# AI coding agents Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/ai-coding-agents
> Markdown URL: https://aitinkerers.org/technologies/ai-coding-agents.md
> Technology record last updated: 2026-03-20T18:36:20Z
> Generated: 2026-09-21T02:44:06Z

Autonomous software engineers that navigate entire codebases to plan, execute, and debug complex features.

AI coding agents like Devin, Cursor, and GitHub Copilot Workspace represent a shift from autocomplete to full-scale task autonomy. These systems use Large Language Models (LLMs) to index local repositories, execute terminal commands, and resolve GitHub issues without constant human intervention. By integrating directly into the IDE or a sandboxed cloud environment, they reduce technical debt and accelerate development cycles by handling boilerplate and refactoring tasks in seconds.

- Official technology site: https://www.cursor.com
- Public AI Tinkerers demos and talks: 3
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Chunk Sidecars: Inner-Loop Validation for AI Coding Agents](https://sf.aitinkerers.org/talks/rsvp_1SFW5CFN7NA)

Rob Zuber of CircleCI demonstrated Chunk sidecars: automatic, fast, deterministic validation for any agent. He showed how agent hooks can trigger fast remote checks before code reaches the outer CI pipeline, preserving context and shortening the fix-and-verify feedback cycle.

- Event context: AI Tinkerers San Francisco: July GTM Engineering Track w/ Attio — 2026-07-09 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_1SFW5CFN7NA

### [Don't Lose the Engineering: Parallel Development with AI Agents, Human Orchestration & a Real Methodology](https://medellin.aitinkerers.org/talks/rsvp_KgLs7C6JZlQ)

We built an internal development methodology and orchestration system where AI agents develop features in parallel — coordinated by human architects — shipping an international-grade SaaS product in 3 months. The demo shows our real workflow: how we structure agent-driven development cycles, how our CTO/CPO + backend architect (Lorgi) + frontend architects (Francisco, Mike) validate and audit every AI-generated output, and how we stripped Scrum down to what actually works — killing the bureaucracy and replacing it with product development iterations focused on real value. I'll walk through our local-first approach where each engineer runs their own AI pipeline before integration, our governance structure, and how we recovered engineering rigor after almost losing it to uncontrolled vibe coding. Live demo on our actual codebase and orchestration tools.

- Event context: AI Tinkerers Medellín #20 - SalesAds - 16 de Abril — 2026-04-16 — Medellín
- Public talk page: https://medellin.aitinkerers.org/talks/rsvp_KgLs7C6JZlQ

### [Encoding Engineering Judgment into AI Coding Agents](https://toronto.aitinkerers.org/talks/rsvp_d8pBUS_N4jA)

LLMs are great at writing code, but they mostly follow patterns they learned from random internet repos. That’s fun until those patterns start leaking into your production codebase. In this talk I’ll demo Mystro, a system that lets you encode your own coding practices and use them to guide an AI coding agent. Instead of hoping the model does the right thing, you can test, evaluate, and retry automatically until it starts following your rules. It's using the same underlying algo (GEPA) as autoresearch from Karparthy that was recently released. Think less vibes, more engineering policy. A quick look at what it might take to actually run coding agents inside real codebases.

- Event context: AI Tinkerers Toronto - March - hosted by Mozilla! — 2026-03-25 — Toronto
- Public talk page: https://toronto.aitinkerers.org/talks/rsvp_d8pBUS_N4jA

## Related Technologies

- [Agent hooks](https://aitinkerers.org/technologies/agent-hooks) ([Markdown](https://aitinkerers.org/technologies/agent-hooks.md)) — 1 public demo
- [Autoresearch](https://aitinkerers.org/technologies/autoresearch) ([Markdown](https://aitinkerers.org/technologies/autoresearch.md)) — 1 public demo
- [CI/CD](https://aitinkerers.org/technologies/ci-cd) ([Markdown](https://aitinkerers.org/technologies/ci-cd.md)) — 7 public demos
- [Claude Code](https://aitinkerers.org/technologies/claude-code) ([Markdown](https://aitinkerers.org/technologies/claude-code.md)) — 214 public demos
- [Code validation](https://aitinkerers.org/technologies/code-validation) ([Markdown](https://aitinkerers.org/technologies/code-validation.md)) — 1 public demo
- [Codex](https://aitinkerers.org/technologies/codex) ([Markdown](https://aitinkerers.org/technologies/codex.md)) — 44 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Deterministic validation](https://aitinkerers.org/technologies/deterministic-validation) ([Markdown](https://aitinkerers.org/technologies/deterministic-validation.md)) — 1 public demo
- [GEPA](https://aitinkerers.org/technologies/gepa) ([Markdown](https://aitinkerers.org/technologies/gepa.md)) — 3 public demos
- [Python](https://aitinkerers.org/technologies/python) ([Markdown](https://aitinkerers.org/technologies/python.md)) — 662 public demos
- [Spec-Driven Development](https://aitinkerers.org/technologies/spec-driven-development) ([Markdown](https://aitinkerers.org/technologies/spec-driven-development.md)) — 2 public demos
- [vibe kanban](https://aitinkerers.org/technologies/vibe-kanban) ([Markdown](https://aitinkerers.org/technologies/vibe-kanban.md)) — 1 public demo