Trusting AI with Your Data: Safe Automation from Branch to Production

Managing Changes from Multiple AI Agents

In this video, I walk you through managing changes from multiple AI agents in our to-do app, specifically focusing on the Expert to CSV button. We explore design options using ground agents, where one agent proposes a green design and the other a blue one. After some time, both agents complete their tasks, and their changes are synchronized to GitHub and our local machine. I demonstrate the final designs and decide to ship the green version as the main one. I encourage you to apply this approach in your own projects and consider using rebase in GitHub for similar tasks.

Git AI - Track AI Code all the way to production

Cross-agent observability from prompt to production. Track AI-generated code from Cursor, Claude Code, GitHub Copilot, Gemini, and more through the entire SDLC.

weave — Merge without conflicts

Entity-level semantic merge driver for Git. Two agents edit different functions in the same file? Clean merge. Every time.

The Last Human-Written Paper: Agent-Native Research Artifacts

Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, reproduce, and extend published work. We introduce the Agent-Native Research Artifact (ARA), a protocol that replaces the narrative paper with a machine-executable research package structured around four layers: scientific logic, executable code with full specifications, an exploration graph that preserves the failures compilation discards, and evidence grounding every claim in raw outputs. Three mechanisms support the ecosystem: a Live Research Manager that captures decisions and dead ends during ordinary development; an ARA Compiler that translates legacy PDFs and repos into ARAs; and an ARA-native review system that automates objective checks so human reviewers can focus on significance, novelty, and taste. On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities.

Agents Done Right: A Framework Vision for 2026

Agents choke on context, loop on failures, and dump walls of code for review. It's time to rethink the architecture.

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.

GitHub - Responsible-Dataset-Sharing/easy-dataset-share: A CLI tool that helps AI researchers share datasets responsibly.

A CLI tool that helps AI researchers share datasets responsibly. - Responsible-Dataset-Sharing/easy-dataset-share

New data agents across the Agentic Data Cloud | Google Cloud Blog

Learn about new data agents and tools for business analysts, data scientists, and database admins to integrate with the Agentic Data Cloud.

Lean Data Automation: A Principal Components Approach

Plus: A nimble, composable example with Github Actions, Hamilton, and Runhouse

Rebuilding Cognition's Agentic MapReduce

How do you run large-scale agent tasks across a codebase?

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

TERMINAL-BENCH-SCIENCE

A benchmark for evaluating AI agents on research workflows across scientific domains