Muthukrishnan Bommiah · muthub.org
In June, Google Cloud published the Open Knowledge Format, and July's v0.2 added provenance, verification and freshness. It is the right foundation. Regulated enterprises still need to add ownership, classification and a policy for how much trust an agent needs before it acts.
Context engineering7 min readDocumentation fails because it is a second job. The knowledge we need is already produced as a by-product of work: commits, tickets, incidents, reviews and decisions. Capture it passively, distill it, and keep a human approval gate before anything becomes trusted.
Context engineering6 min readThe tempting answer to fragmented context is to pour everything into one place. We tried that with data, and many lakes became swamps. A context layer has to be a curated overlay: retrieval-first, owned, and pointing back to the systems that hold the truth.
Context engineering6 min readMost enterprise AI pilots hit the same wall: systems record what happened, but the reasoning behind decisions evaporates. Durable, governed context about the why is the real foundation for useful agents.
Data & AI platforms6 min readThe knowledge an agent needs is scattered across code, tickets, chat, wikis, incident tools and people's heads. Each fragment is accurate and useless alone. Fragmentation, more than model quality, is what makes enterprise agents brittle.
Context engineering6 min readEnterprises budget for compute, models and licenses, but almost none budget for the context those models depend on. Unmanaged context is the largest cost nobody tracks, and every new AI agent adds to it.
Context engineering6 min readDocs that regenerate on every commit describe what code does. The harder, more valuable problem is capturing why it exists.
Note1 min read