Bardeen

Build me a focused workflow automation and app integrations workflow for the personal core of Bardeen. Requirements:

- Use TypeScript, Node.js 22, PostgreSQL, Redis, BullMQ, and Docker Compose. Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Paid product context: Automate a narrow browser workflow on user-approved pages with visible steps. Build only this DIY scope: Automate a narrow browser workflow on user-approved pages with visible steps, execute it durably, expose retries and logs, and avoid claiming a general integration platform.
- 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.
- Add rate limits, backoff, dead-letter handling, manual replay, cancellation, and secret rotation.
- Use a focused workflow automation and app integrations input, review, and export interface. Required input or access: OAuth or API credentials for two chosen services; Redis. Keep credentials in .env.
- Recovery: Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A retry after a provider timeout must not repeat a completed external action without an explicit reconciliation step.
- Out of scope: browser automation library, integrations, cloud execution, templates, and model orchestration; thousands of connectors. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for Bardeen

## Project scope
Automate a narrow browser workflow on user-approved pages with visible steps, execute it durably, expose retries and logs, and avoid claiming a general integration platform.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Bardeen, automate a narrow browser workflow on user-approved pages with visible steps. The hard boundary is browser automation library, integrations, cloud execution, templates, and model orchestration, plus connector breadth and execution reliability.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- OAuth or API credentials for two chosen services
- PostgreSQL
- Redis
- public HTTPS endpoint
- background worker

## Stack and architecture
- Use TypeScript, Node.js 22, PostgreSQL, Redis, BullMQ, and Docker Compose.
- Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Interface for this workflow automation and app integrations workflow: a focused workflow automation and app integrations input, review, and export interface.

## Security and data integrity
- Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: browser automation library, integrations, cloud execution, templates, and model orchestration.

## Agent implementation rules
- Project rule, data: Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Project rule, behavior: Implement a fixed trigger, transform, condition, and action workflow model rather than a general visual language.
- Project rule, recovery: Store every run, step input hash, output summary, retry, and final status in PostgreSQL.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this workflow automation and app integrations operation with sample or user-owned data: Implement a fixed trigger, transform, condition, and action workflow model rather than a general visual language.
- Show a concrete result or export: Add rate limits, backoff, dead-letter handling, manual replay, cancellation, and secret rotation.
- State the practical limit: browser automation library, integrations, cloud execution, templates, and model orchestration.

## Engineering roadmap
1. Phase 1, architecture and data: Use TypeScript, Node.js 22, PostgreSQL, Redis, BullMQ, and Docker Compose. Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
2. Phase 2, implement: Implement a fixed trigger, transform, condition, and action workflow model rather than a general visual language.
3. Phase 3, implement: Connect exactly two named services using documented APIs and encrypted credentials.
4. Phase 4, review and output: Add rate limits, backoff, dead-letter handling, manual replay, cancellation, and secret rotation.
5. Phase 5, recovery and acceptance: Store every run, step input hash, output summary, retry, and final status in PostgreSQL. Verify this invariant with a saved fixture: A retry after a provider timeout must not repeat a completed external action without an explicit reconciliation step. State the practical limit: browser automation library, integrations, cloud execution, templates, and model orchestration.

## Paid-product capabilities outside this build
- browser automation library, integrations, cloud execution, templates, and model orchestration
- thousands of connectors
- maintained OAuth applications
- schema-drift handling
- high-scale durable execution and support

## Implementation prompt
Build me a focused workflow automation and app integrations workflow for the personal core of Bardeen. Requirements:

- Use TypeScript, Node.js 22, PostgreSQL, Redis, BullMQ, and Docker Compose. Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Paid product context: Automate a narrow browser workflow on user-approved pages with visible steps. Build only this DIY scope: Automate a narrow browser workflow on user-approved pages with visible steps, execute it durably, expose retries and logs, and avoid claiming a general integration platform.
- 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.
- Add rate limits, backoff, dead-letter handling, manual replay, cancellation, and secret rotation.
- Use a focused workflow automation and app integrations input, review, and export interface. Required input or access: OAuth or API credentials for two chosen services; Redis. Keep credentials in .env.
- Recovery: Store every run, step input hash, output summary, retry, and final status in PostgreSQL.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: A retry after a provider timeout must not repeat a completed external action without an explicit reconciliation step.
- Out of scope: browser automation library, integrations, cloud execution, templates, and model orchestration; thousands of connectors. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.