Phase 0: Long-Horizon Autonomy · ~45 minutes · Python (stdlib · CodeAct vs JSON tool-call comparison)

The Autonomous Coding Agent Landscape (2026)

SWE-bench Verified went from 4% to 80.9% in under three years.

Hiring signal: Can operate the autonomous coding agent landscape (2026) in production

Introduction

Same Claude Sonnet 4.5 scored 43.2% on SWE-agent v1 and 59.8% on Cline autonomous — the scaffolding around the model now matters as much as the model itself. OpenHands (formerly OpenDevin) is the most active MIT-licensed platform and its CodeAct loop executes Python actions directly in a sandbox instead of JSON tool calls. The headline numbers hide a methodological issue: 161 of 500 SWE-bench Verified tasks require only a 1–2 line change, and SWE-bench Pro (10+ line tasks) sits at 23–59% for the same frontier models.

Type: Learn Languages: Python (stdlib, CodeAct vs JSON tool-call comparison) Prerequisites: Phase 14 · 07 (Tool use), Phase 15 · 01 (Long-horizon agents) Time: ~45 minutes

Objective

Learning objectives

Unlock the full lesson

You've read the first 2 sections. The rest of this lesson covers The Problem, The Concept, Build, Check Yourself, Key Terms & Next — plus a hands-on lab, quiz, and project artifact.

Create a free account to unlock Phase 0 and Phase 1 of every course — no credit card.

Key terms in this lesson

Agent