Machine learning

Manage secrets (write, list keys, delete).

Feature construction from market data for ML trading models including price, volume, on-chain, and microstructure features

Compress an agent's routing file (RESOLVER.md or AGENTS.md) by converting granular skill-per-row tables into functional-area dispatchers.

Unified Minions skill for both deterministic shell jobs and LLM subagent orchestration.

Review a proposed Agent Skill for structural validity and content quality before publishing.

Test RAG vector stores (Pinecone, Qdrant, Weaviate, Chroma, pgvector, FAISS) for embedding inversion, cross-tenant data leakage, and data poisoning per OWASP…

Wires Promptfoo and DeepTeam into CI/CD for automated, repeatable red-teaming of LLM apps against OWASP LLM Top 10, OWASP Agentic, and MITRE ATLAS presets…

Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary…

Detects prompt injection using regex signature matching, heuristic scoring for structural anomalies, and DeBERTa-based transformer classification, flagging…

Deploys anomaly detection for OT/ICS environments using machine learning on OT network baselines, physics-based process models, and Modbus/DNP3/OPC UA traffic…

Identify poisoned training data and backdoored ML models across the pipeline using IBM's Adversarial Robustness Toolbox (activation clustering, spectral…

Detect AI-generated deepfake audio used in voice phishing (vishing) by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing…

Detect anomalies in DNP3 communications used in SCADA/ICS systems by monitoring unauthorized control commands, firmware update attempts, protocol violations…

Detect data exfiltration via DNS tunneling (tools like iodine, dnscat2, dns2tcp) by analyzing query entropy, subdomain length, query volume to single domains…

Detect and defend against indirect prompt injection hidden in web pages, documents, and images consumed by an agent, via content extraction (HTML/PDF/OCR)…

Detect MITRE ATLAS AML.T0024 attacks (model stealing, inversion, membership inference) performed via inference-API abuse, by monitoring per-principal query…

Structured daily/weekly briefs, tag digests, and check-ins from the PM wiki.

Guide for instrumenting and operating observable software systems.

Use when designing or implementing an evaluation loop for AI agent outputs — reflection loops, evaluator-optimizer pipelines, LLM-as-judge scoring, or…

Use when configuring AgentClash LLM-as-judge scoring, judge prompts, rubrics, assertion/reference/n-wise modes, evidence inputs, scorecard dimensions…

Use when interpreting AgentClash rankings, scorecards, replay timelines, artifacts, LLM judge results, or failure-review evidence into source-backed findings…

Validates the deterministic SafetyGateEngine and fail-closed routing invariants.

Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

Extract edge hints from daily market observations and news reactions, with optional LLM ideation, and output canonical hints.yaml for downstream concept…