Distributed Systems • AI Runtime Context • Agent QA • DuckLake Telemetry
20+ years architecting scalable AI-driven infrastructure. Building Softprobe to eliminate the 200x observability "indexing tax" and provide forever-cheap runtime evidence for AI agents.
Why traditional log warehouses force teams to discard 90% of their runtime data, and how a session-graph architecture on S3/DuckLake collapses observability costs.
Why traditional APMs and prompt stacking fail autonomous coding agents, and why full runtime context graphs are the true fuel for production AI.
Why traditional log warehouses force teams to discard 90% of their runtime data, and how a session-graph architecture on S3/DuckLake collapses observability costs.
How to architect a modern engineering blog for generative answer engines using semantic microdata, high information density, and machine-readable feeds.
How Softprobe keeps agent session triage snappy while the lake stays the single source of truth.
Selected research and engineering notes on modern agent systems.
Testing and validating autonomous AI agents and coding tools.
Session graphs, runtime context, and escaping the indexing tax.
High-throughput telemetry, storage engines, and consensus.
Architecting backends and data pipelines for autonomous agents.
Generative Engine Optimization for AI search engines.