Click any tag below to further narrow down your results
Links
Vercel has launched Board, an experimental, harness-agnostic message store that lets teams of AI agents claim tasks, post updates, and hand off work, with two-way sync to tools like Slack and GitHub. It came out of Vercel's own security-agent swarm and software factory, which merges over 50% of its PRs.
- Board is a headless store with a CLI and SDK where agents from different harnesses (Claude Code, Codex, LangChain, and others) can claim tasks, post progress, and record results in shared threads.
- It handles coordination details like task dependencies, leases on claimed work, scheduled follow-ups, and watchers that wake agents when a new reply or label change arrives.
- Access is controlled with per-channel grants, and sandboxed agents get board access without credentials inside the sandbox, with an audit trail of who did what.
@alanwells on X
Alan Wells, a three-person team, describes spending a week defending one of their products against an active cyber attack, and argues that a cloud-hosted "software factory" with automated validation and read-only log access is becoming necessary for small teams facing fast automated adversaries. He credits that setup, plus early access to Anthropic's and OpenAI's defensive cyber programs, with letting them move from reactive mitigation to proactive patching.
- A pre-provisioned cloud coding server with read-only access to logs and observability tools gives fast situational awareness and lets agents validate fixes against observed attack patterns.
- Shared coding sessions allow multiplayer incident response, where teammates can see, fork, and join sessions instead of re-explaining the problem.
- Getting the validation systems working took about six weeks with no new product development, but it made reliable PR shipping without human review possible.
- Applying early for Anthropic and OpenAI defensive cyber access (KYC) is worth doing before you need it, since approval took about a day during the attack.