Reproduce diagnose and verify defect fixes

As of 2026-10-09, AI does this work at L2 Partial automation. 5 updates bear on it. Strongest evidence: From the publisher only.

L0ManualL1AssistedL2Partial automationL3Conditional automationL4High automationL5Full automation

What moved it

Every update that bears on this work, newest first.

2026-10-01Meta
Meta releases Immersive Web SDK version 1.0
Meta releases Immersive Web SDK version 1.0, enabling agents to play, profile, and fix apps on device until frame rate targets are met.
L2 Partial automationClaimed L3 · Accepted L2From the publisher onlySource ↗
2026-09-27Microsoft
GitHub Copilot app supports running agents in parallel
GitHub Copilot app allows running agents in parallel, with each session getting its own Git worktree and context for simultaneous building, reviewing, and testing.
L1 AssistedFrom the publisher onlySource ↗
2026-09-15OpenAI
Cognition's Devin uses GPT-6 Astra for test generation
OpenAI Devs states that GPT-6 Astra helps Cognition's Devin back up 'it works' with tests before the team ships.
L2 Partial automationFrom the publisher onlySource ↗
2026-09-14OpenAI
Perplexity engineer uses GPT-6 Astra in Codex for end-to-end testing
An engineer at Perplexity reports using GPT-6 Astra in Codex to build test harnesses and mock third-party API responses for end-to-end testing.
L2 Partial automationFrom the publisher onlySource ↗
2026-09-09OpenAI
OpenAI shares cyber defense architecture and playbook
OpenAI describes mobilizing 250+ people to strengthen defenses across hundreds of systems, with cyber models finding and fixing vulnerabilities, and shares the architecture and a practical playbook.
L1 AssistedFrom the publisher onlySource ↗