AI & ML

Auto-routes Claude Code subtasks to the cheapest capable model (Haiku/Sonnet/Opus), logs token costs, and A/B tests tiers to validate savings against real workloads.

Guides building production-grade AI features with LLM integration patterns, RAG architecture, prompt engineering, and cost optimization.

Augments nearest-neighbour search with graph Laplacian features to retrieve items based on both semantic similarity and structural role.

Build LLM-powered applications using the Claude API, Anthropic SDKs, or the Agent SDK with language-specific guidance and best practices.

Decides whether a personalized gift should be created each day, then generates it as an interactive H5 page, AI image, or AI video through a five-stage creative pipeline.

Build evaluation frameworks for agent systems, covering rubric design, test set creation, and automated evaluation pipelines.

Configure and optimize .faf files, MCP servers, and bi-directional sync for AI context across multiple platforms, with championship scoring to achieve 85%+ AI-readiness.

Search and analyze news articles with media bias context, get balanced perspectives, access live stock/ETF/crypto data with AI analysis, and find memes by semantic meaning.

Simulates Yann LeCun, inventor of CNNs and Chief AI Scientist at Meta, for conversations about AI, deep learning, and related topics.

Discover, audit, repair, adapt, and design bounded, verifiable AI-agent loops with explicit triggers, actions, stopping conditions, and guardrails.

Build, deploy, evaluate, debug, and measure latency for a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection and VLM classification.

Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API.

Builds and validates DeepStream GStreamer pipelines through an interactive questionnaire and a BM25 retrieval engine over 270+ verified pipelines.

Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores like S3, GCS, Azure, HTTP, or HuggingFace.

Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).

Maps a described workflow to the right ECC command-group with run-order and stop condition, and browses all command-group recipe families.

Designs and reviews feedback loops for AI agents to ensure goals are machine-decidable, loops are damped, and human judgment is preserved.

Orchestrate dynamic multi-agent workflows with parallel agents and adversarial verification via a local daemon, or fall back to native agent orchestration.

Discover, compare, audit, repair, adapt, craft, run, debrief, and publish repeatable AI-agent loops for engineering workflows.

Search models, datasets, Spaces, and papers on Hugging Face Hub, retrieve repository details and documentation, run compute jobs, and use Gradio Spaces as AI tools via MCP server tools.

Estimates GPU memory required to load Safetensors or GGUF model weights for inference from the Hugging Face Hub using HTTP Range requests, without downloading weights locally.

Delegate tasks to OpenAI Codex CLI and Google Antigravity CLI from Claude Code with topic-aware sessions.

Build AI agents on Cloudflare Workers using the Agents SDK, covering stateful agents, durable workflows, real-time WebSocket apps, scheduled tasks, MCP servers, chat applications, voice agents, and browser automation.

Send and receive transactional emails using Cloudflare Email Service, including Workers binding, REST API, Agents SDK integration, and email routing with deliverability setup.

Generate spoken audio for narration, voiceovers, IVR prompts, and accessibility reads using the OpenAI Audio API with bundled CLI and built-in voices.

Transcribe audio files to text with optional speaker diarization and known-speaker hints using OpenAI models.

Provides authoritative, current guidance from OpenAI developer docs using the developers.openai.com MCP server, including model selection, API migration, and prompt-upgrade guidance.

Scaffold, build, and refactor ChatGPT Apps SDK projects with a docs-first workflow, combining MCP servers and widget UIs.

Migrate Claude Code configuration, skills, agents, and MCP servers to Codex project and global files.

Finds the open GitHub PR for the current branch and helps address review comments using the gh CLI.

Performs repository-grounded threat modeling by enumerating trust boundaries, assets, attacker capabilities, abuse paths, and mitigations, then writes a concise Markdown threat model.

Scaffolds new agent skills conforming to the Agent Skills specification and dotnet/skills repository conventions, generating SKILL.md files with proper frontmatter and directory structures.

Scaffolds eval.yaml test files for agent skills in the dotnet/skills repository, including scenario writing, assertion definition, and rubric creation.

Scaffolds VS Code custom agent files (.agent.md) with YAML frontmatter, tool configuration, handoffs, and instructions for specialized AI personas.

Grades individual test methods and produces a compact markdown table with a letter grade, score band, and one-line note for each test.

Test C# MCP servers at unit and integration levels using xUnit, Moq, and the MCP client SDK.