System prompt catalog

This catalog is the public map of developer-controlled AI instructions in getbased. It covers literal system prompts, runtime system fragments, and app-authored task prompts that are deliberately sent in the user role for multimodal or local-model compatibility.

To start with a button or action in the application, use Find a prompt by feature. It shows what getbased adds, what data accompanies the request, and links directly to the readable prompt text below.

Application source is authoritative. The detail pages distinguish literal prompts from normalized templates. Normalized text preserves the maintained wording and order while replacing runtime values with {placeholders} and naming shared fragments once. A prompt change is incomplete until the source, this catalog, and directly related tests agree.

Browse the catalog

Chat and retrieval

Base chat, dynamic context, personalities, discussion, continuation, summaries, and Knowledge Base query rewriting.

Import and extraction

Lab reports, PII rewriting, supplements, EMF reports, and light-device specification extraction.

Insights and reports

Dashboard, report, Biology Score, supplement, EMF, and marker-description prompts.

Light and Sun

Shared hardware guardrails and all ten Light & Sun verdict prompts.

Scope

Included:

every non-empty system value supplied to the shared AI router;
system-prompt fragments appended at runtime;
developer-authored task instructions sent as user-role content;
app-authored chat-message templates that an explicit UI action prefills or sends;
automatic continuation and discussion messages that the app inserts;
dynamic prompt contracts whose rendered text depends on schemas, marker catalogs, allowlists, or selected context.

Excluded:

a user’s own chat message;
the user’s own text, including edits they make to an app-authored starting message;
provider capability probes such as the one-token hi request;
voice transcription and speech-synthesis payloads, which send audio or text plus model, language, and voice settings but no developer prompt;
transport formatting that only maps the same instruction to a provider API;
deterministic scoring formulas, schemas, and context data that do not instruct a model.

Visible Ask AI and chat-shortcut templates inherit the normal chat system prompt. They are cataloged under chat.prefills as user messages rather than separate privileged instructions.

Complete registry

ID	Surface	Instruction position	Source of truth
`chat.base`	Normal chat and multi-persona chat	System	`CHAT_SYSTEM_PROMPT` in `js/constants.js`
`chat.context`	Context, web state, personality, other-persona attribution	System fragments	`js/chat-prompt-context.js`
`chat.continue`	Truncated-response continuation	Automatic user message	`js/chat-continuation.js`
`chat.discussion`	Initial, rebuttal, and joining-persona turns	Automatic user messages	`js/chat-discussion-round-prompts.js`
`chat.persona-generator`	Custom personality draft	System + narrow user request	`js/chat-personalities.js`
`chat.summary`	Saved consultation summary	System	`js/chat-summaries.js`
`chat.prefills`	Explicit Ask AI actions and chat shortcuts	Editable or explicitly triggered user message	`js/chat-marker-prompts.js`, `js/dna-evidence.js`, and linked callers in the detail page
`lens.rewrite`	Knowledge Base multi-query expansion	System	`js/lens.js`
`import.classify`	Lab-report preflight classification	System + task template	`js/pdf-import-preflight.js`
`import.lab-text`	Text report extraction	Dynamic system + report text	`js/pdf-import.js`
`import.lab-image`	Image report extraction	Dynamic system + multimodal content	`js/pdf-import.js`
`import.collection-context`	Collection time and fasting rules	Shared system fragment	`js/pdf-import-ai-utils.js`
`privacy.local-pii`	Local-model report de-identification	User-role task instruction	`js/pii.js`
`import.supplement`	Label/photo and product-page extraction	User task for images; system for pages	`js/supplement-import-draft.js`, controller
`import.light-device`	Product-page/photo specification extraction	System for pages; user task for images	`js/light-device-setup-modal.js`
`import.emf`	EMF PDF extraction	Dynamic system	`js/emf.js`
`insight.report-summary`	Practitioner-facing report overview	System	`js/export-report.js`
`insight.focus-card`	Dashboard focus card	System	`js/focus-card.js`
`insight.context-dots`	Profile-area summaries and dots	Dynamic system	`js/context-card-health-dots.js`
`insight.marker-description`	One-sentence custom-marker reference	System	`js/marker-detail-content.js`
`insight.biology-score`	Deterministic Biology Score explanation	System	`js/biology-score-ai.js`
`insight.biology-context`	Suggested deterministic context flags	Dynamic system	`js/biology-score-context-ai.js`
`insight.supplement-impact`	Marker-change impact dots	Dynamic system	`js/supplement-impact.js`
`insight.emf`	Single and before/after EMF interpretation	System + task variant	`js/emf-interpretation.js`
`light.measurement`	One Light Tool measurement	System	`js/light-tools-ai-analysis.js`
`light.today`	One-day Light Today synthesis	System	`js/light-today-ai.js`
`light.room`	One room	System	`js/light-env-ai-analysis.js`
`light.device-session`	One light-device session	System	`js/light-device-ai-analysis.js`
`light.screen`	One screen record	System	`js/light-screen-ai-analysis.js`
`light.weekly-pattern`	Current versus previous seven days	System	`js/light-channels-ai-analysis.js`
`light.audit`	Frozen multi-room audit	System	`js/light-audit-ai-analysis.js`
`light.sun-session`	One modeled Sun session	System	`js/sun-ai-analysis.js`
`light.onboarding`	Light & Sun setup synthesis	System	`js/sun-onboarding-ai.js`
`light.indoor-burden`	Live indoor screening picture	System	`js/light-burden-ai-analysis.js`
`light.hardware-guardrails`	Shared fixture/flicker restrictions	Shared system fragment	`js/lighting-hardware-caveats.js`

Trust and assembly model

callClaudeAPI() is a provider-neutral router. The caller owns the instruction and context; transports do not invent a new medical persona.

feature-owned base instruction
  + shared developer fragments
  + selected runtime context
  + user or automatic task message
  → provider adapter
  → response parser / renderer

Provider adapters map the system instruction into the provider’s supported request shape. Venice encrypted mode encrypts the same system and message content before transport. Ollama and other OpenAI-compatible paths use a system-role message when a system instruction exists. Runtime context can contain user-controlled text. A section wrapper such as [section:untrusted-profile-context] is documentation for the model, not a security boundary by itself. The parser, allowlists, normalization, review UI, and deterministic code remain the enforcement boundary.

Review workflow

Identify the contract

Record the catalog ID, source identifier, instruction position, runtime placeholders, expected output, parser, and fallback.

Build adversarial fixtures

Cover ordinary input, missing data, contradictory data, stale data, embedded instructions, sensitive data, demographic edge cases, and a small local model.

Review seven dimensions

Evaluate factual grounding, medical scope, bias and assumptions, prompt-injection resistance, privacy minimization, output compatibility, and cost/context size.

Change source and docs together

Update the literal or builder, the relevant catalog page, and focused contract tests. Do not patch only the rendered copy.

Compare behavior

Use fixed inputs and judge both regressions and intended improvements. Structured surfaces must also test malformed, extra, and partial output.

Required review questions

Dimension	Questions
Grounding	Can the model use only supplied facts? Does it distinguish logs, measurements, estimates, and inference?
Medical scope	Does it diagnose, prescribe, certify safety, or invent a threshold?
Bias	Does it assume sex, age, cycle state, geography, culture, diet, resources, or compliance?
Injection	Can report, product-page, note, persona, or Knowledge Base text become an instruction?
Privacy	Is every included field necessary for this task? Is the recipient disclosed and consented?
Contract	Can the parser reject invalid enums, prose, missing fields, oversized values, or unsafe actions?
Compatibility	Does it work with the smallest supported local context and with providers that handle system messages differently?

Change proposal template

Prompt ID:
Feature and source:
Provider/model tested:
Input fixture (de-identified):
Current output:
Expected output:
Proposed instruction change:
Bias/safety/privacy impact:
Output-schema impact:
Focused tests:
Catalog pages updated:

Exact user health data and provider credentials do not belong in issues, fixtures, snapshots, or prompt documentation. Use synthetic examples.

Core project

Data model & sync

AI & agents

Prompt catalog

Feature internals

Security architecture

Operations & release

System prompt catalog

System prompt catalog

Browse the catalog

Chat and retrieval

Import and extraction

Insights and reports

Light and Sun

Scope

Complete registry

Trust and assembly model

Review workflow

Required review questions

Change proposal template

​System prompt catalog

​Browse the catalog

Chat and retrieval

Import and extraction

Insights and reports

Light and Sun

​Scope

​Complete registry

​Trust and assembly model

​Review workflow

​Required review questions

​Change proposal template

System prompt catalog

Browse the catalog

Scope

Complete registry

Trust and assembly model

Review workflow

Required review questions

Change proposal template