Can AI replace Relay.app?
The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Relay.app, build a small human-in-the-loop workflow across two approved services. The hard boundary is polished approvals, ai steps, integrations, shared workflows, and managed execution, plus connector breadth and execution reliability.
01What it costs
Checked Jul 31, 2026 · source: relay.app.
02Could AI build it for you?
The core job: Connect two approved services, execute a small durable human-in-the-loop workflow, expose retries and logs, and avoid claiming a general integration platform.
What a working version needs:
- OAuth or API credentials for two chosen services
- PostgreSQL
- Redis
- public HTTPS endpoint
- background worker
Editorial comparison targets the Professional plan and a two-service personal automation DIY substitute. Recheck price before merge.
03What you'd give up
- polished approvals, AI steps, integrations, shared workflows, and managed execution
- thousands of connectors
- maintained OAuth applications
- schema-drift handling
- high-scale durable execution and support
People still pay for Relay.app because one automation is easy; maintaining hundreds of connectors and making every run recoverable is the business. The recurring cost buys OAuth review, token refresh, webhooks, polling, schemas, retries, idempotency, queues, secrets, rate limits, observability, and upgrades, not just the visible interface.
04Free and cheaper alternatives
Visual workflows with approval steps and human input, without paying per successful handoff.
activepieces.com →Human approval can sit inside a durable workflow; the interface is less relentlessly friendly.
n8n.io →05The build prompt
Paste this into an AI coding tool (such as Claude, ChatGPT, Lovable or Replit) to build your own version.
Build a personal replacement for Relay.app in an empty repository. Use TypeScript, Node.js 22, PostgreSQL, Redis, BullMQ, and Docker Compose; do not offer alternative stacks. The core loop is: connect two approved services, execute a small durable human-in-the-loop workflow, expose retries and logs, and avoid claiming a general integration platform. Make the first run work locally with one documented command. Store all user data locally by default and make export straightforward. Put secrets in .env, ship .env.example, and never commit credentials. Implement a fixed trigger, transform, condition, and action workflow model rather than a general visual language. Connect exactly two named services using documented APIs and encrypted credentials. Store every run, step input hash, output summary, retry, and final status in PostgreSQL. Make side effects idempotent and support retry from the failed step without repeating completed actions. Add rate limits, backoff, dead-letter handling, manual replay, cancellation, and secret rotation. Ship Docker Compose, health checks, sample workflows, tests, backups, and connector-limit documentation. Include clear empty, loading, success, and recoverable error states. Add input validation, safe filenames, and graceful handling of unavailable APIs. Write focused tests for the core transformation and one end-to-end happy path. Create a README with setup, architecture, permissions, data location, and backup steps. Do not add accounts, billing, telemetry, analytics, or a hosted control plane. Deliberately leave out a broad connector marketplace. Deliberately leave out unreviewed user code execution. Deliberately leave out enterprise governance, guaranteed execution, and vendor-operated OAuth apps. Finish by running the tests and listing the exact commands used.
06Open-source starting points
- Activepieces: Active open-source automation platform with connectors and durable workflow execution.
App prices, verdicts, alternatives and build prompts are adapted from Can I Vibecode It? (MIT License, © 2026 Rob Hallam). Each price shows the date it was checked and its source. Prices change; confirm on the vendor's site before you decide.
Get new verdicts in your inbox.
One short email when new verdicts land: what AI can now do for you, and what it still gets wrong. No spam. Unsubscribe anytime.