Vibecode LLM Pulse

You are building a lean indie version of LLM Pulse.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# LLM Pulse indie build

## Goal

Build the smallest trustworthy replacement for the core LLM Pulse workflow for one developer or a tiny team.

## Scope

Run a fixed prompt set against one model API, store the answers, detect brand and competitor mentions and citations, and show weekly trends for one project.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- managed execution across the full model set
- long-term historical comparisons and evidence
- reputation, source, traffic, and competitor workflows
- team permissions, exports, alerts, and integrations
- production monitoring and support

If those capabilities are essential, use Elmo instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build a local, single-user AI visibility tracker for one brand.
Use Node.js 22, TypeScript, Express, better-sqlite3, server-rendered HTML, and vanilla JavaScript.
Bind the app to localhost:4173 and provide one documented command for the first run.
Keep MODEL_BASE_URL, MODEL_API_KEY, and MODEL_NAME in .env and ship a safe .env.example.
Support one JSON chat endpoint configured entirely through those environment variables.
Document the endpoint contract and isolate it behind one small adapter so it can be replaced later.
Let the user configure one brand, aliases, three competitors, and up to 25 prompts.
Run prompts manually and on a weekly local schedule with a clear API budget limit.
Limit concurrency, retry transient failures, and keep failed prompts visible instead of dropping them.
Store every prompt, raw answer, model name, timestamp, latency, and error in SQLite.
Detect case-insensitive brand and competitor mentions using editable aliases.
Extract and normalize URLs from answers, then preserve the source answer for every citation.
Use one structured model pass to label brand sentiment as positive, neutral, negative, or absent.
Calculate mention rate, citation rate, competitor share of voice, and net sentiment with documented formulas.
Show current results, weekly trends, and a prompt-level evidence table on a compact dashboard.
Make every aggregate metric link back to the raw answers used to calculate it.
Export prompts, answers, mentions, citations, and weekly metrics as CSV files.
Add backup and restore commands for the SQLite database.
Do not add accounts, billing, teams, telemetry, web crawling, or an integration catalog.
Do not claim parity with managed multi-model collection, reputation workflows, traffic analytics, or production monitoring.
Write tests for alias matching, URL normalization, retry handling, and metric calculations.
Include a README with setup, API cost controls, data location, backup steps, and limitations.
Run the tests and production build before finishing, then list the exact commands used.

## Required capabilities

- one compatible model API key
- Node.js 22
- SQLite
- a scheduled local process
- a small API budget

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a lean indie version of LLM Pulse.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== README.md =====
# LLM Pulse indie build

## Goal

Build the smallest trustworthy replacement for the core LLM Pulse workflow for one developer or a tiny team.

## Scope

Run a fixed prompt set against one model API, store the answers, detect brand and competitor mentions and citations, and show weekly trends for one project.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- managed execution across the full model set
- long-term historical comparisons and evidence
- reputation, source, traffic, and competitor workflows
- team permissions, exports, alerts, and integrations
- production monitoring and support

If those capabilities are essential, use Elmo instead of pretending the gap is solved.

===== AGENTS.md =====
# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

===== BUILD_PLAN.md =====
# Build plan

## Original build brief

Build a local, single-user AI visibility tracker for one brand.
Use Node.js 22, TypeScript, Express, better-sqlite3, server-rendered HTML, and vanilla JavaScript.
Bind the app to localhost:4173 and provide one documented command for the first run.
Keep MODEL_BASE_URL, MODEL_API_KEY, and MODEL_NAME in .env and ship a safe .env.example.
Support one JSON chat endpoint configured entirely through those environment variables.
Document the endpoint contract and isolate it behind one small adapter so it can be replaced later.
Let the user configure one brand, aliases, three competitors, and up to 25 prompts.
Run prompts manually and on a weekly local schedule with a clear API budget limit.
Limit concurrency, retry transient failures, and keep failed prompts visible instead of dropping them.
Store every prompt, raw answer, model name, timestamp, latency, and error in SQLite.
Detect case-insensitive brand and competitor mentions using editable aliases.
Extract and normalize URLs from answers, then preserve the source answer for every citation.
Use one structured model pass to label brand sentiment as positive, neutral, negative, or absent.
Calculate mention rate, citation rate, competitor share of voice, and net sentiment with documented formulas.
Show current results, weekly trends, and a prompt-level evidence table on a compact dashboard.
Make every aggregate metric link back to the raw answers used to calculate it.
Export prompts, answers, mentions, citations, and weekly metrics as CSV files.
Add backup and restore commands for the SQLite database.
Do not add accounts, billing, teams, telemetry, web crawling, or an integration catalog.
Do not claim parity with managed multi-model collection, reputation workflows, traffic analytics, or production monitoring.
Write tests for alias matching, URL normalization, retry handling, and metric calculations.
Include a README with setup, API cost controls, data location, backup steps, and limitations.
Run the tests and production build before finishing, then list the exact commands used.

## Required capabilities

- one compatible model API key
- Node.js 22
- SQLite
- a scheduled local process
- a small API budget

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

===== .env.example =====
# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

You are building a production product version of LLM Pulse.

Create the following project files first, then implement the application by following them. Keep the files updated as decisions change. Do not collapse this into a single README or prompt.

===== PRODUCT.md =====
# LLM Pulse product brief

## Problem

The core loop is a realistic weekend build: run a fixed prompt set against a model API, detect brand and competitor mentions, collect citations, and chart the results. The gap appears when you need dependable runs across many models, long-term evidence, team access, exports, alerts, and the broader visibility and reputation workflow.

## Product outcome

Run a fixed prompt set against one model API, store the answers, detect brand and competitor mentions and citations, and show weekly trends for one project.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- one compatible model API key
- Node.js 22
- SQLite
- a scheduled local process
- a small API budget

## Explicit non-goals for v1

- managed execution across the full model set
- long-term historical comparisons and evidence
- reputation, source, traffic, and competitor workflows
- team permissions, exports, alerts, and integrations
- production monitoring and support

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

===== ARCHITECTURE.md =====
# Architecture

## Starting brief

Build a local, single-user AI visibility tracker for one brand.
Use Node.js 22, TypeScript, Express, better-sqlite3, server-rendered HTML, and vanilla JavaScript.
Bind the app to localhost:4173 and provide one documented command for the first run.
Keep MODEL_BASE_URL, MODEL_API_KEY, and MODEL_NAME in .env and ship a safe .env.example.
Support one JSON chat endpoint configured entirely through those environment variables.
Document the endpoint contract and isolate it behind one small adapter so it can be replaced later.
Let the user configure one brand, aliases, three competitors, and up to 25 prompts.
Run prompts manually and on a weekly local schedule with a clear API budget limit.
Limit concurrency, retry transient failures, and keep failed prompts visible instead of dropping them.
Store every prompt, raw answer, model name, timestamp, latency, and error in SQLite.
Detect case-insensitive brand and competitor mentions using editable aliases.
Extract and normalize URLs from answers, then preserve the source answer for every citation.
Use one structured model pass to label brand sentiment as positive, neutral, negative, or absent.
Calculate mention rate, citation rate, competitor share of voice, and net sentiment with documented formulas.
Show current results, weekly trends, and a prompt-level evidence table on a compact dashboard.
Make every aggregate metric link back to the raw answers used to calculate it.
Export prompts, answers, mentions, citations, and weekly metrics as CSV files.
Add backup and restore commands for the SQLite database.
Do not add accounts, billing, teams, telemetry, web crawling, or an integration catalog.
Do not claim parity with managed multi-model collection, reputation workflows, traffic analytics, or production monitoring.
Write tests for alias matching, URL normalization, retry handling, and metric calculations.
Include a README with setup, API cost controls, data location, backup steps, and limitations.
Run the tests and production build before finishing, then list the exact commands used.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

===== AGENTS.md =====
# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

===== MILESTONES.md =====
# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

===== OPERATIONS.md =====
# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted LLM Pulse capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

# LLM Pulse indie build

## Goal

Build the smallest trustworthy replacement for the core LLM Pulse workflow for one developer or a tiny team.

## Scope

Run a fixed prompt set against one model API, store the answers, detect brand and competitor mentions and citations, and show weekly trends for one project.

## Quick start

1. Install the documented dependencies.
2. Copy `.env.example` to `.env`.
3. Run the development command chosen during implementation.
4. Complete the acceptance checks in `BUILD_PLAN.md`.

## Honest limits

This build deliberately does not replace:
- managed execution across the full model set
- long-term historical comparisons and evidence
- reputation, source, traffic, and competitor workflows
- team permissions, exports, alerts, and integrations
- production monitoring and support

If those capabilities are essential, use Elmo instead of pretending the gap is solved.

# Agent instructions

- Optimize for a working, understandable weekend build.
- Prefer the fewest moving parts that satisfy the brief.
- Do not invent cryptography, security guarantees, APIs, or compliance claims.
- Keep secrets out of source control and logs.
- Add focused tests for destructive, security-sensitive, and data-loss paths.
- Run the project checks before declaring the build complete.
- Record any deliberate shortcut in the README under "Tradeoffs".

# Build plan

## Original build brief

Build a local, single-user AI visibility tracker for one brand.
Use Node.js 22, TypeScript, Express, better-sqlite3, server-rendered HTML, and vanilla JavaScript.
Bind the app to localhost:4173 and provide one documented command for the first run.
Keep MODEL_BASE_URL, MODEL_API_KEY, and MODEL_NAME in .env and ship a safe .env.example.
Support one JSON chat endpoint configured entirely through those environment variables.
Document the endpoint contract and isolate it behind one small adapter so it can be replaced later.
Let the user configure one brand, aliases, three competitors, and up to 25 prompts.
Run prompts manually and on a weekly local schedule with a clear API budget limit.
Limit concurrency, retry transient failures, and keep failed prompts visible instead of dropping them.
Store every prompt, raw answer, model name, timestamp, latency, and error in SQLite.
Detect case-insensitive brand and competitor mentions using editable aliases.
Extract and normalize URLs from answers, then preserve the source answer for every citation.
Use one structured model pass to label brand sentiment as positive, neutral, negative, or absent.
Calculate mention rate, citation rate, competitor share of voice, and net sentiment with documented formulas.
Show current results, weekly trends, and a prompt-level evidence table on a compact dashboard.
Make every aggregate metric link back to the raw answers used to calculate it.
Export prompts, answers, mentions, citations, and weekly metrics as CSV files.
Add backup and restore commands for the SQLite database.
Do not add accounts, billing, teams, telemetry, web crawling, or an integration catalog.
Do not claim parity with managed multi-model collection, reputation workflows, traffic analytics, or production monitoring.
Write tests for alias matching, URL normalization, retry handling, and metric calculations.
Include a README with setup, API cost controls, data location, backup steps, and limitations.
Run the tests and production build before finishing, then list the exact commands used.

## Required capabilities

- one compatible model API key
- Node.js 22
- SQLite
- a scheduled local process
- a small API budget

## Delivery order

1. Scaffold the smallest runnable application and document its commands.
2. Implement the primary data model and core workflow.
3. Add validation, safe failure states, and persistence.
4. Cover the critical path with automated tests.
5. Exercise a clean install from the README and fix every missing step.

## Done when

- A new user can go from clone to first successful workflow using only the README.
- The core workflow works without paid infrastructure unless the brief requires it.
- Tests cover the highest-risk behavior.
- Known limitations are explicit rather than hidden.

# Copy to .env and document every variable when it is introduced.
# Never put real credentials in this file.

APP_ENV=development
# Add only values required by the selected implementation.

# LLM Pulse product brief

## Problem

The core loop is a realistic weekend build: run a fixed prompt set against a model API, detect brand and competitor mentions, collect citations, and chart the results. The gap appears when you need dependable runs across many models, long-term evidence, team access, exports, alerts, and the broader visibility and reputation workflow.

## Product outcome

Run a fixed prompt set against one model API, store the answers, detect brand and competitor mentions and citations, and show weekly trends for one project.

## Target user

A serious builder who needs a maintainable product foundation rather than a one-off demo.

## Required capabilities

- one compatible model API key
- Node.js 22
- SQLite
- a scheduled local process
- a small API budget

## Explicit non-goals for v1

- managed execution across the full model set
- long-term historical comparisons and evidence
- reputation, source, traffic, and competitor workflows
- team permissions, exports, alerts, and integrations
- production monitoring and support

## Success criteria

- The primary workflow is measurable end to end.
- Setup is reproducible in a clean environment.
- Failure, recovery, and support paths are documented.
- Product claims match what the implementation actually guarantees.

# Architecture

## Starting brief

Build a local, single-user AI visibility tracker for one brand.
Use Node.js 22, TypeScript, Express, better-sqlite3, server-rendered HTML, and vanilla JavaScript.
Bind the app to localhost:4173 and provide one documented command for the first run.
Keep MODEL_BASE_URL, MODEL_API_KEY, and MODEL_NAME in .env and ship a safe .env.example.
Support one JSON chat endpoint configured entirely through those environment variables.
Document the endpoint contract and isolate it behind one small adapter so it can be replaced later.
Let the user configure one brand, aliases, three competitors, and up to 25 prompts.
Run prompts manually and on a weekly local schedule with a clear API budget limit.
Limit concurrency, retry transient failures, and keep failed prompts visible instead of dropping them.
Store every prompt, raw answer, model name, timestamp, latency, and error in SQLite.
Detect case-insensitive brand and competitor mentions using editable aliases.
Extract and normalize URLs from answers, then preserve the source answer for every citation.
Use one structured model pass to label brand sentiment as positive, neutral, negative, or absent.
Calculate mention rate, citation rate, competitor share of voice, and net sentiment with documented formulas.
Show current results, weekly trends, and a prompt-level evidence table on a compact dashboard.
Make every aggregate metric link back to the raw answers used to calculate it.
Export prompts, answers, mentions, citations, and weekly metrics as CSV files.
Add backup and restore commands for the SQLite database.
Do not add accounts, billing, teams, telemetry, web crawling, or an integration catalog.
Do not claim parity with managed multi-model collection, reputation workflows, traffic analytics, or production monitoring.
Write tests for alias matching, URL normalization, retry handling, and metric calculations.
Include a README with setup, API cost controls, data location, backup steps, and limitations.
Run the tests and production build before finishing, then list the exact commands used.

## Boundaries

Separate the product into replaceable modules for interface, application logic, persistence, external integrations, and operational concerns. Keep domain logic independent from delivery frameworks and vendors.

## Production baseline

- Configuration: validated at startup with safe local defaults where possible.
- Security: least privilege, input validation, secret redaction, rate limits on abuse-prone paths, and no invented security primitives.
- Data: explicit schema and migrations, transactional writes where integrity matters, backup and restore instructions.
- Integrations: adapters around third-party providers, idempotent webhook or job processing, bounded retries, and timeouts.
- Observability: structured logs with request or operation IDs, an error-tracking hook, and health/readiness checks where a server exists.
- Quality: unit tests for domain rules, integration tests at module boundaries, and one end-to-end critical-path test.

## Decision records

For each major dependency, document why it was chosen, its failure mode, and how it can be replaced. Do not introduce infrastructure until a requirement justifies it.

# Agent instructions

- Read `PRODUCT.md` and `ARCHITECTURE.md` before changing code.
- Implement milestone by milestone; keep each change reviewable and leave the application runnable.
- Treat authentication, payments, encryption, imports, webhooks, and destructive actions as high-risk boundaries when present.
- Never invent cryptography or silently weaken a requirement to make a test pass.
- Use provider interfaces for external services and deterministic fakes in tests.
- Add migrations and rollback or recovery notes for persistent data changes.
- Log useful operational context without credentials, tokens, passwords, or personal data.
- Update documentation and run all checks before completing a milestone.

# Delivery milestones

## M0 — Decisions and scaffold

- Confirm the runtime, persistence model, threat boundaries, and deployment target.
- Create a reproducible local environment and continuous checks.

## M1 — Core workflow

- Implement the smallest end-to-end product path with validation and tests.
- Keep integrations behind interfaces.

## M2 — Trust layer

- Add secure failure behavior, recovery paths, audit-relevant events, and data safeguards.
- Test abuse cases and destructive operations.

## M3 — Operability

- Add structured logs, error reporting hooks, health signals, backup/restore documentation, and deployment configuration.

## M4 — Release gate

- Run a clean-install test, critical-path end-to-end test, dependency review, and documented rollback exercise.
- Compare the shipped behavior with `PRODUCT.md` and publish remaining limitations.

# Operations

## Before release

- Validate configuration and secrets at startup.
- Define backup, restore, and rollback procedures and test them.
- Document logs, error tracking, health signals, and alert ownership.
- Set dependency update and vulnerability review expectations.

## Incident checklist

1. Contain the issue without destroying evidence or user data.
2. Record the timeline and affected scope.
3. Rotate exposed secrets and revoke compromised sessions or credentials.
4. Restore from a verified source when needed.
5. Document the root cause, remediation, and regression test.

## Launch constraint

Do not market omitted LLM Pulse capabilities as implemented. The v1 non-goals in `PRODUCT.md` remain user-visible limitations until they are deliberately delivered.

$ choose a build depth, inspect the files, then open the complete pack in your agent