Category Archives: Technology

Amazon AWS AIP-C01: Multi-Agent Systems on AWS Multi-agent architecture is useful when one model-driven workflow becomes easier to govern by splitting responsibilities among specialized agents. The value is not that several agents sound more intelligent than one. It is that planning, domain knowledge, tools, permissions, and accountability can be divided into narrower units with clearer […]

Amazon AWS AIP-C01: OpenSearch Hybrid Search Hybrid search combines lexical retrieval with semantic retrieval so that exact terms and meaning can contribute to the same result set. That matters in generative AI because retrieval quality determines which evidence reaches the model. Keyword search is strong when product codes, names, error strings, and rare terms matter; […]

Prompt optimization sounds like a shortcut for writing better instructions, but the useful version is more disciplined than “ask another model to rewrite the prompt.” Google’s Prompt Optimizer can search for improved instructions and examples against an evaluation objective, giving teams a repeatable way to compare prompt candidates instead of relying only on intuition. Google […]

Savings Plans and EC2 Reserved Instances both exchange flexibility for lower compute pricing, but they bind that commitment in different ways. Savings Plans commit to a consistent amount of eligible usage measured in dollars per hour. Reserved Instances commit more directly to an EC2 configuration and, depending on scope, can also provide capacity reservation. The […]

Retrieval-augmented generation becomes operationally difficult after the first successful demo. The model call is usually the easy part. The harder questions are how documents are parsed, how chunks are created, which embedding model represents them, where vectors and metadata are stored, how retrieval is filtered, and how the evidence is passed into generation without losing […]

AWS Step Functions error handling is most effective when a workflow distinguishes transient failure from permanent failure. A network timeout, a throttled API, invalid business input, an authorization error, and an oversized state payload should not all receive the same retry policy. Step Functions provides retriers, catchers, explicit error names, backoff, jitter, and redrive capabilities […]

AWS Transit Gateway route tables can be used as routing domains that segment groups of VPC, VPN, Direct Connect, peering, and other supported attachments. The useful mental model is similar to virtual routing and forwarding: an attachment sends traffic into one associated transit gateway route table, and that table determines which destination attachment receives the […]

Change data capture becomes difficult when the target needs more than a simple “latest row wins” merge. Source systems can emit inserts, updates, deletes, late events, duplicate events, and out-of-order changes. Analytics teams may also need both the current state and a history of how that state changed. Databricks Lakeflow pipelines address that problem with […]

“Vertex AI Model Armor” is a useful search term, but the current Google Cloud product is Model Armor, a separate security and safety service that can protect generative-AI traffic, including Gemini requests on Google’s current Gemini Enterprise Agent Platform. Google renamed much of the Vertex AI generative-AI surface in April 2026, so architects now need […]

Lakeflow Connect managed connectors are Databricks’ answer to a common data-engineering problem: moving operational data into the lakehouse without every team building and operating its own extraction framework. The managed connector layer handles source-specific authentication, incremental reads, schema handling, retries, and ingestion-pipeline execution for supported systems. That can remove substantial plumbing, but it also changes […]

Vertex AI Model Garden has long been Google Cloud’s catalog for discovering and using Google, partner, and open models. In April 2026 Google renamed the wider generative-AI platform to Gemini Enterprise Agent Platform, and the current name is simply Model Garden on that platform. The older “Vertex AI Model Garden” term remains important because documentation, […]

Parameters are how a reusable Lakeflow Job becomes a production workflow instead of a hard-coded sequence that has to be cloned for every environment, date, customer, or backfill. Databricks supports parameters at the job level and at individual tasks, along with dynamic value references and task values for passing information through a workflow. The useful […]

Model monitoring is easy to reduce to a chart labeled “drift,” but production monitoring is really a decision system. A team chooses a baseline, chooses the production data to compare against it, selects a distance metric, defines thresholds, and then decides what an alert should cause humans or automation to do. Google’s current Model Monitoring […]

A failed data job does not always justify replaying an entire workflow. In a multi-task Lakeflow Job, some tasks may have completed successfully, others may have failed, and downstream tasks may have been skipped because their prerequisites never finished. Databricks repair runs are designed for that situation: they preserve the original run context while re-running […]

Safety filters are one of the most misunderstood parts of a generative-AI architecture because teams often treat them as a universal “safe mode.” In practice, the Gemini API exposes configurable content-safety controls for defined harm categories, while Google also applies non-configurable protections for certain prohibited content. The application chooses thresholds for supported configurable categories and […]