Perception Agents Workshop

AI-Native Workshop is a repository-based workshop for practicing AI-native software development workflows. Its curriculum covers voice coding, agent sessions, loops and measurable goals, Git worktrees, verification gates and hooks, adversarial review, and scheduled tasks. The repository includes setup skills, exercises, slides, a glossary, a facilitator guide, and an optional local `aie-coach` MCP server with seven tools for check-ins and setup scoring. Its setup workflow runs inside Claude Code and can install and verify Bun, the Codex CLI, and Git; the workshop is organized in four blocks covering voice, loops and goals, gates, and schedules.

The Mastering AI Observability Workshop repository is a hands-on workshop resource for building a trace-backed support-agent improvement workflow with Braintrust. It provides a local Python workshop app, setup instructions, a support agent using tool calls, seeded evaluation cases, production-like trace generation, Braintrust datasets and evaluations, hosted scorers, Topics facets, sample-trace imports, and optional draft evaluation cases derived from traces. The workflow connects tracing and online analysis to offline evaluations, custom scoring, failure investigation, regression cases, and reviewable code changes. The repository includes a public WORKSHOP.md guide, environment setup through uv and Make commands, local database seeding, a web interface, and configuration for Braintrust Gateway model calls.

AutoBrowse is an open-source browser-skill training demo from the AI Engineers workshop. It pairs a frozen doer agent, which operates a browser through the browse CLI and records a trace, with a teacher agent that studies the trace, forms a hypothesis, edits strategy.md, and judges the next attempt. Repeated iterations hill-climb the strategy for a specified website and task; a final graduation run converts the strategy into a reusable SKILL.md that can be installed for Claude Code or Codex. The repository includes a local live UI, headless forge and demo commands, streamed run events, and per-run artifacts under ./workspace. It uses Browserbase for browser sessions and Anthropic models by default, and the README identifies the vendored evaluate.mjs doer as MIT-licensed.

Multi-Agent Workbench is a local-first browser control room for orchestrating coding agents such as Claude Code, Codex CLI, and generic PTY-based command-line agents. Agents work in task rooms under editable YAML role cards that define permissions, speaking style, and decision boundaries; a rule-driven orchestrator pauses execution and risky commands for human approval, while persistent sessions expose terminal activity and status. The system uses a local event-driven architecture with a React interface, Fastify backend, REST API, server-sent events, agent adapters, an approval service, and a SQLite event store. Every action passes through the API and is recorded in an append-only event log, whose events are projected into timelines, decisions, terminal views, artifacts, and diff views. It also provides task templates, Markdown reports and decision logs, real-time room updates, and configurable risk resolutions. Code-writing agents are intended to use isolated Git worktrees, with diff and patch review before changes reach the main workspace; the repository marks this worktree and merge flow as in progress.

Agent Context Workshop is a hands-on workshop resource for building and evaluating context layers for coding agents. It uses selected crates from the Qdrant Rust codebase to extract syntax with tree-sitter, resolve symbols and relationships with rustdoc JSON, store the resulting code knowledge graph in Neo4j, and expose graph tools such as search, blast-radius analysis, and implementor lookup to an agent. The workshop compares graph-based agents with grep-style agents using gold-verified questions, deterministic scoring, cached evaluation results, tool-adoption measurements, and trace inspection. Additional notebooks cover static Python resolution with Griffe and an optional Fenic-and-LLM semantic layer. The GitHub repository maintains the workshop through ordered Jupyter notebooks, typed extraction and graph code, evaluation harnesses, tests, committed Qdrant seed data, and a committed evaluation cache; it is licensed under Apache-2.0.