New models and tools ship every day. I ask one question: will it hold up in production? Notes on data, AI and traceability, for the people who have to run them.https://rainwu0710.com/enhttps://rainwu0710.com/writing/dbt-agent-trust-eval-framework/https://rainwu0710.com/writing/dbt-agent-trust-eval-framework/Data Culture took an e-commerce analytics agent from 0% to 94.7% accuracy without changing the model, by adding context one layer at a time and grading it on a fixed exam. Using their open-source agent-trust-for-dbt repository, I draw the architecture as five layers, from the dbt foundation and the contract the agent reads to a grading cascade that ends in an LLM judge, and sort what you can copy as-is from what you should change.Wed, 28 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/entire-trails-agent-review-flow/https://rainwu0710.com/writing/entire-trails-agent-review-flow/Entire, the company former GitHub CEO Thomas Dohmke started, launched a Git forge for people and agents on October 26. It swaps the pull request for a Trail, where review agents rescore every push and gates, CI and people decide whether a change merges. I walked one change through it using the official docs and mapped who does what at each step.Wed, 28 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/liquid-clustering-layout-benchmark/https://rainwu0710.com/writing/liquid-clustering-layout-benchmark/An InfoQ benchmark compares partitioning, ZOrder and Liquid Clustering on 50 million Delta Lake rows. I chart latency and data read for the three measured query types, point out that the fourth, a full-scan aggregation, repeats the second one's numbers, and lay out each layout's strengths and weak spots in one table.Mon, 26 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/raw-history-agent-memory-baseline/https://rainwu0710.com/writing/raw-history-agent-memory-baseline/Two October papers pit elaborate agent-memory systems against a plain baseline that keeps raw conversations and retrieves with reranking. The baseline wins six of seven settings and ingests in a fraction of the time. Build it first, measure write cost, accuracy and lost evidence, then choose a memory architecture.Mon, 26 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/claude-text-watermark-eu-ai-act/https://rainwu0710.com/writing/claude-text-watermark-eu-ai-act/To meet the EU AI Act, Anthropic has watermarked the text output of new Claude models since August. I explain what happened and how the watermark works, unpack what Article 50 asks of providers and publishers, and lay out what a watermark can and cannot answer.Sat, 24 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/dashboards-to-summary-agents/https://rainwu0710.com/writing/dashboards-to-summary-agents/Jeweler Brilliant Earth moved its analytics into Snowflake, took 100+ store users off a legacy BI tool and has an LLM write weekly reports from numbers its code computes. I use the case to answer one question. If visualization is the last step of the data pipeline, will an agent that summarizes take its place?Sat, 24 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/shipsidekick-neon-to-clickhouse-postgres/https://rainwu0710.com/writing/shipsidekick-neon-to-clickhouse-postgres/Logistics SaaS Shipsidekick moved its Postgres from Neon to ClickHouse Managed Postgres and cut over in a weekend. I chart the core numbers before and after and the migration steps, and separate what came from architecture, what came from a bigger machine, and the bill the case study leaves out.Sat, 24 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/dbt-state-free-tier/https://rainwu0710.com/writing/dbt-state-free-tier/dbt Labs made dbt State free forever for self-hosted users, at 1,000 DATT a month. I explain how it decides to skip, clone or rebuild, how to use it in prod, staging and dev, and what the free allowance is actually worth.Wed, 21 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/snowflake-decision-fast-warehouse/https://rainwu0710.com/writing/snowflake-decision-fast-warehouse/On October 19 Snowflake announced Decision Fast, a low-latency decision model in private preview that returns classifications, scores and routes with probabilities from a single SQL call. I draw its design in three steps and look at where a model like this saves the most money and time inside a warehouse.Wed, 21 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/snowflake-pipeline-repair-agent/https://rainwu0710.com/writing/snowflake-pipeline-repair-agent/Snowflake's data team uses agents to repair failed data pipelines, averaging under 16 minutes from detection to a pull request waiting for review. I turn the setup into a tutorial you can follow, covering what you need first, how to build it, what it buys you, how to roll back and at what cost, and what the original post leaves out.Wed, 21 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/databricks-multi-statement-transactions/https://rainwu0710.com/writing/databricks-multi-statement-transactions/Databricks made multi-statement, multi-table transactions generally available on October 16, but gives each customer story a single quote. Here are the Fivetran and Accolade cases spelled out (the old two-step writes, what a failure halfway left behind, what one transaction changes) plus the path from BEGIN to END.Sat, 17 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/atlassian-ocsf-security-lakehouse/https://rainwu0710.com/writing/atlassian-ocsf-security-lakehouse/Atlassian normalized two decades of messy security logs into OCSF on a Databricks lakehouse and reports an 80% cut in ingestion cost; here are the seven moves behind it, in the order the data travels, and why the 80% is attributed three different ways.Fri, 16 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/snowflake-postgres-mirroring-vs-lakebase/https://rainwu0710.com/writing/snowflake-postgres-mirroring-vs-lakebase/Snowflake Postgres data mirroring went GA on October 15; next to Databricks Lakebase it has the stronger consistency story but makes you choose between fresh and transactionally whole, while Databricks already syncs both ways with the Postgres-to-Delta leg still in preview.Fri, 16 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/ai-track-before-train/https://rainwu0710.com/writing/ai-track-before-train/Snowflake's manufacturing survey says 41% of manufacturers are stuck in pilots and half still run on spreadsheets. EU, US and Chinese figures measure different things but point the same way. AI is the train, the data foundation is the track, and most companies haven't laid it yet.Tue, 13 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/databricks-openjev-judge-audit/https://rainwu0710.com/writing/databricks-openjev-judge-audit/Databricks now lets a small classifier, OpenJev, act as the judge in Unity Gateway service policies. I like decision models taking over filter scripts, but in audited work you need answers on confidence, replay and rollback first.Mon, 12 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/eu-gdpr-audit-gap/https://rainwu0710.com/writing/eu-gdpr-audit-gap/An IAPP column asks whether predictability and coherence can make up for the EU's missing regulatory convergence. My view is that the rules can be strict, but only regulators and companies can check them. Individuals get a statement.Sun, 11 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/harness-zero-error-agents/https://rainwu0710.com/writing/harness-zero-error-agents/Financial regulatory reporting demands zero errors, and an AICon talk lays out a full set of controls for agents. The logic holds, but it buys accuracy with constraints, and non-standard data created upstream is still there.Sun, 11 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/data-engineering-specialist-agents/https://rainwu0710.com/writing/data-engineering-specialist-agents/Josh Wills says agents write data pipelines that are correct and wildly expensive. I read that as a missing feedback problem, and it points to what data engineering is waiting for, a specialist agent.Sat, 10 Oct 2026 00:00:00 GMThttps://rainwu0710.com/writing/d1-decision-model-errors-at-scale/https://rainwu0710.com/writing/d1-decision-model-errors-at-scale/Liquid AI open-sourced d1, a small model that answers without writing text. I want models like this, but before production I'd multiply its error rate by its call volume.Fri, 09 Oct 2026 00:00:00 GMT