Personio

Build me a small private employee directory and leave request tracker as a limited substitute for Personio. Requirements:

- Use Django, its built-in authentication and admin, and SQLite. Run on a private host with documented TLS or VPN access; do not publish employee records openly.
- Store employee name, work email, team, manager, start date, status, and optional document references. Keep compensation and identity documents out of the first version.
- Employees can request leave with start and end dates and a note. A named manager can approve or reject it; record actor, time, decision, and edits in an append-only activity table.
- Show balances only when an admin enters an explicit allowance and adjustments. Do not calculate statutory entitlements or infer eligibility from jurisdiction.
- Provide a team calendar, pending approvals, CSV export of directory and requests, and a dated SQLite backup with restore instructions.
- Use role checks for every read and write, and record document access. No payroll, recruiting, benefits, automated employment decisions, telemetry, or compliance certification.
- README: private deployment, account provisioning, retention and deletion choices, backups, and legal or HR review needed for official policies.

# AGENTS.md — Build guide for Personio

## Project scope
Maintain a small employee directory and leave workflow, track approvals and records, and export data without calculating payroll, automating recruiting, or making employment decisions.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Personio, maintain a small employee directory and leave workflow without payroll or recruiting automation. The hard boundary is european hr compliance, payroll, recruiting, workflows, integrations, and support, plus compliance, payroll, and regulated integrations.
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
- PostgreSQL
- private self-hosted deployment
- strict admin access
- documented retention policy

## Stack and architecture
- Django
- Django built-in authentication and admin
- SQLite
- Private host with TLS or VPN

## Security and data integrity
- Apply role checks to employee records and leave approvals
- Record actors and times for all decisions and corrections
- Keep sensitive documents out of the first version and backups access controlled
- Do not claim HR or labor-law compliance

## Agent implementation rules
- Model employees, manager relationships, leave requests, and approval events
- Make allowance values admin-entered, not statutory calculations

## 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.
- Position as a small internal directory and leave tracker with explicit policy limits

## Engineering roadmap
1. Implement employees, role-scoped access, and private deployment defaults.
2. Add leave requests, named approvers, and decision history.
3. Add exports, backup/restore guidance, and policy limits.

## Paid-product capabilities outside this build
- European HR compliance, payroll, recruiting, workflows, integrations, and support
- payroll rails
- tax and labor-law compliance
- benefits integrations
- identity checks and global employment infrastructure

## Implementation prompt
Build me a small private employee directory and leave request tracker as a limited substitute for Personio. Requirements:

- Use Django, its built-in authentication and admin, and SQLite. Run on a private host with documented TLS or VPN access; do not publish employee records openly.
- Store employee name, work email, team, manager, start date, status, and optional document references. Keep compensation and identity documents out of the first version.
- Employees can request leave with start and end dates and a note. A named manager can approve or reject it; record actor, time, decision, and edits in an append-only activity table.
- Show balances only when an admin enters an explicit allowance and adjustments. Do not calculate statutory entitlements or infer eligibility from jurisdiction.
- Provide a team calendar, pending approvals, CSV export of directory and requests, and a dated SQLite backup with restore instructions.
- Use role checks for every read and write, and record document access. No payroll, recruiting, benefits, automated employment decisions, telemetry, or compliance certification.
- README: private deployment, account provisioning, retention and deletion choices, backups, and legal or HR review needed for official policies.

## 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.