Execute Groq incident response: triage, mitigation, fallback, and postmortem.
Set up observability for Groq integrations: latency histograms, token
Evaluates and prioritizes growth, conversion, and retention experiments based on evidence, capacity, and risk constraints.
Apply GSD Core's loop-engineering methodology to ML/data-science tasks.
Quick-start guide for gs_quant: session setup with GsSession, constructing portfolios, resolving instruments.
When the user wants to define GTM metrics, build a metrics dashboard, measure pipeline efficiency, or track AI product performance.
Fires when a fellow needs to decide how an AI product is stopped from doing the wrong thing — "design the guardrails", "when does a human…
Incident response runbook for Guidewire InsuranceSuite production incidents.
Operate a Guidewire Cloud API integration in production — define SLIs/SLOs for token availability, bind success rate, FNOL p99 latency…
Use right after a hackathon problem/plan is scoped (e.g. following hackathon-brainstorm, or from a fresh prompt) to build the first…
Per-individual prediction-interpretation report: loads one individual's data and recent CGM, hits the deployed endpoint, then asks Claude…
Routes agents using HanLP for multilingual NLP via native Python
Phases diploid genotypes into chromosome-length haplotypes using Beagle 5.4 and SHAPEIT5 command-line workflows.
Performs a comprehensive 7-dimension audit of platform configurations to identify capability gaps and provide actionable improvement…
Displays Harness UI dashboard for monitoring and task management.
Debug AI agents and LLM applications via Langfuse MCP.
Produce a full status report on the perpetual headless Claude Code agent running in the current project (set up via the headless-agent…
Implement health check and readiness endpoints for SDK consumers
Analyzes and optimizes health goal data by tracking progress, evaluating SMART criteria, and providing data-driven wellness insights.
Expert-thinking profile for Health Informatician (clinical / research): Reasons from semantic interoperability, provenance, and patient…
When the user wants to design, weight, calibrate, backtest, audit, or fix a customer health score.