Dynamic workflows are in public preview across Copilot CLI, the Copilot app, and the SDK: you write (or ask Copilot to write) a coded orchestration that sequences and parallelizes agent steps, checkpoints, and tool calls—unlike /fleet’s free-form delegation. Enable with --experimental or /experimental on in CLI; all Copilot plans.
At Select, Supabase made schema and config repo native with pg delta migrations, Docker free local stacks (alpha), and long running Compute services beside the DB. Apps can also ship an authenticated Edge Function MCP ( npx shadcn@latest add @supabase/mcp server ) so user agents act under RLS as the signed in user…
Ace Data Cloud’s Flux MCP ( https://flux.mcp.acedata.cloud/mcp ) adds flux generate image and flux edit image so Claude Code can draft with Flux Dev, refine with Pro, and patch existing images with Kontext without leaving the terminal. Add it via claude mcp add flux transport http with an Ace Data Cloud API token; verify with claude mcp list…
Anthropic opened Claude Security (public beta, Enterprise) at claude.ai/security: Opus 4.7 scans connected GitHub repos for vulns with confidence/severity and proposed patches you can open in Claude Code on the Web. Admins get scheduled scans, CSV/Markdown export, and Slack/Jira webhooks; Team/Max access is coming later…
As of Oct 2, GitHub Copilot dropped Gemini 3.5 Flash, Gemini 3.6 Flash, Kimi K2.7 Code, and Claude Opus 4.7 across chat, edits, agent mode, and completions—switch to Gemini 3.8 Flash, Kimi K3, or Claude Opus 5.5. Copilot Enterprise admins may need to enable the replacements in model policies…
You can now request a Copilot code review via REST and GraphQL (with an optional per request effort level) on Pro through Enterprise plans, so scripts and internal tools can kick off reviews without the UI. Balanced is the new default effort for Default settings as of Sept 28; explicit Lite picks still stick…
Spotted something we missed? Start a thread.
