Marketplace

Harden APIs against attacks: input validation, output encoding, rate limiting, CORS, CSP, and injection prevention.

Design zero trust network architectures: identity-based perimeters, microsegmentation, and continuous verification.

Use to adversarially test an LLM app, agent, or tool pipeline for prompt-injection/jailbreak weakness and produce a scored hardening report.

Invoke to audit or tighten an AI agent's tool/MCP permissions: diff granted access against observed usage and recommend a least-privilege allowlist.

Design disaster recovery strategies: RTO/RPO targets, backup automation, failover procedures, and DR testing.

Deploy and manage DigitalOcean infrastructure: Droplets, App Platform, Kubernetes, managed databases, spaces, and networking via doctl CLI.

Design effective chatbot conversations: intent mapping, escalation flows, personality design, and fallback strategies.

Scan and harden container images: base image vulnerabilities, runtime permissions, distroless patterns, and admission policies.

Invoke when an AI system touches the EU market and you must classify its EU AI Act risk tier and output the obligations and article citations that follow.

Use when adding, upgrading, or auditing third-party packages: judge vulnerabilities, maintenance health, and supply-chain risk before they ship.

Audit application configuration: environment variables, secrets management, config validation, and environment parity.

Optimize how context is assembled for LLM calls: system prompt design, few-shot example selection, context pruning, and token budget management.

Use when a repo's test suite is red and you must drive it to green by patching the code under test within a budget, without masking regressions.

Audit code for race conditions, deadlocks, and thread safety issues in async and multi-threaded code.

Design conversational analytics interfaces: NL-to-SQL, query disambiguation, result narration, and data storytelling.

Deploy and manage Azure infrastructure: VMs, AKS, App Service, databases, storage, networking, and Entra ID via az-cli with safety checks.

Design ML experiment tracking: hyperparameter logging, model versioning, reproducibility, and experiment comparison workflows.

Design and implement ML feature stores: online/offline serving, feature freshness, training-serving skew prevention, and feature discovery.

Design secure authentication flows: OAuth2, OIDC, session management, token rotation, and multi-factor authentication patterns.

Plan ML model deployment: serving patterns, A/B testing, canary releases, monitoring, and rollback for production ML.

Build comprehensive model evaluation: benchmark selection, statistical significance, human evaluation protocols, and safety testing.

Design multi-region active-active and active-passive architectures: data replication, failover, DNS routing, and consistency.

Design comprehensive observability: metrics, logs, traces, and profiles with SLO-driven alerting and dashboard design.

Use when auditing an LLM answer that carries source citations, to verify each claim is entailed by its cited sources and flag unsupported or misattributed ones.