Workflow App, Qunatified Self & Tableau
Workflow on iOS is basically Alteryx in your pocket for quantified-self tracking.
- Workflow on iOS lets you build automations that run from widgets, the share sheet or the Apple Watch
- The app works much like Alteryx - chaining inputs, variables, behaviours and outputs into a recipe
- You can hook into Apple APIs and external services such as Google Sheets to capture and store data
- Location can be pulled in automatically to add context to logged data, such as identifying which fuel station you're at
- It's a flexible tool for quantified-self tracking, from logging water to recording fuel purchases
Workflow on iOS lets you build lightweight automations - triggered from a widget, share sheet or Apple Watch - that prompt for input, pull in context like location, and push the result to an external store such as Google Sheets. It's a handy way to capture quantified-self data without building a dedicated app.
Tim demos this on iOS only (no Android support). The running example is a fuel tracker recipe that logs fuel purchases alongside location, but the same pattern works for any recurring data-capture habit.
- Trigger recipes from a widget 0:00
You can add a Workflow widget to your home screen containing icons for individual recipes, so a routine action - like logging water - is one tap away rather than buried in an app.
- Recipes can fire background actions 0:20
A recipe doesn't have to just log data - it can also open another app and insert pre-calculated text pulled from sources like your health data, so it's useful for pre-filling repetitive entries elsewhere.
- Not every recipe needs to live on the widget 0:41
Recipes can instead be exposed through the share extension sheet or on the Apple Watch, so you choose the entry point that fits how and where you'll actually use each one.
- Think of it like Alteryx for your phone 1:02
Workflow chains together inputs, variables and behaviours much like a data workflow tool, hooking into Apple's APIs and third-party app APIs (such as Google Sheets) so you can define a repeatable process rather than a one-off script.
- Prompts capture input as variables 1:21
As you build a recipe, you set up prompts that ask for information when it runs; whatever you enter gets captured and held as a variable for use later in the recipe.
- Output to an external store like Google Sheets 1:42
Once a recipe has gathered its variables, it can push the finished record out to a service such as Google Sheets, giving you a running log you can analyse later - the same pattern applies to any quantified-self tracking need, not just fuel.
- Workflow is iOS-only; there's no Android equivalent shown here.
- Grabbing location can be slow indoors, since GPS takes longer to resolve without a clear signal.
Reach for this when you want to log a recurring personal metric - fuel, water, habits - with minimal friction and have it land automatically in a spreadsheet for later analysis.
How this Rollup was made provenance & method
A Rollup is drafted by AI from the video's transcript, then reviewed and edited by Tim. Everything used to produce this one is listed below — the model, the exact prompt, and the source video — so the process is transparent and reproducible.
- Transcription
- On-device — NVIDIA Parakeet v3 for recent videos, OpenAI Whisper large-v3 for earlier ones. The transcript never leaves the machine or gets published.
- Drafting
- Claude Sonnet 5 in the cloud, from that transcript.
- Prompt
- The exact Rollup prompt (v2) — the full system prompt, unedited.
- Source video
- Watch on YouTube
- Drafted
- 5 July 2026 at 09:38
- Reviewed & edited
- 5 July 2026 at 09:41 · by Tim Ngwena
Model + prompt + video is everything you'd need to recreate a Rollup like this yourself. The one thing we don't share is the transcript.
Rights. The video and its transcript are the property of TN Media Ltd. Unauthorised use or download is prohibited. © TN Media Ltd.