Swamp Club
Swamp (swamp-club.com) approaches automation from the opposite direction of open-ended AI agents: composable, typed behaviors wired together into declarative YAML workflows, with secrets held in vaults and every run auditable and schedulable. The pitch is repeatability; an automation you can read, version, and re-run beats a transcript you can only hope repeats.
We adopted it in Replicator's operations layer, where its definitions are committed to the repository: a standing production-data audit, an orphan-blob audit, and scheduled sweeps that run as swamp workflows on cron triggers.
How We Use It
- Standing data audits and scheduled operational sweeps
- Repeatable multi-step automations with vaulted credentials
- Keeping ops work deterministic and auditable where an agent session would be overkill
AI / LLM
Why this matters: Controversial, misunderstood, and overhyped though they may be, AI and LLMs are transforming industries and society. Used carefully and responsibly, they are still a valuable tool for innovation and progress. We design and deploy LLM-powered features with a focus on safety, performance, and maintainability, leveraging managed model providers and an SDK-first approach for rapid iteration. Preferred defaults: Vercel AI SDK + AI Gateway for multi-model orchestration; Anthropic and OpenAI as primary model providers.