A REE run produces two outputs: the generated text and a receipt. The receipt binds the job inputs to the job output, including the model, prompt, configuration, and generated result.
Reproducible Execution Environment (REE) | Tech | Gensyn
Run AI model inference in a machine-agnostic environment where the same model and inputs produce the same outputs across supported hardware.
Production Is a Compiler Input - The Phoenix Architecture
Unrolling the Codex agent loop
A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.
shepherd-agents/shepherd
A runtime substrate that turns an agent's execution into a reversible, Git-like trace, so meta-agents can observe, fork, replay, and revert any run. Couples agent and environments in a copy-on-write fork ~5x faster than docker commit, with ~95% KV-cache reuse on replay. Framework built for meta-agents to supervise, optimize, and train other agents
The Agent Harness
A specification for agent behavior that LLM frameworks leave undefined: error handling, context management, tool execution, and state transitions.
The AI Operating System: Stateful Agents with Letta | Cameron Pfiffer, AI By the Bay25
Inngest - Durable Execution for Workflows & AI
Build reliable background jobs, workflows, and AI agents without extra infrastructure. Automatic retries, flow control, and step-level observability.
Regenerative Software - The Phoenix Architecture
Evaluations Are the Real Codebase - The Phoenix Architecture
Why behavior outlives implementations
Signals: Toward a Self-Improving Agent | Factory.ai
Traditional product analytics tell you what happened. Session duration, tool calls executed, completion rates. But they...
Reproducibility in Machine Learning-based Research: Overview, Barriers and Drivers
The concept of reproducibility can have different interpretations across various research fields and even within the same field [39]. To avoid confusion, we first specify our terms, broadly defining reproducibility and then further categorizing it into various types and degrees. The first distinction comes from Goodman et al. [42], who specify a fundamental division between whether we (i) mean reproducible in principle (termed “methods” reproducibility) due to sufficient description/sharing of methodologies, materials, etc., or (ii) whether results/conclusions actually prove to be reproducible when experiments or analyses are re-done. In the second category, they distinguish “results” and “inferential” reproducibility, depending on whether the analyses or inferences to broader conclusions are reproduced.
Structured Outputs with Will Kurt and Cameron Pfiffer - Weaviate Podcast #119!
quint-co/quint
An executable specification language with delightful tooling based on the temporal logic of actions (TLA)
Replit — Model Context Protocol (MCP): A Comprehensive Guide
Learn how Replit's Model Context Protocol (MCP) lets AI models access tools and data seamlessly using a simple, universal interface.
Model Context Protocol - MLOps Community
The MLOps Community fills the swiftly growing need to share real-world Machine Learning Operations best practices from engineers in the field.
