# AGENTS.md — Build guide for Gojiberry AI

## Project scope
Import a permitted prospect dataset, score it against transparent ICP rules and draft a connection note referencing the recorded signal. Require human review and manual outreach or an explicitly authorized provider integration.

Catalogue verdict: yes. Every stage of this loop is already a bought part. Signals come from ready-made Apify actors, or from a Hermes agent running the watch on a schedule. Finding and enriching the people behind them is a single call to MoltSets or Prospeo. The LinkedIn send is Unipile, which will hold several connected accounts at once, so the DIY version is not capped at the two senders Pro gives you. What you actually write is the glue, the ICP scoring, and the send queue, and that is one sitting. The asterisk: you are renting four services instead of writing them, and the outreach still runs on real LinkedIn accounts with real limits.
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- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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
- A supported Node release, PostgreSQL, HTTPS for a shared deployment, and a backup destination. Begin with one workspace and explicit owner/member permissions.
- Implementation components: Next.js App Router and TypeScript for server-rendered pages and validated mutations. PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace.
- Scope boundary: Platform-approved acquisition, enrichment rights and lawful outreach need independent confirmation; no account-fleet automation.

## Stack and architecture
- Next.js App Router and TypeScript for server-rendered pages and validated mutations.
- PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace.
- Domain model: user-authorized prospect imports, observable signals, ICP rules, source evidence, draft messages and suppression states

## Security and data integrity
- Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML.
- Correctness boundary: Do not scrape protected accounts, rotate identities or automate unsolicited messages; absence of data is not an inferred personal trait.
- Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.
- Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching.

## Agent implementation rules
- Project rule — data model: user-authorized prospect imports, observable signals, ICP rules, source evidence, draft messages and suppression states
- Project rule — preserve this invariant: Do not scrape protected accounts, rotate identities or automate unsolicited messages; absence of data is not an inferred personal trait.
- Project rule — acceptance evidence: A prospect lacking the required signal receives no fabricated personalization; a suppressed contact cannot enter an approved outreach export.

## Optional agent skills and references
- Optional external skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — Review PostgreSQL schemas, queries, indexes, pooling, concurrency and row-level security. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
- Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.

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 the actual Gojiberry AI-inspired workflow with owned or clearly labeled sample data: Import a permitted prospect dataset, score it against transparent ICP rules and draft a connection note referencing the recorded signal. Require human review and manual outreach or an explicitly authorized provider integration.
- Publish a reproducible walkthrough with this observable result: A prospect lacking the required signal receives no fabricated personalization; a suppressed contact cannot enter an approved outreach export.
- Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: Platform-approved acquisition, enrichment rights and lawful outreach need independent confirmation; no account-fleet automation. Avoid guaranteed savings, performance scores or implied endorsement.

## Engineering roadmap
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import a permitted prospect dataset, score it against transparent ICP rules and draft a connection note referencing the recorded signal. Require human review and manual outreach or an explicitly authorized provider integration. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Platform-approved acquisition, enrichment rights and lawful outreach need independent confirmation; no account-fleet automation.
2. Phase 2 — Durable model. Model user-authorized prospect imports, observable signals, ICP rules, source evidence, draft messages and suppression states Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Do not scrape protected accounts, rotate identities or automate unsolicited messages; absence of data is not an inferred personal trait.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.
4. Phase 4 — Permissions and integration failure. Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. A prospect lacking the required signal receives no fabricated personalization; a suppressed contact cannot enter an approved outreach export. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

## Paid-product capabilities outside this build
- one enrichment provider instead of a 15+ provider waterfall, so coverage on the hard contacts is thinner
- cross-customer benchmarking and the weekly self-tuning
- the ten-minute setup: your version does not exist until you build it
- someone else absorbing the breakage when an actor or a LinkedIn endpoint changes
- a support line when a sending account gets restricted

## Implementation prompt
WORKING SLICE
Import a permitted prospect dataset, score it against transparent ICP rules and draft a connection note referencing the recorded signal. Require human review and manual outreach or an explicitly authorized provider integration.

Build this scoped Gojiberry AI-inspired workflow with a documented data model and visible failure states.

Architecture
- Next.js App Router and TypeScript for server-rendered pages and validated mutations.
- PostgreSQL with Drizzle migrations; Better Auth sessions for a small private workspace.

Prerequisites and limits
A supported Node release, PostgreSQL, HTTPS for a shared deployment, and a backup destination. Begin with one workspace and explicit owner/member permissions.
Outside this release: Platform-approved acquisition, enrichment rights and lawful outreach need independent confirmation; no account-fleet automation.

Data model and correctness
user-authorized prospect imports, observable signals, ICP rules, source evidence, draft messages and suppression states
Invariant: Do not scrape protected accounts, rotate identities or automate unsolicited messages; absence of data is not an inferred personal trait.
Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.

Security and privacy
Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML.

Recovery and export
Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching.

Implementation order
1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Import a permitted prospect dataset, score it against transparent ICP rules and draft a connection note referencing the recorded signal. Require human review and manual outreach or an explicitly authorized provider integration. Record prerequisites, select representative user-owned fixtures and document the unsupported features: Platform-approved acquisition, enrichment rights and lawful outreach need independent confirmation; no account-fleet automation.
2. Phase 2 — Durable model. Model user-authorized prospect imports, observable signals, ICP rules, source evidence, draft messages and suppression states Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: Do not scrape protected accounts, rotate identities or automate unsolicited messages; absence of data is not an inferred personal trait.
3. Phase 3 — Complete the first useful path. Implement the workflow's input, review and output interface, with clear controls and explicit empty/error states. Commit related database changes in one transaction. Use version checks for competing edits and an outbox for external notifications; retry delivery independently of saving the record.
4. Phase 4 — Permissions and integration failure. Authorize every record read and mutation on the server using its workspace membership; validate payloads, protect mutations against CSRF, and escape user-authored HTML. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results.
5. Phase 5 — Portable handoff. Export versioned JSON plus attachments and a readable CSV summary. Restore into a separate database and compare record IDs and attachment checksums before switching. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README.
6. Phase 6 — Acceptance scenarios. A prospect lacking the required signal receives no fabricated personalization; a suppressed contact cannot enter an approved outreach export. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder.

Acceptance
A prospect lacking the required signal receives no fabricated personalization; a suppressed contact cannot enter an approved outreach export.
Use real source data or clearly labeled fixtures. Explain unsupported input and provider failures; do not fabricate analytics, delivery receipts, accuracy claims or security guarantees.

Optional agent guidance
Optional external skill: [vercel-react-best-practices](https://github.com/vercel-labs/agent-skills/blob/main/skills/react-best-practices/SKILL.md) — Improve React and Next.js data fetching, rendering, bundle size and server performance. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — Review PostgreSQL schemas, queries, indexes, pooling, concurrency and row-level security. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Optional external skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — Review web interfaces for accessibility, keyboard focus, forms, navigation and interaction quality. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission.
Project rule — data model: user-authorized prospect imports, observable signals, ICP rules, source evidence, draft messages and suppression states
Project rule — preserve this invariant: Do not scrape protected accounts, rotate identities or automate unsolicited messages; absence of data is not an inferred personal trait.
Project rule — acceptance evidence: A prospect lacking the required signal receives no fabricated personalization; a suppressed contact cannot enter an approved outreach export.

## 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.