Conductor now bundles plan mode, fast mode, skills, repo quick start, and an experimental merge-conflict UI around Codex sessions. Try it if you want a higher-level harness for long-running code agents, but watch the foreground chat UX on larger tasks.
/office-hours automatically.Conductor's announcement bundles three workflow controls around Codex: plan mode, fast mode, and skills. The screenshot shows these as explicit session-level options next to the model picker, with separate toggles for speed and planning depth rather than a single opaque agent setting.
A second change landed under Settings → Experimental: the settings post describes "Merge conflict resolution" that pushes conflicted files to the top of the git panel and adds a dedicated conflict-resolution UI with accept buttons inside the diff view. That matters for long-running coding sessions because conflict handling is now pulled into the same interface instead of bouncing developers back to manual git resolution.
The quick start post frames Conductor less as a thin chat wrapper and more as a repo harness for agent-driven work. Its new flow will "setup gstack, install skills," then "create a new repo" and "kick off /office-hours," collapsing several bootstrapping steps into one entry point. The attached bootstrap walkthrough shows the sequence executing end to end from the terminal.
That higher-level automation is the practical throughline across this release: Conductor is adding opinionated scaffolding around Codex sessions, not just more model knobs. The tradeoff, based on practitioner feedback, is that the UX still lags on foreground responsiveness; Husain says it is "still not quite as nice of a UX as Claw" because the agent often stays silent until a task finishes, which becomes more noticeable on larger coding jobs.
Claude can now drive macOS apps, browser tabs, the keyboard, and the mouse from Claude Cowork and Claude Code, with permission prompts when it needs direct screen access. That makes legacy desktop workflows automatable, and Anthropic is pairing the push with more background-task support for longer agent loops.
releaseOpenClaw shipped version 2026.3.22 with ClawHub, OpenShell plus SSH sandboxes, side-question flows, and more search and model options, then followed with a 2026.3.23 patch. Teams get a broader plugin surface, but should patch quickly and review plugin trust boundaries as the ecosystem grows.
releaseCursor shipped Instant Grep, a local regex index built from n-grams, inverted indexes, and Bloom filters that drops large-repo searches from seconds to milliseconds. Faster candidate retrieval shortens the coding-agent loop, especially when ripgrep-style scans become the bottleneck.
breakingChatGPT now saves uploaded and generated files into an account-level Library that can be reused across conversations from the web sidebar or recent-files picker. It removes repetitive re-uploading and makes past PDFs, spreadsheets, and images part of a persistent working context.
breakingEpoch AI says GPT-5.4 Pro elicited a publishable solution to one 2019 conjecture in its FrontierMath Open Problems set, with a formal writeup planned. Treat it as an early milestone worth reproducing, not blanket evidence that frontier models can already automate math research.
You can now quick start a repo with gstack initialized! Conductor will automatically: - setup gstack, install skills - create a new repo - kick off /office-hours
Codex in Conductor now has plan mode, fast mode, and skills!
live now! Settings → Experimental to try it out
claude implement this now, ultrathink
