Final Round AI

Build me a focused resumes, job tracking and interview practice workflow for the personal core of Final Round AI. Requirements:

- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and an optional OpenAI API. Model the inputs, state transitions, and outputs named in this resumes, job tracking and interview practice prompt; keep source IDs and timestamps.
- Paid product context: Provide ethical offline interview practice and post-session review without live deceptive assistance. Build only this DIY scope: Run ethical offline interview practice with post-session review, tailor user-authored materials against a supplied role, and keep every claim traceable to the user's own evidence, without live deceptive assistance.
- Create a structured evidence bank for roles, projects, skills, dates, metrics, and source notes.
- Import a job description and highlight requirements without inventing missing experience.
- Generate a tailored resume variant only from approved evidence and show the source for each bullet. Add application stages, contacts, tasks, dates, notes, documents, and a follow-up view. Export resume data as JSON and PDF plus the application tracker as CSV.
- Use a local web page with input, progress, review, and export views. Required input or access: local browser; resume and job-description files. Keep credentials in .env.
- Recovery: If optional OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- 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: live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure; proprietary recruiter data. 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 Final Round AI

## Project scope
Run ethical offline interview practice with post-session review, tailor user-authored materials against a supplied role, and keep every claim traceable to the user's own evidence, without live deceptive assistance.

Catalogue verdict: no. A consolation build is possible, but the paid product's decisive value sits outside a solo rebuild. For Final Round AI, provide ethical offline interview practice and post-session review without live deceptive assistance. The hard boundary is live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure, plus data, distribution, and coaching.
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
- local browser
- resume and job-description files
- optional OpenAI API key

## Stack and architecture
- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and an optional OpenAI API.
- Model the inputs, state transitions, and outputs named in this resumes, job tracking and interview practice prompt; keep source IDs and timestamps.
- Interface for this resumes, job tracking and interview practice workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- If optional OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure.

## Agent implementation rules
- Project rule, data: Model the inputs, state transitions, and outputs named in this resumes, job tracking and interview practice prompt; keep source IDs and timestamps.
- Project rule, behavior: Create a structured evidence bank for roles, projects, skills, dates, metrics, and source notes.
- Project rule, recovery: If optional OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.

## 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 resumes, job tracking and interview practice operation with sample or user-owned data: Create a structured evidence bank for roles, projects, skills, dates, metrics, and source notes.
- Show a concrete result or export: Export resume data as JSON and PDF plus the application tracker as CSV.
- State the practical limit: live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure.

## Engineering roadmap
1. Phase 1, architecture and data: Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and an optional OpenAI API. Model the inputs, state transitions, and outputs named in this resumes, job tracking and interview practice prompt; keep source IDs and timestamps.
2. Phase 2, implement: Create a structured evidence bank for roles, projects, skills, dates, metrics, and source notes.
3. Phase 3, implement: Import a job description and highlight requirements without inventing missing experience.
4. Phase 4, review and output: Generate a tailored resume variant only from approved evidence and show the source for each bullet. Export resume data as JSON and PDF plus the application tracker as CSV.
5. Phase 5, recovery and acceptance: If optional OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result. 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: live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure.

## Paid-product capabilities outside this build
- live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure
- proprietary recruiter data
- job-board distribution
- human coaching
- automated application networks

## Implementation prompt
Build me a focused resumes, job tracking and interview practice workflow for the personal core of Final Round AI. Requirements:

- Use Next.js 15, TypeScript, SQLite, Drizzle ORM, and an optional OpenAI API. Model the inputs, state transitions, and outputs named in this resumes, job tracking and interview practice prompt; keep source IDs and timestamps.
- Paid product context: Provide ethical offline interview practice and post-session review without live deceptive assistance. Build only this DIY scope: Run ethical offline interview practice with post-session review, tailor user-authored materials against a supplied role, and keep every claim traceable to the user's own evidence, without live deceptive assistance.
- Create a structured evidence bank for roles, projects, skills, dates, metrics, and source notes.
- Import a job description and highlight requirements without inventing missing experience.
- Generate a tailored resume variant only from approved evidence and show the source for each bullet. Add application stages, contacts, tasks, dates, notes, documents, and a follow-up view. Export resume data as JSON and PDF plus the application tracker as CSV.
- Use a local web page with input, progress, review, and export views. Required input or access: local browser; resume and job-description files. Keep credentials in .env.
- Recovery: If optional OpenAI API key is unavailable, keep the source record and show a recoverable error instead of a fabricated result.
- 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: live transcription, proprietary coaching, interview data, integrations, and real-time infrastructure; proprietary recruiter data. 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.