Callie Brennan

Dunholm Precision / BB-Demo – Onboarding

Callcompleted

Dunholm Precision: documents logo Dunholm Precision: documents · 2024-12-23 16:30

Onboarding call on 23 Dec 2024 with Nathan Booth only; the business owner was out. The order system loaded cleanly, a couple of dozen part exceptions are held out, and older tickets join patchily.

What was said

What this says

Current to 11 Oct 26

Onboarding call on 23 Dec 2024 with Nathan Booth only; the business owner was out. The order system loaded cleanly, a couple of dozen part exceptions are held out, and older tickets join patchily.

What happened: Callie Brennan reported the order system load matched the export, with a couple of dozen old part references held out for Nathan to decide. The helpdesk connector is live and most tickets joined to an order.

Customer view: Nathan accepted that the brain keeps current values only and has no audit trail. He wants it stated in the setup note so nobody expects one.

Watch: Older tickets have empty or free-text order references, so answers on older material need care. Nathan said the other category is a big bucket.

Next: Invitations are held until the first data look is done. Nathan will check the refresh status page, watching for flat counts.

AI · claude-sonnet-5-5 · 11 Oct 2026

Themes

Current to 9 Oct 26
Theme
Onboarding data load status
Importance
neutral
Sentiment
positive
Voice
user

Who was there

BB-Demo

Them

Follow-up

Next steps

Current to 9 Oct 26
  • Callie Brennan to send the held-out parts sheet and write the setup note with the audit trail and older ticket caveat.
  • Nathan Booth to decide as many held-out parts as he can and check the status page on a couple of mornings.
  • Callie to send an invite for the first call after the holiday that suits Nathan and the business owner.

Risks

Current to 9 Oct 26
  • The business owner was absent and relies on a written setup note to see the audit trail and ticket caveats.
  • Older tickets join to orders patchily, so answers on older material may disappoint.
  • Flat record counts over the holiday could go unnoticed if the morning checks are missed.

Opportunities

Current to 9 Oct 26
  • The large other ticket category could justify a category of its own once the business owner sees it.
  • A clean first look at the data before invitations should help adoption among the first users.

Transcript

  1. Callie Brennan
    Callie Brennan None
    Afternoon, Nathan. Can you hear me alright? I've got a bit of an echo on mine.
  2. Nathan Booth
    Nathan Booth None
    Clear as anything. Afternoon. It's quiet here today, half the building's gone already.
  3. Callie Brennan
    Callie Brennan None
    Same here. Plan for the next hour or so, then we can both go and have Christmas. First, the order system load and the part mapping. Second, the helpdesk connector. Third, what happens over the break.
  4. Nathan Booth
    Nathan Booth None
    Sounds good. Ruth's out already, she's back after the holiday, so it's just me.
  5. Callie Brennan
    Callie Brennan None
    That's fine, I'll write it up for her. Right, the order system. The load ran out of hours as we planned, and it completed. I've got the counts for you.
  6. Nathan Booth
    Nathan Booth None
    Go on.
  7. Callie Brennan
    Callie Brennan None
    Customers came in matching your export. Orders, the same. On the parts, using your revision rule, the base part grouping worked for almost all of them. A small handful of the old ones didn't follow the rule, which is the exceptions list you gave me, and I've held those out for you to look at.
  8. Nathan Booth
    Nathan Booth None
    Okay. How many are in that held-out set? Just roughly.
  9. Callie Brennan
    Callie Brennan None
    A couple of dozen. I've put them in a sheet with the order lines they came from. I'll share it. What I need from your side is a decision on each: is it a different part, or the same part written differently?
  10. Nathan Booth
    Nathan Booth None
    I can do some of them myself. A few I'd need to check with the planners.
  11. Callie Brennan
    Callie Brennan None
    That's fine. Do what you can, and mark the rest as unknown. I'd rather an honest unknown than a wrong answer.
  12. Nathan Booth
    Nathan Booth None
    Agreed. Can I ask something? When a part is corrected in the order system afterwards, does the brain keep the old value or overwrite it?
  13. Callie Brennan
    Callie Brennan None
    It takes the current value at each nightly refresh. So if a planner corrects a part reference on Tuesday, Wednesday morning it reflects that. The history of the change itself isn't kept unless the source system holds it.
  14. Nathan Booth
    Nathan Booth None
    That's fine for us. I just wanted to be sure nobody expects an audit trail from it.
  15. Callie Brennan
    Callie Brennan None
    Worth saying out loud, and I'll put it in the setup note so Ruth sees it too.
  16. Callie Brennan
    Callie Brennan None
    Now the helpdesk. Your access note arrived, thank you. I started the connector yesterday afternoon, and the tickets are in. The order reference join, the one we talked about, I've run it.
  17. Nathan Booth
    Nathan Booth None
    And?
  18. Callie Brennan
    Callie Brennan None
    Most tickets joined to an order. Some didn't, because the reference field was empty, or had text that isn't an order number. Notes like see email, that kind of thing. I've listed those so you can see which ones they are.
  19. Nathan Booth
    Nathan Booth None
    I know the sort. It's mostly the older ones, before we made the field expected. Newer ones are better.
  20. Callie Brennan
    Callie Brennan None
    That matches what I see. The recent tickets join well, and the older ones are patchy. So for questions about the last few months you'll get good answers, and for older material I'd treat it with care.
  21. Nathan Booth
    Nathan Booth None
    Can the free text be used to fill the gaps?
  22. Callie Brennan
    Callie Brennan None
    It can be searched, and the brain can read it. I wouldn't want to promise it'll find an order number reliably from free text. It might. I'd call that a second pass, once the first is settled.
  23. Nathan Booth
    Nathan Booth None
    Fair. Let's do it properly first.
  24. Callie Brennan
    Callie Brennan None
    Agreed. Now, categories. You have a category field on tickets. I'd like to check I understand them. Can you talk me through what the main ones mean?
  25. Nathan Booth
    Nathan Booth None
    Sure. There's a dimensional one, for out of tolerance. A surface finish one. Paperwork, which is certificates and documentation. Late delivery gets raised by customer ops, not quality, but it ends up in the same system. And an other.
  26. Callie Brennan
    Callie Brennan None
    Good. I'll map those as they stand, so the names people use are the names they see. The other one I'd flag. If it's a big bucket, it's a sign something needs a category of its own.
  27. Nathan Booth
    Nathan Booth None
    It is a big bucket, to be honest. Ruth knows. I think it'll come up once she sees it.
  28. Callie Brennan
    Callie Brennan None
    That's a good outcome for the brain, if it helps her see it. Okay. Now users.
  29. Nathan Booth
    Nathan Booth None
    Ruth gave me two names for the first people. I've got them added, as invited users, not yet logged in.
  30. Callie Brennan
    Callie Brennan None
    Lovely. I'd hold the invitations until the first look at the data is done. If the first thing they see is half-mapped, they'll form a view and it's hard to change.
  31. Nathan Booth
    Nathan Booth None
    Agreed. I'll hold them until after the holiday. Ruth wants to look first anyway.
  32. Callie Brennan
    Callie Brennan None
    That fits. So the plan over the break: the nightly refresh runs on the two sources as they are. Nothing new connected until we're back. Nathan, could you do a quick look on a couple of mornings to check it ran? I'll show you where.
  33. Nathan Booth
    Nathan Booth None
    Yes, show me. I'd rather check than assume.
  34. Callie Brennan
    Callie Brennan None
    So, share your screen and I'll walk you through the refresh status page. On the left you'll see the connectors, each with a last-run time and a records count.
  35. Nathan Booth
    Nathan Booth None
    I've got it. Order system, last run overnight. Helpdesk, same.
  36. Callie Brennan
    Callie Brennan None
    Right. What you're looking for is the time being this morning and the count not being lower than yesterday. If the count's the same for days on end, that's the sign the source has stopped feeding through, even if nothing's flagged red.
  37. Nathan Booth
    Nathan Booth None
    Flat counts, got it. And if it is?
  38. Callie Brennan
    Callie Brennan None
    Email me. Don't wait. I'll be offline for a couple of days, but I'll look when I'm back, and you'll also have the support route.
  39. Nathan Booth
    Nathan Booth None
    I will.
  40. Callie Brennan
    Callie Brennan None
    Actions. Nathan: decisions on the held-out parts, as many as you can, and a look at the status page on a couple of mornings. Me: the setup note, with the audit trail point and the older ticket caveat, and the held-out sheet to you before I sign off today.
  41. Nathan Booth
    Nathan Booth None
    Sounds right. When's the next call?
  42. Callie Brennan
    Callie Brennan None
    The week after the holiday. I'll send an invite for a day that suits you and Ruth. Have a good Christmas, Nathan.
  43. Nathan Booth
    Nathan Booth None
    And you. Cheers, Callie.

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