Skip to main content

← Glow case study

Glow · Client & product automations

Two automations, built and tested on the live canvas

Two automations built in Glow: a travel intake automation now in client testing, and a build that goes from a sticky note and a voice prompt to a tested, reusable template.

Client & product automations

Boutique travel agency

A tailored form for each inquiry

Client testing

A Glow automation that turns an inquiry email into an individually customized Tally form, with questions and a greeting shaped by that trip.

The client can test generated forms in their own Glow account and give feedback on the questions and tone.

From inquiry to review
  1. Read the inquiry

    The client supplies an inquiry, and an AI step separates confirmed trip details from missing information to guide the questions that follow.

  2. Tailor the questions

    A second AI step drafts the greeting, questions and answer options for that specific inquiry, using the trip details and the agency's guidance.

  3. Create the form

    Python builds and validates the Tally blocks, then a separate HTTP step calls the Tally API to create the individual form.

  4. Review the form

    The founder can inspect the generated form during client testing and must approve its questions and tone before sharing it with a traveler.

Client testing only, with no automatic sending; founder approval is required before a form reaches a traveler.

Brief & technical details: A tailored form for each inquiry

The brief

The agency plans custom journeys and needs follow-up questions that reflect what each traveler has already shared. I built the intake automation around a separate Tally form for each inquiry, while keeping approval with the founder. Partner briefing is a later phase, outside this delivery.

What shapes the form

Build on the inquiry
The prompts distinguish confirmed facts from preferences that need detail, so questions can explore the trip rather than repeat dates or group size.
Keep options relevant
Destination choices stay within the requested region, and budget options reflect the destination rather than assumptions about the traveler's wealth.
Voice + MCP · Live Multiplayer Canvas

From a sticky note and voice to a tested, reusable automation

Live in production

Glow MCP documentation ↗

With the team, I designed the architecture for building, validating and testing automations on Glow's shared canvas through MCP, so multiple teammates and external AI agents operated by voice can build and iterate at the same time.

People and AI agents co-edit one live canvas, run end-to-end tests through any external MCP server and refactor working automations into reusable templates.

From canvas note to tested template
  1. Write or speak the brief

    Anyone on the team drops a sticky note on the shared canvas and speaks to the agent. The agent reads the note and current graph over Glow MCP.

  2. Build, validate & tweak live

    Glow MCP validates step schemas and lays out the graph on the canvas while teammates can immediately adjust models or settings in place.

  3. Test across any MCP

    The agent uses a second MCP server (such as Gmail MCP sending a realistic inquiry from Linear) to trigger a real run and verify the resulting draft and Slack summary.

  4. Branch or parameterize

    By voice or from a second sticky note, the agent branches logic or extracts hardcoded values into a Custom Variables step so the automation becomes a reusable template.

Runs under scoped workspace permissions, credit caps and live-automation mutation guards, with a write-free preview mode available before live execution.

Brief & technical details: From a sticky note and voice to a tested, reusable automation

Context & responsibility

In the architecture I designed with the team, you connect any AI tool, voice client or IDE as the reasoning brain, while Glow MCP validates schemas and exposes canvas state, sticky notes, live mutation guards and execution traces.

How the multiplayer MCP loop works

Simultaneous live co-editing
Several teammates and AI agents can work on the same automation at once: dropping sticky notes, tweaking models or prompts in place, and watching MCP edits land live while concurrency guards block an agent from overwriting a step modified since its last read.
End-to-end testing via any MCP
Pairing Glow MCP with any other MCP server in the same AI chat (such as Gmail, Slack, Linear or a database MCP) lets the agent fire realistic test events, inspect step-by-step execution traces and verify outputs automatically.

Watch the voice & MCP automations in action

The two latest unscripted builds, recorded on the shared canvas.

Sketch, Notes & Transcript · 04:27

Sketch, Notes & Transcript to a Live AI Automation via Claude MCP

Loads YouTube only when you press play. Privacy

Prompt on sebbuild.com ↗

Canvas Object to 9 Steps · 06:56

Claude Turns a Raw Call Transcript into a 9-Step Automation

Loads YouTube only when you press play.

Prompt on sebbuild.com ↗

Unscripted product demos, built and tested live through MCP.

Part one · Glow case study
Building the product and the automations people use it for
Let's connect

Let's talk about what you are building.

If you have a process you'd like to automate, a team exploring this way of working, or an idea worth a Friday build, reach out. I read every message.

LinkedIn (opens in a new tab)