Machine learning

Build AI features with Vercel AI SDK (chat, agents, RAG, tools).

Catalogs reusable Artifact components and supplies the exact scripts, styles, tokens, markup contract, and composition limits for embedding interactive…

Complete autotel API reference: trace(), span(), instrument(), getRequestLogger(), createStructuredError(), parseError(), track(), init().

trace(), span(), instrument(), init().

Prepare, verify, and resume operator-owned Hugging Face or NVIDIA NGC access for exact NPA dependencies, including human-bound upstream approvals, while…

Package, preflight, run, validate, or troubleshoot NVIDIA Alpamayo 2 Super 34B VLA inference in NPA, including its OpenMDW model terms, separately gated…

Design and build reactive, type-safe, production-grade backends on Convex.

Preparar um corpus local rastreável e abrir o chat especialista por meio dos módulos e da CLI do projeto.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Survey one surface of tdmcp (artist controls, library/packaging, CLI/DX, AI/LLM, or TouchDesigner depth) for candidate NEW features — inventory what exists…

Survey the whole tdmcp project and produce a prioritized list of NEW features it could implement — across artist controls, CLI/DX, AI/LLM integration, and…

Calibrate historical or uncertain investigation findings, distinguish evidence from inference, and report source coverage and gaps.

Define and verify deterministic format-conditional adapter routing at inference.

Portable OKF knowledge bundle for coding-agent memory and LLM wikis.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Add an AI agent / RAG backend (@convex-dev/agent) to the Convex app.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Operate Codex as a high-autonomy repository executor for implementation, debugging, and long-running research loops.

Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart".

Build a paper sheet in Three.js that reads as paper up close — washi, cotton rag or kraft with baked fibre and tooth relief, laid and chain lines, a torn…

Use when adding, configuring, verifying or repairing Laya decision inference through Nerve on a repository's Docker Hermes instance; not for Layui, replacing…

Run a stateful red team / blue team security audit on the current project or a specific module.

Orchestrates the recurring daily-maintenance loop for the PM wiki — registry-driven multi-source sweep, ingest, daily brief, brief rotation, and a health…

Research sprints, competitive deep dives, and auto-enrichment of stub wiki pages.