Capture fast
Save the idea to Captures before you lose it.
capture --type audio --project api-gatewayCapture raw ideas. Turn them into builder-ready outputs.
Voice notes, text jots, links, images, and screenshots - saved instantly, source-preserved, and distilled into specs, prompts, plans, issues, and exports. AI output from images and screenshots comes with Plus. On Free, raw audio is removed 14 days after it processes, or at most 44 days after transcription if you decide later what to make from it; its transcript stays.
Capture firstSource preservedAI separatedExport ready
Recording idea
Saved on this device before it uploads
AudioTextLinksImages
RecordSaved locallyDistilledExported
Raw transcript remains accessible.
Explicit, inferred, open questions, risks, next actions.
How it works
Messy input goes in. Useful working artifacts come out.
Capture now and organize later. Your source stays separate from AI output, and you generate or export only when you know what you need.
Preserve source
Keep every captured source as a first-class record, never a byproduct of the AI output.
source.lock({ mode: 'preserve' })Distill later
Generate structured output only after the messy input is safely stored.
ai.distill({ separateInference: true })Export when ready
Ship Markdown, workspace exports, or GitHub-ready issue drafts.
export.markdown({ includeSource: true })CapturesQuick capture ready
Audio: auth redirect edge caseScreenshot: billing table layoutLink: Supabase RLS docs
Source + AIseparate records
Source stays its own record; AI output never overwrites it.
AI output highlights decisions, risks, and next actions.
Export Consoleexport-ready
markdown.zipgithub.issue.draftmcp.search.readonlyFeatures
A capture loop tuned for technical context.
QuillCaddie is not another meeting-notes page. It is a builder-focused place to keep raw thinking, technical vocabulary, and reusable output connected.
Capture without ceremony
Capture audio, text, links, images, and screenshots on any plan. Folder, model, and template choices can wait.
Source-first by design
Raw transcript and source text stay preserved. AI output is derived, inspectable, and never silently replaces the original.
Developer vocabulary aware
Keep RLS, OIDC, JWT, Supabase, Kubernetes, product names, and internal terminology intact during capture and cleanup.
Project context containers
Group captures by product, workspace, folder, or product context so later AI output has the right working memory.
Export-ready outputs
Move source and derived output into Markdown, folder exports, vault-shaped bundles, or GitHub-ready issue drafts.
Connector-ready architecture
QuillCaddie is built export-first. Action connectors, full sync and enterprise permissioning stay behind stronger controls.
Scoped MCP access for your AI tools
On Pro, AI coding environments can search captures, read product context and decisions, and pull spec bundles through scoped MCP tools.
Trust controls in the loop
Retention, export, deletion, provider isolation, and workspace boundaries are visible product concerns, not hidden footnotes.
Developer forward
Designed to become the connective tissue between ideas and tools.
Export captures as GitHub-ready issue drafts, and give AI tools scoped access to your workspace through MCP.
Provider-agnostic processing interfaces Workspace and product context boundaries Export and deletion flows built into the model
GitHub
MCP
QuillCaddiesource + output graph
Legal
Trust pages are part of the product surface.
These policy pages reflect the current V1 posture: preserve user source, separate AI output, keep secrets out of user-visible context, and make retention, export, and deletion visible.