engineering▌

Diagnose whether your AI workflows are context stuffing or context engineering, then implement structured practices to improve output quality. \n \n Distinguishes between context stuffing (volume-based) and context engineering (structure-based), with five diagnostic questions to identify Context Hoarding Disorder \n Guides two-layer memory architecture: short-term conversational memory plus long-term persistent memory via vector databases for semantic retrieval \n Implements the Research→Plan→Re

Comprehensive PostgreSQL database engineering covering indexing, query optimization, replication, and production management. \n \n Covers 6 index types (B-tree, Hash, GiST, GIN, BRIN, SP-GiST) with decision matrices for choosing the right index for specific query patterns \n Includes streaming and logical replication setup, failover procedures, and high-availability configuration with synchronous/asynchronous modes \n Provides partitioning strategies (range, list, hash) with automation examples

Engineering operating model for teams shipping code with AI-assisted generation. \n \n Emphasizes planning quality, evaluation coverage, and behavior-focused code review over traditional syntax checking and typing speed \n Requires agent-friendly architectures with explicit boundaries, stable contracts, typed interfaces, and deterministic tests to minimize implicit behavior \n Shifts review priorities to behavior regressions, security assumptions, data integrity, failure handling, and rollout sa

Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.

A diagnostic skill that identifies code, architecture, and technical decisions built to impress rather than to ship. Vanity engineering is entropy disguised as craftsmanship — it increases complexity without proportional capability gain, and it compounds maintenance cost while delivering zero additional user value.

AI-guided antibody optimization pipeline from preclinical lead to clinical candidate. Covers sequence humanization, structure modeling, affinity optimization, developability assessment, immunogenicity prediction, and manufacturing feasibility.

Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.

Master prompt engineering for AI models via inference.sh CLI.

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.