A Company Brain Example: The One That Runs My Company
Oct 14, 2026 · 8 min read
A real company brain example: the folders, the jobs that feed it and the commands that read it, after 3,474 commits. And what still breaks.
Read morePick a topic, or start with the three posts below. The older posts cover AI coding and Django.
Oct 14, 2026 · 8 min read
A real company brain example: the folders, the jobs that feed it and the commands that read it, after 3,474 commits. And what still breaks.
Read moreOct 31, 2026 · 8 min read
Only if the contract allows it and you're on a company plan. Training off doesn't release an NDA, and deleting a chat can leave what Claude remembered.
Read moreOct 16, 2026 · 7 min read
Claude Code works for non-technical people when the work is documents. Our team installs four things. What we took off their plate, and what's still hard.
Read moreNov 1, 2026 · 12 min read
Two months of Claude desktop changes, checked against Anthropic's docs: what to use, what to skip, and what Team plans don't get yet.
Read moreOct 31, 2026 · 8 min read
Only if the contract allows it and you're on a company plan. Training off doesn't release an NDA, and deleting a chat can leave what Claude remembered.
Read moreOct 31, 2026 · 7 min read
Yes, once you set it up. It runs as you, beyond any one folder, and new sessions let a second model approve actions in your place.
Read moreOct 31, 2026 · 7 min read
Safe if you block delete first. Claude's Dropbox connector can remove files but can't restore them, and on a team the big undo belongs to an admin.
Read moreOct 31, 2026 · 8 min read
Safe once you change one default. Out of the box any teammate can open your meetings, and Claude likely inherits that. Fix it before anyone connects.
Read moreOct 31, 2026 · 7 min read
Safe if writes need your approval. An event, change or RSVP from Claude emails every attendee by default, and one Anthropic page calls it read-only.
Read moreOct 31, 2026 · 8 min read
Safe if one admin connects it and approves every call. The listing says query and analyze. The tools can run payroll and link a bank account.
Read moreOct 31, 2026 · 7 min read
Safe once an admin sets it. Connecting for Jira tickets can also open Confluence public links and code merges unless you turn those groups off.
Read moreOct 31, 2026 · 8 min read
Safe if you check first. On Business or Enterprise with Notion AI, it can reach linked Slack, Gmail and Drive. Notion's docs list trashing databases.
Read moreOct 31, 2026 · 7 min read
Safe on Read-only. The listing says read-only, but Full access is Ramp's default, and a bill approved there can start the payment.
Read moreOct 31, 2026 · 7 min read
Safe in a sandbox or with tight permissions. Stripe's human check covers refunds, not voided invoices, canceled subscriptions or new webhooks.
Read moreOct 30, 2026 · 15 min read
I traced the famous AI failure rates to their sources. RAND's 80% is a footnote to a CEO profile, and MIT's own chart points nearer 75% than 95%.
Read more