Artist onboarding, release workflows, and creative production. I’m Tad, a musician and builder turning the work around my own music and teaching business into useful software.
Autolabel by Preballin: an artist operating system.
I designed and built Autolabel, from artist onboarding and profile discovery to saved context, AI-assisted strategy, and the release workspace. I use AI coding tools throughout the build and own the product decisions, integration, testing, and deployment.
Live product · early-stageAUTOLABEL: ARTIST OPERATING SYSTEMStart with an artist link, confirm the profiles, refine the context, and get an editable starting picture. The artist stays in control of what the system uses and what happens next.Open live app →
Working today: profile discovery, editable context and first-map generation are deployed. This is an early product; artist adoption and campaign outcomes are still being validated. Connected publishing depends on each platform’s authorization and approval.
Watch the onboarding walkthrough · no account needed
Recorded in Autolabel with a fictional artist and example responses. This demonstrates the workflow, not a real artist analysis or a live platform lookup.
Explore Autolabel: screens & how it works
Inside the build Four screens from the same system: the Artist Snapshot web, the deep read, the connections hub, and the label desk. Tap any panel to open the live app.
Artist Snapshot · the webAn artist profile you can exploreThe AI writes a full label read covering core themes, visual world, content voice, fan archetypes, influences, and the fit, then renders it as an explorable web you drag through and tap to read.Artist Snapshot · the readLong-form, in the artist's voiceEvery section expands into a written read grounded in confirmed profiles and the artist's own words: with sources and room for the artist to correct or add context.Connections hubArtist assets in one placePress assets, EPKs, discography and ISRCs, split sheets, and PRO registration: release details collected in one workspace, with nothing required to start.The label deskYour whole team, in syncOne dashboard that reads from a single source on the artist: ask the room, or hand a job to the right desk, such as the release strategist or content director, with approval-gated automation.
Integrations
Everything wired in
Build notes
Music platforms: Spotify Web API, Apple Music (iTunes), Deezer, YouTube Data API, and SoundCloud, with live artist and catalog search
Social: Instagram Graph API for official profile and insights, plus X, Twitch, TikTok, Threads, and Facebook search
AI models: GLM via Z.ai (OpenAI-compatible), bring-your-own-key for Anthropic / OpenAI / OpenRouter / Gemini, or your own AI subscription over an OAuth runtime
Payments: Stripe subscriptions and Label Balance top-ups, signed webhooks crediting a tier-aware ledger
Email: Resend on a verified domain for artist confirmations
Notifications: Discord webhooks on every intake and payment
Auth and data: Google OAuth with HMAC sessions, Postgres (Neon/Supabase), and Supabase blob storage
Manual analytics: paste and upload layer for Spotify for Artists, Apple for Artists, Chartmetric, Songstats, Soundcharts, and Viberate
How it works
Under the hood
Build notes
Stack: Next.js App Router on Vercel serverless with a tenant-scoped multi-workspace data model and fail-closed auth
Connector library: normalizes 8+ platforms into one honest schema, showing "unavailable" wherever a platform does not expose data instead of guessing
Artist Snapshot engine: combines confirmed profiles, retrieved context, and artist input to generate an editable first map
AI layer: uses supplied context and source references, with artist review to catch errors and fill gaps
Agentic but safe: drafts captions, campaigns, and posts automatically while publishing stays human-approved
Billing: Stripe Checkout (no card data touches the app), a signed webhook, then a Label Balance ledger with 20%-markup and at-cost tier logic
Security: AES-encrypted credential storage for bring-your-own-key, with secrets never serialized
Quality: 838 tests passed for the October 12 onboarding release, with one optional integration test skipped; responsive UI and provider checks also completed
Music video · Ray J
Ray J. Red Noses.
A song and music video calling out celebrity crypto scams. I connected with Ray J’s business partner/manager and pitched the concept to them and Ray J. They were in, and we made it happen together.
I originated and pitched the concept, wrote the lyrics for my part, and worked with the team to record and arrange the song and shoot the video. I handled all the editing and AI work, then helped put the finished collaboration out into the world.
From pitch to release: creative development, collaborator outreach, songwriting and performance, arrangement, video editing, and AI visuals.
AEO in practice · October 2026
People are finding my lessons through ChatGPT. Here’s how.
Over roughly a month, multiple students told me they found my lessons through ChatGPT before reaching out and booking. Behind that result is the AEO and automation system I built for my piano, Ableton, production, and songwriting lesson business.
The process: I use Hermes, Codex, and Claude Code to check the live service pages, find questions a prospective student still needs answered, and prepare source-backed updates for review. The pages explain what I teach, where lessons happen, what they cost, and how to book. I review the changes before publishing, then verify the released pages and monitor AI-search referrals.
The result: Students are discovering the business through ChatGPT and turning that discovery into lesson bookings. I track referral traffic separately from what students tell me; the evidence supports discovery and bookings, not a guaranteed ranking or a claim that any single edit caused them.
Bring me a repeated task, or a team building with AI.
I'm open to automation clients, applied AI roles, and artists or founders who want to collaborate. The public examples show research, run handling, and reporting with synthetic inputs or published aggregates. Customer data and production prompts stay private.
Tools for making music, running a teaching business, and keeping everyday work moving.
AI operations command center
Hermes, Codex, and Claude Code operations
Recurring discovery reports, site checks, lead-source reconciliation, bookmark intake, and shared agent history. Public examples show how runs expose incomplete coverage, suppress duplicates, and recover after failure. Inspect the selected systems and code.
Music education product
Notespawn: Sight-Reading Generator
A web app that writes fresh grand-staff piano sight-reading exercises. You pick difficulty, key, time signature, hands, and seed, then play it back or export it to PDF, MusicXML, or MIDI.
A closer look at the music tools, rehearsal app, and workflows behind the projects.
Theater practice appScenePal / ScenePal rehearsal modeLine-practice interface with hidden lines, character roles, progress tracking, and reveal controls for running a scene.Open live tool →Script parsing workflowScenePal script import and setupScript import and scene-selection flow that turns messy script input into practice-ready material.Open live tool →Music education appNotespawn: Sight-Reading GeneratorGenerated grand-staff exercise with playback plus PDF, MusicXML, and MIDI export.Open live tool →Creator commerceBeat marketplace playerMusic-commerce interface with playable previews, license tiers, checkout buttons, and a compact audio player.Open live storefront →System architectureHermes automation fleetClean architecture view of recurring checks, report generation, approval gates, delivery routes, and archive/search handoff.Reliability modelAgent wake/cost optimizationBefore/after model for reducing noisy agent runs while preserving useful coverage and observability.Research intelligenceDaily intelligence and triage engineA research workflow that turns scattered sources into ranked findings and useful next actions.Safe deployment laneApproval-gated site operationsSafe-lane deployment flow that separates draft work from public changes and verifies production before calling work complete.Product proof pipelineProduct interface proof pipelineHow music and rehearsal tools turn structured or messy inputs into playable, exportable, public-facing interfaces.Approval-gated workflowJob and lead workflow abstractionA workflow for matching opportunities, preparing relevant examples, and reviewing follow-up drafts.
