AI research and projects
The research, projects, and explanations behind the people. Read the source, inspect verified code and models, and find a collaborator.
A source check confirms that a source supports the summary. It is not an independent replication or endorsement. Our methodology ↗
Vapi.ai: Autonomous Multi-Step Workflow Engine & Error Recovery
Mat Mathews · Vapi.aiA verified production automation architecture implemented by Mat Mathews at Vapi.ai, orchestrating multi-agent state machines, deterministic validation gates, and human-in-the-loop review queues.
Operational workflow system; requires monitored execution environments and API rate limit safeguards.
Context: WebRTC, Deepgram, OpenAI/Groq, Cartesia/ElevenLabs voice pipelines.
View missionAI for Non-Techies: Applied Generative AI Playbook & Workflow Integration
Heather Murray · AI for Non-TechiesA comprehensive educational guide and implementation curriculum created by Heather Murray at AI for Non-Techies, training professionals on advanced prompting, context-window management, and practical generative workflows.
Curriculum and operational methodology; technical adoption requires ongoing practitioner practice and organizational enablement.
Context: Claude, ChatGPT Enterprise, Microsoft Copilot, and internal company guidelines.
View missionRealmIQ: Applied Generative AI Playbook & Workflow Integration
Curt Doty · RealmIQA comprehensive educational guide and implementation curriculum created by Curt Doty at RealmIQ, training professionals on advanced prompting, context-window management, and practical generative workflows.
Curriculum and operational methodology; technical adoption requires ongoing practitioner practice and organizational enablement.
Context: Enterprise creative suites, Midjourney, and multimodal generative tools.
View missionGenerative Interfaces and Dynamic AI Design Systems
Linus Ekenstam · Independent DesignerExploration of intent-driven interfaces where layout, components, and visuals are synthesized in real-time according to user intent and structured token streams.
Requires modern streaming front-end frameworks (Next.js/React Server Components) and fast token generation speeds.
Context: Generative UI, component synthesis, and dynamic design ergonomics.
View missionMistral Open-Source Cookbook: Multi-Modal & Function Calling Implementation Guides
Sophia Yang, Ph.D. · Mistral AIComprehensive open-source repository providing end-to-end notebooks on function calling, structured generation, Pixtral visual document parsing, and local self-hosted deployment.
Cookbook assumes modern GPU or cloud API access; quantized CPU inference requires custom llama.cpp flags.
Context: Mistral Large, Pixtral 12B, Python, Hugging Face, and Ollama.
View missionGoogle AI Studio Developer Architecture & Long-Context Workflows
Logan Kilpatrick · GoogleArchitecture supporting million-token context retrieval, multimodal video/audio parsing, and zero-latency prompt prototyping for enterprise builders.
Cloud-hosted developer interface; throughput governed by API quota tier.
Context: Gemini 1.5 Pro / Flash APIs, function calling, and system instructions.
View missionCommercial Cinematography Simulation with Diffusion Models
Nick St. Pierre · Nick St. Pierre CreativeParameter frameworks detailing optical lens simulation (anamorphic, focal length, aperture) and camera rigging within modern image generation models.
Focuses on commercial aesthetics and visual steering parameters; not algorithmic model training.
Context: Midjourney parameters, sref style references, and diffusion prompt design.
View missionAgentic Design Patterns for LLM Workflow Performance
Dr. Andrew Ng · AI Fund / DeepLearning.AIInfluential technical series establishing the four design patterns of autonomous AI: Reflection, Tool Use, Planning, and Multi-Agent Collaboration.
Conceptual and architectural framework; production deployment requires automated evaluation against task benchmarks.
Context: Autonomous agent loop architecture and multi-agent coordination.
View missionYour AI Product Needs Evals: Comprehensive Guide to Unit Testing & LLM Evaluation
Hamel Husain · Parlance Labs / ex-GitHubComprehensive framework for creating automated evaluation loops, synthetically augmented test sets, and LLM-as-a-judge scoring harnesses that measure production degradation before deployment.
LLM-as-a-judge evaluators can exhibit self-preference bias and positional bias if uncalibrated against human baseline judgments.
Context: Promptfoo, Braintrust, Python, OpenAI, Anthropic, and OpenPipe.
View missionAllie K. Miller Consulting: Applied Generative AI Playbook & Workflow Integration
Allie K. Miller · Allie K. Miller ConsultingA comprehensive educational guide and implementation curriculum created by Allie K. Miller at Allie K. Miller Consulting, training professionals on advanced prompting, context-window management, and practical generative workflows.
Curriculum and operational methodology; technical adoption requires ongoing practitioner practice and organizational enablement.
Context: Enterprise software strategy, change management, and executive alignment.
View missionProduction Open-Source LLM Fine-Tuning & Evaluation Cookbook with TRL and vLLM
Philipp Schmid · Independent / ex-Hugging FaceComprehensive production blueprint demonstrating automated DPO, SFT, and vLLM deployment pipelines with continuous evaluation harnesses on AWS SageMaker and Kubernetes.
Requires careful GPU memory budget tuning when scaling multi-GPU distributed tensor parallelism across heterogenous cluster nodes.
Context: Hugging Face TRL, vLLM, PyTorch, Ray, and AWS SageMaker.
View missionThe Daily Bil: Scalable Model Serving Architecture & Latency Optimization
Bilawal Sidhu · The Daily BilA production infrastructure blueprint developed by Bilawal Sidhu at The Daily Bil, implementing continuous batching, quantized weights, and horizontal autoscaling for high-concurrency model inference.
Deployment specifications are tailored to modern GPU cluster infrastructure; requires containerized execution runtimes.
Context: Gaussian Splatting, NeRF, WebGL, and mobile sensor capture.
View missionLarge Language Models as Regulatory Compliance Agents
John Nay · Norm AiEmpirical legal research translating statutory regulations, securities rules, and marketing compliance guidelines into deterministic agent evaluation engines.
Complex statutory ambiguities require licensed human legal counsel review for final legal liability determination.
Context: Legal knowledge graphs, regulatory text parsing, and compliance agent evaluation.
View missionLangGraph: Controllable Multi-Agent Orchestration Engine
Harrison Chase · LangChainAn open-source cyclic computation engine that enables multi-agent state persistence, human-in-the-loop approval breakpoints, and memory time-travel debugging.
Requires persistent state checkpointing storage (e.g. Postgres or Redis) and custom schema validation for production multi-tenant workloads.
Context: Python and TypeScript graph orchestration over modern LLM APIs.
View missionThe Healthy Scientist: Applied AI Workflow Architecture & Developer Prompting System
Pierre-Henry Soria · Soria / pH-7Architectural guides and curriculum formalizing prompt engineering protocols, agentic workflow automation, and clean full-stack system patterns for AI-assisted software delivery.
Designed for production web and cloud environments; requires structured schema validation and API key rate limit orchestration when integrating foundation model providers.
Context: TypeScript, Node.js, Python, OpenAI API, Claude 3.5 Sonnet, Docker Sandboxing
View missionMeasuring the Carbon and Energy Footprint of Machine Learning Inference
Dr. Sasha Luccioni · Hugging FaceEmpirical evaluation measuring the exact energy consumption and carbon intensity across diverse machine learning tasks and model classes during real-world inference.
Readings vary according to regional grid energy sources and specific data center PUE coefficients.
Context: Energy profiling across 88 multimodal and language model tasks.
View mission