewis Kerr tied this to 26 Sep 2025 as the point for a proposal decision.

Watch: Cian wants the policy side as strong as the claims side. The first-response field in the sample is inconsistent, which is a data point for the customer's data engineer.

AI · claude-sonnet-5-5 · 11 Oct 2026

Themes

Current to 9 Oct 26
Theme
Pre-sale demo, broker view
Importance
upsell
Sentiment
positive
Voice
decision-maker

Who was there

BB-Demo

Them

Follow-up

Next steps

Current to 9 Oct 26
  • Hannah Lowe to send a note on what was covered and the open points on data fields.
  • Lewis Kerr to suggest a date for the longer second demo with Brendan invited.
  • Lewis Kerr to work towards a proposal decision by 2025-09-26.

Risks

Current to 9 Oct 26
  • Cian wants the policy side as strong as the claims side and may be unconvinced until he sees it.
  • The first-response field in the sample is inconsistent, which could weaken answers on policy queries.

Opportunities

Current to 9 Oct 26
  • A longer second demo on dashboards and connectors, with Brendan seeing the broker view, moves the deal towards a proposal.
  • A saved open-claims-by-broker view gives broker managers a concrete early use.

Transcript

  1. Lewis Kerr
    Lewis Kerr None
    Good morning, everyone. Siobhán, Cian, welcome. Hannah's with me, she'll drive the demo.
  2. Siobhán Dunne
    Siobhán Dunne None
    Morning, Lewis. Hi, Hannah. Cian's just sitting down, he's had a morning.
  3. Cian Farrell
    Cian Farrell None
    Morning. Sorry, I'm here. Can you hear me? I think my headset is doing something odd.
  4. Hannah Lowe
    Hannah Lowe None
    We can hear you fine, Cian. Thanks for joining. Before I share anything, can I ask what you most need to know today? I'd rather aim at that than walk you through every page.
  5. Siobhán Dunne
    Siobhán Dunne None
    So, two things. Can it see the broker activity, the policy queries and the claims tickets together, on a single broker. And can the underwriters trust what it says. What's the source of truth?
  6. Cian Farrell
    Cian Farrell None
    From my side, I want to know if it can answer the kind of question I get asked, like which brokers have had repeated queries on the same policy type. And whether I can see where the answer came from.
  7. Hannah Lowe
    Hannah Lowe None
    Good, that gives me a clear aim. I'll share my screen now. What you're seeing is a brain built on a sample extract you sent us, sitting in a Snowflake account set up for this demo. Same shape as it would be in yours.
  8. Siobhán Dunne
    Siobhán Dunne None
    Is that our real data?
  9. Hannah Lowe
    Hannah Lowe None
    To be precise, it's the sample extract you gave us, with the fields you flagged as sensitive removed. So it's your structure and your kind of records, but not live production data.
  10. Siobhán Dunne
    Siobhán Dunne None
    Good, that's what I wanted to hear.
  11. Hannah Lowe
    Hannah Lowe None
    Right. Let me start with search, because it's the simplest. I'll type a broker's name. And what comes back is one page: the CRM activity, the policy queries and the claims tickets, in order, with the source named next to each line.
  12. Cian Farrell
    Cian Farrell None
    Mm. So that line there, that's from the helpdesk?
  13. Hannah Lowe
    Hannah Lowe None
    Yes. And if you click on it, it opens the original ticket. That's the answer to where did it come from, it's always one click back to the record.
  14. Cian Farrell
    Cian Farrell None
    Okay. That's better than what I have now, which is a screenshot somebody sent me.
  15. Lewis Kerr
    Lewis Kerr None
    Ha. That's the sort of thing we hear a lot.
  16. Hannah Lowe
    Hannah Lowe None
    Now the chat. Cian, you tell me a question and I'll type it exactly as you say it.
  17. Cian Farrell
    Cian Farrell None
    Which brokers have raised more than one query on the same policy type in the last quarter?
  18. Hannah Lowe
    Hannah Lowe None
    Typing that. It takes a few seconds. There. It's given a short list, and underneath each name the queries it counted. And it's also saying what it's not sure about, here, where two records might be the same broker spelled differently.
  19. Siobhán Dunne
    Siobhán Dunne None
    Oh, that's honest. I like that it flags it. Last tool we looked at just gave an answer with total confidence.
  20. Hannah Lowe
    Hannah Lowe None
    The short answer is it will be wrong sometimes, like any tool. The longer answer is that it shows its working, so you can see when to challenge it. I'd rather you knew that now.
  21. Cian Farrell
    Cian Farrell None
    What about if the underlying record is wrong? Say the underwriter keyed the policy type incorrectly.
  22. Hannah Lowe
    Hannah Lowe None
    Then the brain reflects what's in the source. It doesn't fix it, it surfaces it. But because you can see both records side by side, it's usually quicker to spot the discrepancy than before. Fixing the source stays with you.
  23. Siobhán Dunne
    Siobhán Dunne None
    And that's the right way round, to be honest. I wouldn't want a tool quietly correcting our records.
  24. Lewis Kerr
    Lewis Kerr None
    Siobhán, can I ask, does the claims ticket view cover what you were hoping for?
  25. Siobhán Dunne
    Siobhán Dunne None
    Nearly. Hannah, could you filter the claims tickets by how long they've been open, per broker? That's what the broker managers keep asking for.
  26. Hannah Lowe
    Hannah Lowe None
    Yes. Let me do that. I'll ask it in plain words. Show me open claims tickets for this broker, oldest first. And there it is, with the age beside each one. I can save that as a view so the broker managers have it ready.
  27. Siobhán Dunne
    Siobhán Dunne None
    That would save me an evening a week, I'd say. Cian, you agree?
  28. Cian Farrell
    Cian Farrell None
    For the broker managers, yes. For me, I'd want the policy side as strong as the claims side. Can we look at that before the end?
  29. Hannah Lowe
    Hannah Lowe None
    Absolutely. Give me a minute to switch to the policy view. Lewis, anything you want to say while I load that?
  30. Lewis Kerr
    Lewis Kerr None
    Only that this is the sample, and what you'd get in the real thing is built on your actual sources, in your account. Hannah will say how connectors work in the follow-up call.
  31. Hannah Lowe
    Hannah Lowe None
    Right, policy view. Same search, but this time the policy queries lead. Cian, ask me something.
  32. Cian Farrell
    Cian Farrell None
    Show me policy queries where the broker came back within a week of the first response.
  33. Hannah Lowe
    Hannah Lowe None
    That's a good one. Typing it. Hmm, it's asking me to clarify what counts as the first response. That's a fair question, because in your sample the field isn't consistent. So that's a real data point for you, not a limitation of the tool.
  34. Siobhán Dunne
    Siobhán Dunne None
    That's one for my data engineer. Noted. Honestly that's useful in itself.
  35. Cian Farrell
    Cian Farrell None
    Agreed, I didn't know that field was patchy.
  36. Hannah Lowe
    Hannah Lowe None
    I'll write that up in the follow-up so it's not lost. Anything else you want to try in the time we have left?
  37. Siobhán Dunne
    Siobhán Dunne None
    Can we do a second demo, a longer one, where we go into dashboards and how the connectors would work? And maybe I'd like Brendan to see the broker view.
  38. Lewis Kerr
    Lewis Kerr None
    Yes. Let's do that. I'll suggest a date in the coming weeks and keep 26 Sep 2025 in mind as the point we'd want a proposal decision by, so you're not rushed but we've a shape to work to.
  39. Siobhán Dunne
    Siobhán Dunne None
    Grand. That works for me.
  40. Hannah Lowe
    Hannah Lowe None
    I'll send a short note on what we covered and the open points on the data fields. Thanks, all.
  41. Cian Farrell
    Cian Farrell None
    Thanks. That was more useful than I expected.
  42. Lewis Kerr
    Lewis Kerr None
    Thanks, everyone. I'll send that over today. Speak soon.

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
Organisations75
People at customers290
BB-Demo staff40
Calls784
Email threads1,169
Support tickets449
Documents477
Deals117
Invoices101
Events49
News items56

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.

Ask B

Ask B

B-Brain · read-only