# AGENTS.md — Build guide for Savio ## Project scope Import customer feedback, link it to customer/account context, merge duplicate feature requests and maintain a transparent decision board. Catalogue verdict: kinda. The core loop is buildable, but a dependable replacement becomes a real weekend or multi-day project. For Savio, centralize manually imported feedback, tag it, and connect it to feature decisions. The hard boundary is crm and support integrations, customer revenue context, workflow, and collaboration, plus participant network, synthesis workflow, and collaboration. 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 - Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.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 - Runtime and tools: TypeScript, React, Node and PostgreSQL with workspace membership enforced on the server. - Before starting: A PostgreSQL database, session authentication, two isolated example workspaces and private attachment storage. ## Stack and architecture - TypeScript, React, Node and PostgreSQL with workspace membership enforced on the server - Data design: Store FeedbackSource, Quote, CustomerReference, FeatureRequest and MergeDecision; one source message counts once and merges retain the original evidence and dissent. - Setup: A PostgreSQL database, session authentication, two isolated example workspaces and private attachment storage ## Security and data integrity - Check membership on reads, mutations, attachments and exports. Keep activity history separate from editable current state; do not make private records public through search. - Start with manual CSV imports and an internal board. Revenue-weighted prioritization is a stated choice, not objective user value; public views must omit private customer evidence. - Keep secrets outside client bundles and exported projects; document what leaves the device and make retention/deletion controls visible. ## Agent implementation rules - Project rule — domain: Store FeedbackSource, Quote, CustomerReference, FeatureRequest and MergeDecision; one source message counts once and merges retain the original evidence and dissent. - Project rule — scope and recovery: Start with manual CSV imports and an internal board. Revenue-weighted prioritization is a stated choice, not objective user value; public views must omit private customer evidence. - Project rule — acceptance: Import the same ticket twice, merge two feature requests and undo the merge; counts and customer associations remain explainable without duplicating demand. - Project rule — delivery: document real setup commands and permissions; do not claim a build, accuracy level, performance result or security certification that has not been demonstrated. ## Optional agent skills and references - Recommended skill: [supabase-postgres-best-practices](https://github.com/supabase/agent-skills/blob/main/skills/supabase-postgres-best-practices/SKILL.md) — review this PostgreSQL domain schema, uniqueness constraints, transaction boundaries and access-scoped queries; Supabase hosting is not required. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. - Recommended skill: [web-design-guidelines](https://github.com/vercel-labs/agent-skills/blob/main/skills/web-design-guidelines/SKILL.md) — review keyboard access, focus, validation, error recovery and the readable work/review interface or HTML report. Follow the maintainer's installation instructions and match its requirements to the chosen runtime. 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 working slice using synthetic or explicitly authorized non-sensitive examples: Import customer feedback, link it to customer/account context, merge duplicate feature requests and maintain a transparent decision board. - Share a synthetic example export and the acceptance walkthrough; keep real customer, health, financial and source data private: Import the same ticket twice, merge two feature requests and undo the merge; counts and customer associations remain explainable without duplicating demand. - State the limits before asking someone to replace their existing tool: Start with manual CSV imports and an internal board. Revenue-weighted prioritization is a stated choice, not objective user value; public views must omit private customer evidence. ## Engineering roadmap 1. Phase 1 — Pin the working slice and create its example input: Import customer feedback, link it to customer/account context, merge duplicate feature requests and maintain a transparent decision board. Confirm setup: A PostgreSQL database, session authentication, two isolated example workspaces and private attachment storage. 2. Phase 2 — Implement persistence and write-time invariants before decorating the UI: Store FeedbackSource, Quote, CustomerReference, FeatureRequest and MergeDecision; one source message counts once and merges retain the original evidence and dissent. 3. Phase 3 — Connect the working view to real saved state. Check membership on reads, mutations, attachments and exports. Keep activity history separate from editable current state; do not make private records public through search. 4. Phase 4 — Expose the app-specific limits and recovery path in context: Start with manual CSV imports and an internal board. Revenue-weighted prioritization is a stated choice, not objective user value; public views must omit private customer evidence. 5. Phase 5 — Walk through this concrete acceptance case and preserve its exported evidence: Import the same ticket twice, merge two feature requests and undo the merge; counts and customer associations remain explainable without duplicating demand. Finish the README and backup/restore instructions; report unfinished capabilities explicitly. ## Paid-product capabilities outside this build - CRM and support integrations, customer revenue context, workflow, and collaboration - large participant panel - recording and transcription infrastructure - advanced research repository - enterprise governance ## Implementation prompt Build the following focused alternative to Savio. This is a deliberately limited personal or small-team substitute, not parity with the paid service. WORKING SLICE Import customer feedback, link it to customer/account context, merge duplicate feature requests and maintain a transparent decision board. SETUP AND ARCHITECTURE Use TypeScript, React, Node and PostgreSQL with workspace membership enforced on the server. Prerequisites: A PostgreSQL database, session authentication, two isolated example workspaces and private attachment storage. Before integrating anything, record actual versions and permissions, plus model files or provider limits only where used, in the README; make unavailable dependencies visible rather than simulating success. DOMAIN MODEL AND INVARIANTS Store FeedbackSource, Quote, CustomerReference, FeatureRequest and MergeDecision; one source message counts once and merges retain the original evidence and dissent. IMPLEMENTATION CONTRACT Check membership on reads, mutations, attachments and exports. Keep activity history separate from editable current state; do not make private records public through search. Provide an input/setup view, the main work view, and a review/export view appropriate to this workflow. Preserve the last saved state if a job or save fails. Include empty, loading, permission-denied, partial and retryable-error states. Log identifiers and error categories without secret values or unnecessary private content. APP-SPECIFIC BOUNDARY AND RECOVERY Start with manual CSV imports and an internal board. Revenue-weighted prioritization is a stated choice, not objective user value; public views must omit private customer evidence. ACCEPTANCE SCENARIO Import the same ticket twice, merge two feature requests and undo the merge; counts and customer associations remain explainable without duplicating demand. Also reopen the app after an interrupted operation, confirm the saved record/export remains inspectable, and document the recovery action. These are implementation acceptance requirements, not a claim that this guide has been tested. DELIVERY Deliver a runnable repository with migrations or project-format versioning, a non-sensitive example, environment/permission setup, the exact manual acceptance steps, and a backup/export-and-restore walkthrough. Implement the working slice before optional integrations; list any deferred paid-product capabilities honestly. Do not add capabilities outside the working slice just to resemble the original product. PROJECT RULES FOR AGENTS.md Keep the domain invariants above executable at the write boundary. Propose scope changes before adding providers or permissions. Never fabricate source evidence, publish results, identity matches or successful delivery. Preserve user originals and require an explicit confirmation for destructive changes or external publication. ## 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.