AGENTIC9 minMay 12
One mind, a fleet underneath: orchestration patterns for senior engineers
Six patterns we use for splitting work between an engineer and a multi-agent fleet — and the three patterns that look right but quietly fail.
Bibek Pandeyread →
APPLIED AI14 minMay 04
RAG isn't a feature. It's an engineering discipline.
Most retrieval-augmented systems fail not at the model layer but at the engineering layer around it. A field-tested checklist.
Anjali Maharjanread →
OPERATIONS7 minApr 29
The 24-hour change cycle: how we close most requests by next morning
It's not magic and it's not "we work harder." It's a specific operating model. Here is exactly how it works.
Prabin Shrestharead →
ENTERPRISE11 minApr 22
Strangling a 14-year-old monolith, politely
How we moved a regulated insurance platform off its mainframe without one big-bang weekend. The boring parts are the hardest.
Tara Adhikariread →
AGENTIC5 minApr 14
What we don't ask agents to do
A short list of the architectural and product decisions we still won't delegate. And the principle behind the line.
Bibek Pandeyread →
PRACTICE6 minApr 06
Outcome pricing: numbers that ship
Why we don't sell hours, how we scope outcome contracts, and what we tell clients who insist on per-hour pricing anyway.
Founder's Officeread →
APPLIED AI10 minMar 28
Evals as tests: bringing CI/CD discipline to AI features
If you wouldn't ship code without tests, you shouldn't ship a model without evals. A practical pipeline.
Anjali Maharjanread →
OPERATIONS4 minMar 19
Quiet alerts: noise-free incident response
A page that pages too often pages no one. Our rules for what counts as an alert and what doesn't.
Prabin Shrestharead →
PRACTICE12 minMar 10
Pushing back: the part of the job we charge nothing for
Why we tell clients when the feature is wrong, before we write a line of code. With three real examples from the last year.
Founder's Officeread →
