Build and run production workloads on Amazon Bedrock with current model availability, Converse API, agents, guardrails, AgentCore, and IAM controls. Use when implementing Bedrock inference pipelines, managed agents, or provider-agnostic model routing on AWS.
Design evaluation, tracing, monitoring, scope-control, and rollback discipline for agent systems. Use when an agent workflow is becoming important enough that you need evidence, not vibes, to decide whether it is good.
Build and operate OpenAI-first coding and agent workflows using Codex app/cloud, the Responses API, current GPT and Codex models, Agents SDK, hosted tools, tool search, MCP/connectors, skills, and approval-aware tool execution. Use when you need long-horizon software agents or OpenAI-native multi-agent orchestration.
Design, evaluate, and operate agentic systems for biomedical and scientific discovery. Use when building or selecting agents for hypothesis generation, experiment planning, autonomous notebook analysis, lab-in-the-loop validation, pathology concept discovery, or multi-agent research workflows.
Implement and operate Model Context Protocol systems safely. Use when designing MCP clients or servers, selecting transports, configuring auth, onboarding remote servers, or enforcing approval and egress controls.
Batch effect correction for multi-cohort bulk RNA-seq data using ComBat, with PCA-based visualization before and after correction.
WGCNA-style weighted gene co-expression network analysis — module detection, soft thresholding, hub genes.
Differential expression analysis via PyDESeq2 with Welch's t-test fallback — volcano plots, MA plots, p-value diagnostics.