An AI Employee Should Learn You AND Your Company — They're Not the Same Thing
Matthew, founder of Bob · July 6, 2026
Key takeaways: "The AI learns your company" is quickly becoming table stakes. But companies don't do work — people do, and two people doing the same job well often do it completely differently. Bob keeps two kinds of memory: how you work, and what's true for your organization — and never confuses the two.
The flaw in one big brain
Here's a real pattern from any team you've ever worked on: the ops lead wants everything as a spreadsheet with pivot-ready columns. The founder wants three bullets and a number. Same report, same company, same "right answer" — different people. Both are correct.
An AI teammate with one undifferentiated memory pool learns a mush of both. Someone says "always give me bullet points" and suddenly everyone gets bullet points. Someone corrects it once in a DM and the correction leaks into a channel it doesn't apply to. The more it "learns your company," the more one person's habits become everyone's defaults. That's not learning — that's averaging.
Two memories, deliberately
Bob keeps them separate:
Person memory. How you like things done: your formats, your tone, your shortcuts, which spreadsheet layout you actually open. Private to you — your preferences never restyle a teammate's work.
Org memory. What's true for the whole workspace: the fiscal year starts in February, refunds over $500 need a manager, the weekly report goes to #ops on Fridays. Shared by everyone, because it is everyone's.
When you ask Bob for something, it recalls both — the org's facts and your way of working — and produces the version of correct that's correct for you. When your teammate asks for the same thing an hour later, they get the version that's correct for them. Same facts, different hands.
The mechanics are simple and auditable: when Bob decides something is worth remembering, it chooses a scope. "I like..." is usually about you. "We do..." is usually about the org. It errs toward org memory for anything ambiguous, and it can tell you which pool a remembered fact lives in.
Why this matters more as AI teammates spread
The industry is racing toward agents that absorb organizational context, and absorbing context is genuinely valuable — we're building the same muscle. But memory design is trust design. Memory that isn't scoped is memory that leaks: across people, across teams, across the boundary between "my working style" and "company policy." Scoping isn't a feature we added to memory. It's what makes memory safe to use.
FAQ
Can I see or delete what Bob remembers?
Memory is stored per workspace in plain, readable facts — an admin surface for reviewing and pruning is on the roadmap; today, asking Bob what it remembers (and telling it to forget) works in the thread.
Does my personal memory follow me across workspaces?
No. All memory is scoped inside your workspace. Nothing crosses tenants, ever.
What about scheduled jobs — whose preferences do those use?
Scheduled runs have no invoking person, so they use org memory only. Deliberately: an unattended job should behave like the company, not like whoever created it.
See a receipt for yourself.
The first ten teams onboard with the founder — 50% off Managed for year one and 3× credits for 90 days, in exchange for a monthly 30-minute feedback call.
Talk to the founder See pricing →