AI & ML

Design habit-forming product loops using the Hook Model (Trigger, Action, Variable Reward, Investment) to analyze and improve user engagement, retention, and re-engagement strategies.

Model software around the business domain using bounded contexts, aggregates, and ubiquitous language, with scoring and diagnostic tools for evaluating domain model quality.

Apply foundational design principles—affordances, signifiers, constraints, mappings, and feedback—to evaluate and improve product usability, bridging the gulfs of execution and evaluation.

Score and rank options contracts for any ticker using a multi-factor model covering liquidity, IV attractiveness, Greeks balance, and risk/reward. Returns scored option chains with the best contracts highlighted.

Search real-time news with bias scoring, get live stock/ETF/crypto data with AI analysis, ML options pricing, balanced news synthesis, and meme search via the Helium MCP server.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Build, validate, and troubleshoot deep links for Codex, Cursor, VS Code, Visual Studio, and similar tools. Use when users ask for clickable links (especially in Slack) that open threads, files, folders, or app settings.

Coordinate large-scale codebase migrations and multi-file refactors across hundreds of files using batched PRs and CI verification.

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

Creates a new recurring workstream (loop) in a file-based knowledge base: scaffolds the domain folder, runs a real test cycle, and records the result in the timeline and log.

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking, creates orchestration DAGs, builds feature store schemas, deploys model registries, and automates retraining and validation workflows.

Integrates with Atlassian products to manage project tracking and documentation via MCP protocol. Use for querying Jira issues with JQL filters, creating and updating tickets, searching Confluence pages, managing sprints, and setting up MCP server authentication.

Build, debug, and extend MCP servers and clients that connect AI systems with external tools and data sources.

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality.

Fine-tune LLMs using LoRA, QLoRA, and PEFT with Hugging Face, including dataset preparation, hyperparameter tuning, evaluation, and deployment.

Add a batteries-included agent component to React/Next.js apps with runtime, streaming, human-in-the-loop approvals, and client-side tools.

Build AI applications with the inference.sh Python SDK: run apps, build agents, and integrate with 250+ models using sync/async, streaming, file uploads, and a tool builder API.

Run 250+ AI apps from the command line: generate images and videos, call LLMs, search the web, create 3D models, and automate Twitter posts.

Run 250+ AI apps from the command line: generate images and videos, call LLMs, search the web, create 3D models, and automate Twitter posts.

Generate images using Pruna's optimized P-Image models via the inference.sh CLI, supporting text-to-image, LoRA styles, image editing, and multi-image compositing.

Generate videos using Pruna's optimized P-Video and WAN models via the inference.sh CLI, supporting text-to-video, image-to-video, audio input, and multiple resolutions.

Access 100+ LLMs including Claude, Gemini, Kimi, and GLM via the inference.sh CLI with automatic fallback and cost optimization.

Search the web and extract content from URLs using Tavily and Exa APIs via the inference.sh CLI.

Generate and edit images using OpenAI's GPT-Image-2 model via the inference.sh CLI, supporting text-to-image, image editing, inpainting, and batch generation.

Generate images using FLUX models via the inference.sh CLI, supporting text-to-image, image-to-image, and LoRA fine-tuning.

Generate videos using Google Veo models via the inference.sh CLI, with support for multiple Veo versions and cinematic prompts.

Generate and edit videos using Alibaba HappyHorse 1.0 models via the inference.sh CLI, supporting text-to-video, image-to-video, reference-to-video, and video editing with natural language.

Generate and edit images using Alibaba Qwen-Image-2.0 models via the inference.sh CLI, with support for text-to-image, multi-image editing, and text rendering.

Generate multi-person talking head podcast videos from scratch using AI — character creation, TTS, avatar animation, and video stitching.

Generate images using Google Gemini 3.1 Flash Image Preview via the inference.sh CLI, with support for text-to-image, image editing, multi-image input, and Google Search grounding.

Build RAG pipelines that combine web search and LLMs for research, fact-checking, and grounded responses using the inference.sh CLI.

Create realistic multi-speaker dialogue audio using Dia TTS via the inference.sh CLI, with control over speaker tags, emotion, pacing, and conversation structure.

Transcribe audio with high accuracy using ElevenLabs Scribe models, supporting speaker diarization, audio event tagging, forced alignment, and subtitle generation via the inference.sh CLI.

Generate high-quality speech from text using ElevenLabs' premium voices, with support for 32 languages, multiple models, and voice tuning parameters.

Transcribe audio to text using ElevenLabs Scribe and Whisper models via the inference.sh CLI, supporting timestamps, speaker diarization, translation, and multi-language transcription.