Blue Ocean Radar

A private morning podcast for every field tech, made by an agent

Spotify just gave AI agents a way to save private podcast episodes straight to a listener's library. Point that at a trade shop's schedule and every field tech could hear their day (the jobs, the notes from last visit, the parts to bring) on the drive to the first call.

Published Oct 21, 2026

The Wow

What someone built

Spotify released Save to Spotify, an open-source command-line tool and agent skill. Your agent writes something, a voice engine reads it aloud, and the tool saves it as a private episode in your own Spotify library. Spotify's own examples are a morning briefing and a meeting recap.

Open-Source Tool

Original repository
Save to Spotify repository
License
Apache 2.0, per the repository
What you need
  • A Spotify account for each listener; each one authorizes the CLI once
  • A voice engine: the README recommends Kokoro (free, runs locally) and also supports OpenAI TTS with an API key
  • An agent that reads skills, such as Claude Code, Cursor, Codex or OpenClaw (per the README)
  • macOS, Linux or Windows (Git Bash) for the install script; Go 1.21+ only if you build from source
Install
`npx skills add spotify/save-to-spotify`, or the install script and Claude Code plugin listed in the README; then `save-to-spotify auth login`.
A business you could build on it
Per-tech drive-time briefs for small trade shops

Why it's remarkable

One of the biggest consumer apps built a door specifically for AI agents, and the use it imagines is a personal daily show made for one listener.

The Opportunity

The business it reveals

Internal-podcast platforms already sell company-wide audio to large employers. In the products we checked, none makes a personal brief for each tech from that tech's own schedule, sized for a 10-truck plumbing or HVAC shop. The schedule data already sits in the shop's field-service app, and every workday starts with a drive.

Who would pay

Owners of HVAC, plumbing, electrical and pest-control shops with roughly 5 to 30 field techs who already run on a field-service app. Callbacks and unprepared visits cost them money, and they already pay for software.

The Flip

3 ways you could turn this into a business

Pre-visit audio briefs for outside sales reps

Who pays
Distributors with route-based sales reps (for example building supplies or food service)
How it would earn
Monthly fee per rep (hypothesis)
Why it might work
Reps drive between accounts and need last-order history and open issues before each stop.
What already exists
CRM mobile apps already show account notes on screen. We have not researched audio-first tools for this group, so treat it as unexplored, not empty.

Personal morning farm brief

Who pays
Small and mid-size farms
How it would earn
Monthly subscription (hypothesis)
Why it might work
Farmers already start the day with weather and markets, often in a truck or tractor cab.
What already exists
Farm radio market reports and agricultural data subscriptions already deliver weather and prices; personalizing to one farm's fields and tasks is the only angle.

Why we'd try "Per-tech drive-time briefs for small trade shops" first: Existing audio tools sell company-wide broadcasts to large employers; a personal brief from each tech's own schedule is a narrow format for small shops that we did not find offered, and it costs almost nothing to test.

Build It

How you could build it

A daily job that reads each tech's schedule export at 5:30 AM, writes a short spoken brief, renders the audio and delivers it to that tech's private feed.

First step: Install Save to Spotify, paste in a made-up day of four service calls, and have your agent turn it into a 3-minute brief in your own library. Listen to it in the car. If it helps, call one shop owner.

Agents and tools

  • An agent with scheduled tasks (Claude Code, Grok Bot or similar)
  • Save to Spotify or a private podcast host such as Transistor
  • Kokoro local voice (free) or a hosted voice
  • Read-only CSV export of the day's schedule

Setup

  1. Get one day's schedule export from a friendly shop (anonymized).
  2. Write the brief template with the owner: order, length, what never to read aloud.
  3. Pick delivery: each tech's Spotify or one private feed per tech.
  4. Schedule the daily run and a fallback text message if it fails.

What the agent does

  • Groups the tech's jobs in route order
  • Writes the brief from job notes and last-visit history
  • Renders the audio and delivers it
  • Logs which briefs were played, where the host allows it

What you do

  • Keeps the schedule correct
  • Approves the template and safety lines
  • Collects tech feedback weekly
  • Decides whether to keep paying

Your first customer: A local shop owner you can meet in person, with a two-tech pilot.

Test demand first: Two techs, ten working days. Success: both play at least 7 of 10 briefs, and the owner says it prevented at least one wasted trip or forgotten part.

Your starter instructions

Paste this into the AI agent you use (ChatGPT, Claude, Gemini, Grok Bot or another) as your first message. Copying it starts work in your own agent; it doesn't create or deploy a business by itself.

Get a launch plan

Running it

What stays human: The dispatcher stays the source of truth and corrects the schedule; the owner approves the brief template once; techs give feedback; anything about safety rules is written by the shop, not the agent.

Startup cost (estimate)
About $0 to $50 a month for a pilot (Estimate: Save to Spotify and Kokoro are free; Transistor lists private podcasts for 50 subscribers on its $19 a month plan (list price). Not measured)
Running cost
Voice and agent usage per tech per day are unknown until a pilot measures them.
How much the agent runs
Agents run one core part; people run the rest.

Pricing your own version? Use the free startup-cost worksheet.

The evidence

What the source shows: Spotify's public repository and README (Apache 2.0): what the tool does, how to install it, and its example uses. We read them; we haven't run a trade-shop pilot.

What's ours: The trade-shop service is our application of the tool. Nobody sells it yet, so there are no results to report. The market evidence is what adjacent internal-podcast products charge (list prices checked Oct 20, 2026).

Worth planning around

  • A wrong job note read aloud can send a tech out unprepared, so the dispatcher's schedule has to stay the source of truth.
  • Save to Spotify saves to each listener's own library, so every tech authorizes their own account; a private podcast feed may be simpler for a crew.
  • A field-service software vendor could add this as a feature.
  • Running cost per tech (voice and agent usage) is unknown until a pilot measures it.

Sources

Sources reopened Oct 20, 2026. Spot a mistake? Tell us and we'll correct it in public.

Keep reading

The Daily Paycheck: one remarkable AI business at a time, and exactly how you could build around it. Free; unsubscribe anytime.

Get new AI business discoveries by email.