TermsFeed

Build me a focused legal documents, privacy compliance and business administration workflow for the personal core of TermsFeed. Requirements:

- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and a versioned Markdown template engine. Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
- Paid product context: Collect facts and generate clearly labeled policy drafts from user-supplied templates. Build only this DIY scope: Collect facts, fill clearly labeled user-supplied policy templates, track versions and approvals, and repeatedly state that the output requires qualified review.
- Create versioned questionnaires, reusable fact fields, conditional sections, templates, and approval states.
- Show the source, jurisdiction, owner, reviewed date, and expiry date for every template.
- Generate DOCX and PDF drafts with prominent draft and review-required labels. Keep an immutable audit log of answers, template version, generation time, downloads, and approvals. Add role-based access, retention, export, encrypted backups, and a deadline calendar.
- Use a local web page with input, progress, review, and export views. Required input or access: self-hosted deployment; jurisdiction-specific templates supplied by the user or counsel.
- Recovery: On invalid input or interrupted processing, keep the original record, show the failed step, and permit a safe retry.
- 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: lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise; legal advice. 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 TermsFeed

## Project scope
Collect facts, fill clearly labeled user-supplied policy templates, track versions and approvals, and repeatedly state that the output requires qualified review.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For TermsFeed, collect facts and generate clearly labeled policy drafts from user-supplied templates. The hard boundary is lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise, plus expert judgment, compliance, and regulated services.
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
- self-hosted deployment
- PostgreSQL
- jurisdiction-specific templates supplied by the user or counsel
- secure backup

## Stack and architecture
- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and a versioned Markdown template engine.
- Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
- Interface for this legal documents, privacy compliance and business administration workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- On invalid input or interrupted processing, keep the original record, show the failed step, and permit a safe retry.
- Validate imported records and file paths; keep user data within the storage location named in the prompt.
- State the practical limit: lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise.

## Agent implementation rules
- Project rule, data: Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
- Project rule, behavior: Create versioned questionnaires, reusable fact fields, conditional sections, templates, and approval states.
- Project rule, recovery: On invalid input or interrupted processing, keep the original record, show the failed step, and permit a safe retry.

## 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 legal documents, privacy compliance and business administration operation with sample or user-owned data: Create versioned questionnaires, reusable fact fields, conditional sections, templates, and approval states.
- Show a concrete result or export: Keep an immutable audit log of answers, template version, generation time, downloads, and approvals.
- State the practical limit: lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise.

## Engineering roadmap
1. Phase 1, architecture and data: Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and a versioned Markdown template engine. Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
2. Phase 2, implement: Create versioned questionnaires, reusable fact fields, conditional sections, templates, and approval states.
3. Phase 3, implement: Show the source, jurisdiction, owner, reviewed date, and expiry date for every template.
4. Phase 4, review and output: Generate DOCX and PDF drafts with prominent draft and review-required labels. Keep an immutable audit log of answers, template version, generation time, downloads, and approvals.
5. Phase 5, recovery and acceptance: On invalid input or interrupted processing, keep the original record, show the failed step, and permit a safe retry. 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: lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise.

## Paid-product capabilities outside this build
- lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise
- legal advice
- jurisdictional assurance
- filing and registered-agent network
- continuous regulatory monitoring and liability

## Implementation prompt
Build me a focused legal documents, privacy compliance and business administration workflow for the personal core of TermsFeed. Requirements:

- Use Next.js 15, TypeScript, PostgreSQL, Drizzle ORM, and a versioned Markdown template engine. Model source documents, editable pages, links or annotations, and exported versions; store source IDs and timestamps for each.
- Paid product context: Collect facts and generate clearly labeled policy drafts from user-supplied templates. Build only this DIY scope: Collect facts, fill clearly labeled user-supplied policy templates, track versions and approvals, and repeatedly state that the output requires qualified review.
- Create versioned questionnaires, reusable fact fields, conditional sections, templates, and approval states.
- Show the source, jurisdiction, owner, reviewed date, and expiry date for every template.
- Generate DOCX and PDF drafts with prominent draft and review-required labels. Keep an immutable audit log of answers, template version, generation time, downloads, and approvals. Add role-based access, retention, export, encrypted backups, and a deadline calendar.
- Use a local web page with input, progress, review, and export views. Required input or access: self-hosted deployment; jurisdiction-specific templates supplied by the user or counsel.
- Recovery: On invalid input or interrupted processing, keep the original record, show the failed step, and permit a safe retry.
- 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: lawyer-drafted templates, jurisdiction updates, hosted consent tools, and compliance expertise; legal advice. 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.