All audit how I ai teachmetrics
Blog Blog
The Correction of Error

Every system makes mistakes. What separates a trustworthy one is what it does next. A Correction of Error is a structured, no-blame admission: what broke, why the system allowed it, and what changes so the whole class of bug can't return. In our harness the AI files them unprompted, against a written standard, including failures nobody would have caught. Prevention isn't maturity. Honest correction is.

Read more
Blog Blog
Humanity in the loop

We talk a lot about “humans in the loop.” But humans get tired. Humans rubber-stamp. Humans become bottlenecks. The real challenge is preserving humanity in the loop: truthfulness, accountability, craftsmanship, humility, and trust. I explore how a single AI agent can build and review its own work when guided by shared tenets and honest retrospection.

Read more
Tools Blog
How impeccable.style sharpened the way I ship Assurcast

For two days, every UI decision on Assurcast started with an opinionated design agent reviewing my actual code. A dozen cards shipped: Restrained color strategy, real type ramps, a mobile sticky bar, 44pt touch targets, source-byline emphasis above each story title. The best moment? When I rejected its biggest finding and it helped me document why. impeccable.style by Paul Bakaus. AI as design collaborator with strong views, not a stylebot. #howiai #claudecode #design #indiehacker

Read more

I help modern audit and risk professionals embrace data analytics and AI to transform assurance. I also build software products in the social, grc, and analytics domains.

Subscribe

By email

Get the latest news and updates in your inbox.

Customize preferences

By feed reader

We publish RSS, Atom, and JSON feeds sliced by category and tag.

View all feeds →
Feeds
Subscribe by email

Get the latest news and updates in your inbox.

Customize preferences