Asana has successfully utilized OpenAI Codex to replace its outdated testing system, a task initially estimated to take five years. The project was completed in just two weeks, costing approximately $12,000. This remarkable acceleration showcases the potential of AI to drastically reduce development timelines and costs. Asana's experience highlights the transformative impact AI can have on engineering processes, suggesting a new paradigm for tackling extensive technical projects.
Read originalEarlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
TechCrunch AI · May 28, 2026 · Related
OpenAI · June 2, 2026 · Related
TechCrunch AI · June 2, 2026 · Related
The Verge AI · June 29, 2026 · Related
The Verge AI · July 15, 2026 · Related
OpenAI · July 16, 2026 · Related
The Rundown AI · July 16, 2026 · Background
The Rundown AI · August 3, 2026 · Background
Lev Selector · September 11, 2026 · Background
Wes Roth · October 7, 2026 · Background
Matt Wolfe · October 9, 2026 · Background
This release tightens the leash on Claude Code's autonomous capabilities while fixing critical sandbox escapes. The new effort parameter for Agent tools lets developers explicitly control sub-agent depth, a necessary guardrail as these systems grow more complex. Security fixes are prominent, addressing how plugins handle network paths and how file permissions persist during session resumption. It’s a stability patch that ensures the tool remains usable in enterprise environments without compromising on the new agent features.
Anthropic quietly shipped a significant model update alongside routine maintenance. Claude Haiku 5.5 is now the default on the API, offering a 1M context window at $0.10 per million tokens, which lowers the cost floor for high-volume coding tasks. The release also patches critical stability issues in the local agent runtime, specifically fixing memory leaks in HTTP MCP connections and resolving session state corruption during context compaction. These fixes matter because they stabilize the autonomous coding workflow that developers rely on daily. With Haiku 5.5 now standard, teams can deploy cheaper, faster iterations without manual configuration.
Anthropic quietly patched a frustrating edge case in Claude Code’s agent hooks. Previously, instructions like 'Block commands that...' were often ignored because the model didn't recognize them as valid blocking criteria. This update ensures those prompts are properly interpreted, while also refining how stop conditions are judged to prevent premature termination. It’s a small but necessary fix for anyone relying on strict guardrails in automated coding workflows.