Personal AI memory is not company memory
Every big AI tool now remembers you. None of them remembers your company. What the difference is, and what we changed in our own setup today.
Insights
Notes from running our own companies.
What we learn putting sales follow-up, back office systems and AI to work, first in our own businesses and then in our clients'.
- 5 min read
- 3 min read
What we keep out of our AI's memory, and why
This week we copied our company memory so a second AI provider could read it. Deciding what to leave out was the hard part.
- 3 min read
A generic AI persona does not know how your firm works
Built-in 'marketing expert' and 'legal assistant' personas sound capable and know nothing about your firm. Write your own role profiles instead.
- 3 min read
What a vending machine test says about agents in your back office
In Vending-Bench, AI agents running a simple business for a long stretch drifted into failure. The cause matters for anyone handing agents recurring work.
- 4 min read
Your files hold what you wrote, not what you decided
An AI connected to your documents will find the plan you abandoned and recommend it again. Decisions and failures need a home of their own.
- 4 min read
We misread a client brief twice. Write the exceptions down
Good defaults cause expensive mistakes when nobody writes down where they stop applying. What our own misread brief taught us about rules with exceptions.
- 3 min read
Why a small East African firm can get its AI ready faster
Big firms are ahead on AI agents, but what agents need most is written context. A 20-person firm in Nairobi can produce that in weeks.
- 3 min read
A shared AI memory is a new leak unless you scope it
Putting company knowledge where every AI session can read it also creates one place to lose it. Five design rules that keep memory from widening the leak.
- 3 min read
Ten people, ten ChatGPTs, and no shared rules
Most teams already use AI, each person in their own way and often in secret. Questions owners ask us about shadow AI, answered plainly.
- 4 min read
Why your AI forgets the rules by the fortieth message
Rules typed at the top of a long AI chat fade as the conversation grows. Why it happens, and where the rules should live instead.
- 3 min read
Readers mark down anything that sounds machine-written
Customers trust copy less once they suspect AI wrote it, even when a person did. Generic output now has a sales cost. What helps, and what does not.
- 4 min read
Write the AI pilot's stop rule before you write the prompt
Most AI pilots are not killed. They fade, and nobody records why. Six lines to write on day one so a pilot either earns its place or ends cleanly.