Moving Diagnostic Accuracy 42.9% → 85.7% by Changing Two Files
Sometimes the win is structural, not algorithmic. A walkthrough of two file edits that doubled diagnostic accuracy on the benchmark.
All 127 posts in date order, newest first. ← back to topics
Sometimes the win is structural, not algorithmic. A walkthrough of two file edits that doubled diagnostic accuracy on the benchmark.
The architecture and compliance story behind Bodh — an open-source HIPAA-aware multi-agent medical AI platform.
What looked like an idiomatic BigQuery MERGE was scanning the full target table on every batch. The fix was syntactic, not architectural — and it was the single biggest contributor to a 57% data-warehouse cost reduction across the Tata Group engagement.
₹100 Cr / ~$12M in proven savings across a year-plus engagement. The four levers that did the heavy lifting, the lever I expected to win that didn't, and the post-engagement playbook that became a Searce managed service.
We built a small Go + Python service that parses a project's INFORMATION_SCHEMA, asks Gemini to classify each top-spending query against a catalog of anti-patterns, and recommends a rewrite. It is not a magic box; it is a pipeline that cuts the human review time per query from 20 minutes to 90 seconds.
Capacity-based slot reservation is the biggest single FinOps lever for predictable batch workloads, but the transition is harder than the math. Notes from sizing reservations across enterprise GCP customers.
Storage was the second-biggest line item on the Tata BigQuery bill. Long-term storage, physical-vs-logical billing, and column-level retention together took a 6-figure monthly line down to a 5-figure one.
Notes from contributing to Google's open-source Spanner Migration Tool (HarbourBridge). Where to start reading the codebase, where the load-bearing logic lives, and the parts that look simple but aren't.
Spanner partitions by primary-key range. A monotonically-increasing PK like a timestamp or UUID-v1 funnels all writes to one server. The fix changes everything from your sequence strategy to your tenant model.
Interleaving a child table into its parent co-locates the rows for fast joins. It also tightens coupling in ways that bite you on the next schema migration. A practitioner's decision matrix.