Tag
All content about Workflows, organized for fast scanning.
Recent discussions around workflows highlight the evolving landscape of agent development, emphasizing the balance between structured code and flexible prompting methods. Innovations such as automated modes and routine features are being introduced to enhance coding efficiency and streamline processes. Additionally, significant performance improvements in testing workflows have been reported, indicating a trend towards more effective integration of automation in software development.
A recent piece from The AI Frontier takes a closer look at the growing split between code-heavy agent workflows and free-form Markdown prompting. It argues neither extreme works well in production—and explains why a hybrid “intent + guardrails” approach is gaining traction.
Anthropic’s Boris Cherny shared new workflow tweaks for Claude Opus 4.7 focused on longer, less interruption-prone coding runs. Highlights include auto mode for safer auto-approvals, recaps and focus mode, and verification tools like /go for end-to-end tests.
Shopify Engineering says internal teams have been putting pi-autoresearch to work across everything from daily engineering workflows to testing. The company teases a “300x” result for unit tests, but hasn’t shared what, exactly, improved.
Anthropic has rolled out Claude Code Routines in research preview, letting teams package prompts, repos, and connectors into automations that run on schedules, APIs, or GitHub webhooks. It runs on Claude’s web infrastructure, with plan-based daily limits.