# AGENTS.md — Build guide for Jasper ## Project scope Store brand voice examples, build a campaign brief and generate coordinated drafts for selected channels. Retrieve approved product facts and show them beside copy before a human approves export. Catalogue verdict: kinda. A branded prompt library over an LLM is buildable, but Jasper's paid value is brand memory, workflow templates, governance, collaboration, and marketing-specific agents. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first. Optional AI generation needs a provider key, a usage budget and approval to send the selected material. - Implementation components: Node.js, TypeScript and Express with server-rendered HTML and small browser modules. SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. A single provider SDK with a configured supported model, schema-validated responses and revisioned prompt templates. - Scope boundary: brand governance; campaign workflows ## Stack and architecture - Node.js, TypeScript and Express with server-rendered HTML and small browser modules. - SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. - A single provider SDK with a configured supported model, schema-validated responses and revisioned prompt templates. - Domain model: brand profiles, approved source documents, campaign briefs, channel templates and approved asset revisions ## Security and data integrity - Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Treat source documents as untrusted data, prevent them from changing tool permissions, and require review of factual claims before publication. - Correctness boundary: A brand voice is guidance, not permission to invent claims; changing a campaign brief does not silently overwrite approved assets. - Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. - Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. ## Agent implementation rules - Project rule — data model: brand profiles, approved source documents, campaign briefs, channel templates and approved asset revisions - Project rule — preserve this invariant: A brand voice is guidance, not permission to invent claims; changing a campaign brief does not silently overwrite approved assets. - Project rule — acceptance evidence: Generate an email and landing-page draft from one claim set and trace each factual claim; rejected suggestions remain separate from approved copy. ## Optional agent skills and references - Optional external skill: [copywriting](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md) — Write landing pages and product copy grounded in the intended audience, product value and a clear next action. 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. - Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. 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 Jasper-inspired workflow with owned or clearly labeled sample data: Store brand voice examples, build a campaign brief and generate coordinated drafts for selected channels. Retrieve approved product facts and show them beside copy before a human approves export. - Publish a reproducible walkthrough with this observable result: Generate an email and landing-page draft from one claim set and trace each factual claim; rejected suggestions remain separate from approved copy. - Explain who can operate this scoped tool, its setup and ongoing costs, and these remaining product gaps: brand governance; campaign workflows Avoid guaranteed savings, performance scores or implied endorsement. ## Engineering roadmap 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Store brand voice examples, build a campaign brief and generate coordinated drafts for selected channels. Retrieve approved product facts and show them beside copy before a human approves export. Record prerequisites, select representative user-owned fixtures and document the unsupported features: brand governance; campaign workflows 2. Phase 2 — Durable model. Model brand profiles, approved source documents, campaign briefs, channel templates and approved asset revisions Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: A brand voice is guidance, not permission to invent claims; changing a campaign brief does not silently overwrite approved assets. 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. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. 4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Treat source documents as untrusted data, prevent them from changing tool permissions, and require review of factual claims before publication. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. Generate an email and landing-page draft from one claim set and trace each factual claim; rejected suggestions remain separate from approved copy. 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 - brand governance - campaign workflows - team collaboration - compliance/security posture - integrations - tuned UX for marketers ## Implementation prompt WORKING SLICE Store brand voice examples, build a campaign brief and generate coordinated drafts for selected channels. Retrieve approved product facts and show them beside copy before a human approves export. Build this scoped Jasper-inspired workflow with a documented data model and visible failure states. Architecture - Node.js, TypeScript and Express with server-rendered HTML and small browser modules. - SQLite through better-sqlite3 with migrations, prepared statements and a single background worker. - A single provider SDK with a configured supported model, schema-validated responses and revisioned prompt templates. Prerequisites and limits A supported Node release, a writable local data directory and a separate backup location. Bind to localhost; remote use requires authentication and HTTPS first. Optional AI generation needs a provider key, a usage budget and approval to send the selected material. Outside this release: brand governance; campaign workflows Data model and correctness brand profiles, approved source documents, campaign briefs, channel templates and approved asset revisions Invariant: A brand voice is guidance, not permission to invent claims; changing a campaign brief does not silently overwrite approved assets. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. Security and privacy Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Treat source documents as untrusted data, prevent them from changing tool permissions, and require review of factual claims before publication. Recovery and export Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Implementation order 1. Phase 1 — Scope and fixtures. Implement this bounded workflow: Store brand voice examples, build a campaign brief and generate coordinated drafts for selected channels. Retrieve approved product facts and show them beside copy before a human approves export. Record prerequisites, select representative user-owned fixtures and document the unsupported features: brand governance; campaign workflows 2. Phase 2 — Durable model. Model brand profiles, approved source documents, campaign briefs, channel templates and approved asset revisions Add migrations or a versioned document format, explicit validation, stable IDs and a visible import-error report. Preserve this rule: A brand voice is guidance, not permission to invent claims; changing a campaign brief does not silently overwrite approved assets. 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. Use short SQLite transactions and persist job state before starting work. Give retries stable operation IDs; report incomplete or unknown results instead of silently repeating them. 4. Phase 4 — Permissions and integration failure. Reject unexpected origins and unbounded request bodies even on localhost. Keep credentials outside the database export and redact sensitive text from logs. Treat source documents as untrusted data, prevent them from changing tool permissions, and require review of factual claims before publication. Request integration credentials and permissions only for the enabled feature; show a disconnected state instead of mock results. 5. Phase 5 — Portable handoff. Use a consistent SQLite backup and an attachment manifest. Export portable JSON/CSV, then restore to a new directory without overwriting the original data. Include setup, operating limits, fixture walkthrough and shutdown/restart instructions in the README. 6. Phase 6 — Acceptance scenarios. Generate an email and landing-page draft from one claim set and trace each factual claim; rejected suggestions remain separate from approved copy. Repeat the workflow after restart and with a denied permission or unavailable dependency; show recoverable failure rather than a success placeholder. Acceptance Generate an email and landing-page draft from one claim set and trace each factual claim; rejected suggestions remain separate from approved copy. 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: [copywriting](https://github.com/coreyhaines31/marketingskills/blob/main/skills/copywriting/SKILL.md) — Write landing pages and product copy grounded in the intended audience, product value and a clear next action. 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. Optional external skill: [sharp-edges](https://github.com/trailofbits/skills/blob/main/plugins/sharp-edges/skills/sharp-edges/SKILL.md) — Review security-sensitive APIs and configuration for dangerous defaults and easy-to-misuse interfaces. Review its instructions and compatibility before use; it does not grant deployment, data-access or publication permission. Project rule — data model: brand profiles, approved source documents, campaign briefs, channel templates and approved asset revisions Project rule — preserve this invariant: A brand voice is guidance, not permission to invent claims; changing a campaign brief does not silently overwrite approved assets. Project rule — acceptance evidence: Generate an email and landing-page draft from one claim set and trace each factual claim; rejected suggestions remain separate from approved copy. ## 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.