Intercom

Build me a focused help desks, live chat and support knowledge workflow for the personal core of Intercom. Requirements:

- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, WebSockets, and Docker Compose. Model the inputs, state transitions, and outputs named in this help desks, live chat and support knowledge prompt; keep source IDs and timestamps.
- Paid product context: Run a small website inbox and knowledge base without recreating Intercom's AI or channel network. Build only this DIY scope: Receive website messages into a small shared inbox, reply from one place, maintain a knowledge base, and retain searchable history without recreating Intercom's AI or channel network.
- Implement one workspace, agents, contacts, inboxes, conversations, messages, labels, and assignment.
- Create a shared inbox with filters, collision warnings, notes, canned replies, and searchable history.
- Add email notifications, browser notifications, and an immutable assignment and status log. Implement spam controls, attachment scanning hooks, retention settings, export, and contact deletion.
- Use a local web page with input, progress, review, and export views. Required input or access: Docker; public HTTPS deployment.
- Recovery: Ship Docker Compose, backups, health checks, migrations, and a documented admin recovery flow.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs.
- Out of scope: messaging infrastructure, AI resolution, product tours, integrations, and enterprise operations; omnichannel integrations. 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 Intercom

## Project scope
Receive website messages into a small shared inbox, reply from one place, maintain a knowledge base, and retain searchable history without recreating Intercom's AI or channel network.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Intercom, run a small website inbox and knowledge base without recreating Intercom's AI or channel network. The hard boundary is messaging infrastructure, ai resolution, product tours, integrations, and enterprise operations, plus channel integrations and support operations.
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
- Docker
- PostgreSQL
- public HTTPS deployment
- email or chat channel credentials

## Stack and architecture
- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, WebSockets, and Docker Compose.
- Model the inputs, state transitions, and outputs named in this help desks, live chat and support knowledge prompt; keep source IDs and timestamps.
- Interface for this help desks, live chat and support knowledge workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- Ship Docker Compose, backups, health checks, migrations, and a documented admin recovery flow.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: messaging infrastructure, AI resolution, product tours, integrations, and enterprise operations.

## Agent implementation rules
- Project rule, data: Model the inputs, state transitions, and outputs named in this help desks, live chat and support knowledge prompt; keep source IDs and timestamps.
- Project rule, behavior: Implement one workspace, agents, contacts, inboxes, conversations, messages, labels, and assignment.
- Project rule, recovery: Ship Docker Compose, backups, health checks, migrations, and a documented admin recovery flow.

## 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 help desks, live chat and support knowledge operation with sample or user-owned data: Implement one workspace, agents, contacts, inboxes, conversations, messages, labels, and assignment.
- Show a concrete result or export: Implement spam controls, attachment scanning hooks, retention settings, export, and contact deletion.
- State the practical limit: messaging infrastructure, AI resolution, product tours, integrations, and enterprise operations.

## Engineering roadmap
1. Phase 1, architecture and data: Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, WebSockets, and Docker Compose. Model the inputs, state transitions, and outputs named in this help desks, live chat and support knowledge prompt; keep source IDs and timestamps.
2. Phase 2, implement: Implement one workspace, agents, contacts, inboxes, conversations, messages, labels, and assignment.
3. Phase 3, implement: Create a shared inbox with filters, collision warnings, notes, canned replies, and searchable history.
4. Phase 4, review and output: Add email notifications, browser notifications, and an immutable assignment and status log. Implement spam controls, attachment scanning hooks, retention settings, export, and contact deletion.
5. Phase 5, recovery and acceptance: Ship Docker Compose, backups, health checks, migrations, and a documented admin recovery flow. Verify this invariant with a saved fixture: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs. State the practical limit: messaging infrastructure, AI resolution, product tours, integrations, and enterprise operations.

## Paid-product capabilities outside this build
- messaging infrastructure, AI resolution, product tours, integrations, and enterprise operations
- omnichannel integrations
- large-scale deliverability
- AI resolution tuning
- enterprise routing and compliance

## Implementation prompt
Build me a focused help desks, live chat and support knowledge workflow for the personal core of Intercom. Requirements:

- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, WebSockets, and Docker Compose. Model the inputs, state transitions, and outputs named in this help desks, live chat and support knowledge prompt; keep source IDs and timestamps.
- Paid product context: Run a small website inbox and knowledge base without recreating Intercom's AI or channel network. Build only this DIY scope: Receive website messages into a small shared inbox, reply from one place, maintain a knowledge base, and retain searchable history without recreating Intercom's AI or channel network.
- Implement one workspace, agents, contacts, inboxes, conversations, messages, labels, and assignment.
- Create a shared inbox with filters, collision warnings, notes, canned replies, and searchable history.
- Add email notifications, browser notifications, and an immutable assignment and status log. Implement spam controls, attachment scanning hooks, retention settings, export, and contact deletion.
- Use a local web page with input, progress, review, and export views. Required input or access: Docker; public HTTPS deployment.
- Recovery: Ship Docker Compose, backups, health checks, migrations, and a documented admin recovery flow.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: An invalid input or interrupted operation must retain the source and show a recoverable state; exported records must reload with the same IDs.
- Out of scope: messaging infrastructure, AI resolution, product tours, integrations, and enterprise operations; omnichannel integrations. 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.