AI Tutorials
August 25, 2026•13 min read
Do Not Mix the Maps: A Safe Migration for Embedding Indexes
A field guide to rebuilding, evaluating, cutting over, and rolling back vector search when the embedding model, chunks, or index must change.
Blog
Insights, tutorials, and updates from the ZharfAI team
Blog
AI Tutorials
August 24, 2026•15 min read
A Number Is Not a Quantity: The Measurement Contract for AI
A field guide to units, currency, precision, rounding, and deterministic calculation before AI-generated numbers can create business effects.
AI Tutorials
August 23, 2026•14 min read
The Last Release: Retire an AI System Without Leaving It Running
A field guide to closing intake, authority, dependencies, work, evidence, and data so an AI service can be replaced or retired with a verifiable end state.
AI Tutorials
August 22, 2026•13 min read
The Answer Is Optional: An Abstention Contract for AI
A practical guide to deciding when AI should answer, seek evidence, defer, or refuse using calibrated signals, risk–coverage curves, and fallback capacity.
AI Tutorials
August 21, 2026•14 min read
Before You Install the Tool: A Supply-Chain Gate for AI Agents
A field guide to admitting, quarantining, or rejecting MCP servers, plugins, and agent tools using provenance, capability tests, and enforceable runtime limits.
Health & Medicine
August 20, 2026•10 min read
AI-Designed mRNA Cancer Therapy Meets Phase 3 Endpoints
Intismeran plus Keytruda delayed melanoma recurrence in Phase 3. Here is what AI designed, what the topline result proves, and what remains unknown.
AI Tutorials
August 20, 2026•13 min read
Drift Is a Clue, Not a Verdict: Monitoring AI After Deployment
A field guide to baselines, delayed outcomes, change attribution, and deciding when deployed AI should be watched, constrained, rolled back, or rebuilt.
AI Tutorials
August 19, 2026•14 min read
No Secret Before Proof: Confidential Computing for AI
A decision guide to trusted execution, remote attestation, workload-bound channels, and secret release for sensitive AI inference and training.
AI Tutorials
August 18, 2026•14 min read
The Recovery Cut: Rebuilding AI Systems Without Mixing Timelines
A field guide to recovery points, state classification, rebuildable indexes, external-effect reconciliation, and drills for stateful AI systems.
AI Tutorials
August 17, 2026•14 min read
The Borrowed Credential: How AI Agents Get Access Without Holding Secrets
A field guide to workload identity, token exchange, scoped credentials, connector proxies, and evidence when AI agents need temporary access to enterprise systems.
AI Tutorials
August 16, 2026•14 min read
The Tenant Boundary: Isolation for Shared AI Systems
A field guide to deciding what may be pooled, what must be siloed, and how to keep retrieval, memory, caches, tools, logs, and evaluations inside the right customer boundary.
AI Tutorials
August 13, 2026•14 min read
The Fact Was True, But When? Time Semantics for AI Systems
A practical architecture for separating event, observation, record, snapshot, decision, and action time so AI systems can reason honestly about changing facts.