Building MessyData and PhysioTracker has made me think about how easy it is to reach for the same app architecture each time.
MessyData is stateless. PhysioTracker keeps its data in the browser.
Avoiding extra infrastructure helps keep the product focused.
#BuildInPublic #IndieDev #WebDevelopment
MessyData is stateless. PhysioTracker keeps its data in the browser.
Avoiding extra infrastructure helps keep the product focused.
#BuildInPublic #IndieDev #WebDevelopment
September 18, 2026 at 4:33 PM
Building MessyData and PhysioTracker has made me think about how easy it is to reach for the same app architecture each time.
MessyData is stateless. PhysioTracker keeps its data in the browser.
Avoiding extra infrastructure helps keep the product focused.
#BuildInPublic #IndieDev #WebDevelopment
MessyData is stateless. PhysioTracker keeps its data in the browser.
Avoiding extra infrastructure helps keep the product focused.
#BuildInPublic #IndieDev #WebDevelopment
Seeing MessyData described on AppBoard helped sharpen where it fits.
Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.
appboard.pro/product/mess...
#AI #DataCleaning #BuildInPublic
Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.
appboard.pro/product/mess...
#AI #DataCleaning #BuildInPublic
Messy Data — Convert messy data into clean tables in seconds · AppBoard
Convert messy data into clean tables in seconds — see Messy Data reviews, pricing and alternatives on AppBoard.
appboard.pro
September 19, 2026 at 7:43 AM
Seeing MessyData described on AppBoard helped sharpen where it fits.
Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.
appboard.pro/product/mess...
#AI #DataCleaning #BuildInPublic
Airtable and Zapier cover much broader data/workflow needs. MessyData sits in a smaller step: paste inconsistent text, turn it into a table, review, export.
appboard.pro/product/mess...
#AI #DataCleaning #BuildInPublic
Do you work with #metadata & #data in #libraries?
Want to build confidence & practical skills wrangling with #messydata?
Check out our 2day Library @carpentries.carpentries.org Workshop on "Practical Skills for Working with Data" at @astonuniversity.bsky.social 5th & 12th June tinyurl.com/22au9z2m
Want to build confidence & practical skills wrangling with #messydata?
Check out our 2day Library @carpentries.carpentries.org Workshop on "Practical Skills for Working with Data" at @astonuniversity.bsky.social 5th & 12th June tinyurl.com/22au9z2m
May 5, 2026 at 9:58 AM
Do you work with #metadata & #data in #libraries?
Want to build confidence & practical skills wrangling with #messydata?
Check out our 2day Library @carpentries.carpentries.org Workshop on "Practical Skills for Working with Data" at @astonuniversity.bsky.social 5th & 12th June tinyurl.com/22au9z2m
Want to build confidence & practical skills wrangling with #messydata?
Check out our 2day Library @carpentries.carpentries.org Workshop on "Practical Skills for Working with Data" at @astonuniversity.bsky.social 5th & 12th June tinyurl.com/22au9z2m
AI can play quite different roles in the build of a product.
In the Lab I designed MessyData to use AI in the product itself. While PhysioTracker doesn’t need AI in the user experience, but I did rely on AI to help build it.
Two different examples of AI-powered experiments for different reasons.
In the Lab I designed MessyData to use AI in the product itself. While PhysioTracker doesn’t need AI in the user experience, but I did rely on AI to help build it.
Two different examples of AI-powered experiments for different reasons.
September 25, 2026 at 6:59 AM
AI can play quite different roles in the build of a product.
In the Lab I designed MessyData to use AI in the product itself. While PhysioTracker doesn’t need AI in the user experience, but I did rely on AI to help build it.
Two different examples of AI-powered experiments for different reasons.
In the Lab I designed MessyData to use AI in the product itself. While PhysioTracker doesn’t need AI in the user experience, but I did rely on AI to help build it.
Two different examples of AI-powered experiments for different reasons.
📊 New course!
Dealing with Messy Data in R: Cleaning & Visualisation
8–10 April • Online • with @cecibaldoni.bsky.social
Learn tidyverse + ggplot2 to clean, wrangle, & visualise real-world messy data.
www.physalia-courses.org/courses-work...
#Rstats #MessyData #Dataviz
Dealing with Messy Data in R: Cleaning & Visualisation
8–10 April • Online • with @cecibaldoni.bsky.social
Learn tidyverse + ggplot2 to clean, wrangle, & visualise real-world messy data.
www.physalia-courses.org/courses-work...
#Rstats #MessyData #Dataviz
Dealing with messy data in R: data cleaning and visualisation
8-10 April 2026
www.physalia-courses.org
November 30, 2025 at 8:59 AM
📊 New course!
Dealing with Messy Data in R: Cleaning & Visualisation
8–10 April • Online • with @cecibaldoni.bsky.social
Learn tidyverse + ggplot2 to clean, wrangle, & visualise real-world messy data.
www.physalia-courses.org/courses-work...
#Rstats #MessyData #Dataviz
Dealing with Messy Data in R: Cleaning & Visualisation
8–10 April • Online • with @cecibaldoni.bsky.social
Learn tidyverse + ggplot2 to clean, wrangle, & visualise real-world messy data.
www.physalia-courses.org/courses-work...
#Rstats #MessyData #Dataviz
Starting to build more openly around AI Innovation Design Lab.
Focus: practical AI products, prototypes, and workflow tools.
First live tool: MessyData, for turning messy pasted text into cleaner structured data.
I’ll share what gets built, what works, what breaks, and where AI actually helps.
Focus: practical AI products, prototypes, and workflow tools.
First live tool: MessyData, for turning messy pasted text into cleaner structured data.
I’ll share what gets built, what works, what breaks, and where AI actually helps.
July 5, 2026 at 3:25 PM
Starting to build more openly around AI Innovation Design Lab.
Focus: practical AI products, prototypes, and workflow tools.
First live tool: MessyData, for turning messy pasted text into cleaner structured data.
I’ll share what gets built, what works, what breaks, and where AI actually helps.
Focus: practical AI products, prototypes, and workflow tools.
First live tool: MessyData, for turning messy pasted text into cleaner structured data.
I’ll share what gets built, what works, what breaks, and where AI actually helps.
In many R courses, data are clean & everything just works.
But real life is messy—and that’s where problems start
👉 Our course with @cecibaldoni.bsky.social -Dealing with Messy Data in R in April: clean, join & visualise real datasets with tidyverse & ggplot2 💻📊
shorturl.at/zdmht
#Rstats #MessyData
But real life is messy—and that’s where problems start
👉 Our course with @cecibaldoni.bsky.social -Dealing with Messy Data in R in April: clean, join & visualise real datasets with tidyverse & ggplot2 💻📊
shorturl.at/zdmht
#Rstats #MessyData
Dealing with messy data in R: data cleaning and visualisation
8-10 April 2026
www.physalia-courses.org
February 14, 2026 at 9:23 AM
In many R courses, data are clean & everything just works.
But real life is messy—and that’s where problems start
👉 Our course with @cecibaldoni.bsky.social -Dealing with Messy Data in R in April: clean, join & visualise real datasets with tidyverse & ggplot2 💻📊
shorturl.at/zdmht
#Rstats #MessyData
But real life is messy—and that’s where problems start
👉 Our course with @cecibaldoni.bsky.social -Dealing with Messy Data in R in April: clean, join & visualise real datasets with tidyverse & ggplot2 💻📊
shorturl.at/zdmht
#Rstats #MessyData
That multi-column PDF question is exactly why building MessyData in public can sharpen the product fast.
July 8, 2026 at 5:03 PM
That multi-column PDF question is exactly why building MessyData in public can sharpen the product fast.
1/ I got a useful early question about MessyData already making me glad to have started this “build in public” effort:
“Does it handle multi-column PDFs?”
The answer: not reliably enough to claim (/yet).
MessyData is currently a pasted-text cleanup tool, not a dedicated PDF parser.
“Does it handle multi-column PDFs?”
The answer: not reliably enough to claim (/yet).
MessyData is currently a pasted-text cleanup tool, not a dedicated PDF parser.
July 7, 2026 at 1:53 PM
1/ I got a useful early question about MessyData already making me glad to have started this “build in public” effort:
“Does it handle multi-column PDFs?”
The answer: not reliably enough to claim (/yet).
MessyData is currently a pasted-text cleanup tool, not a dedicated PDF parser.
“Does it handle multi-column PDFs?”
The answer: not reliably enough to claim (/yet).
MessyData is currently a pasted-text cleanup tool, not a dedicated PDF parser.
#DataWrangling #DataPreparation #DataQuality
#MessyData #DataCleaning #DataAnalysis
#BusinessIntelligence #DataDriven #Analytics #DataInsights #DataScience #BigData #MachineLearning #AI #TechForGood #Python
#Pandas #SQL #Excel #ETL #Research #DataForResearch #StrategicInsights #EvidenceBased
#MessyData #DataCleaning #DataAnalysis
#BusinessIntelligence #DataDriven #Analytics #DataInsights #DataScience #BigData #MachineLearning #AI #TechForGood #Python
#Pandas #SQL #Excel #ETL #Research #DataForResearch #StrategicInsights #EvidenceBased
June 10, 2025 at 3:52 PM
Building MessyData has made me appreciate something:
The product isn’t the AI.
The product is everything around the AI.
The prompts, the review step, the expectations you set, the places you deliberately don’t automate.
That’s where trust comes from.
The product isn’t the AI.
The product is everything around the AI.
The prompts, the review step, the expectations you set, the places you deliberately don’t automate.
That’s where trust comes from.
July 14, 2026 at 5:15 PM
Building MessyData has made me appreciate something:
The product isn’t the AI.
The product is everything around the AI.
The prompts, the review step, the expectations you set, the places you deliberately don’t automate.
That’s where trust comes from.
The product isn’t the AI.
The product is everything around the AI.
The prompts, the review step, the expectations you set, the places you deliberately don’t automate.
That’s where trust comes from.
Nice! MessyData is simpler at this stage.
The core stack is: Next.js on Vercel, server-side OpenAI call, no database or agent architecture for the core flow.
Workflow is: pasted text → structured JSON → table → CSV export
So for now it’s more structured parser than autonomous agent.
The core stack is: Next.js on Vercel, server-side OpenAI call, no database or agent architecture for the core flow.
Workflow is: pasted text → structured JSON → table → CSV export
So for now it’s more structured parser than autonomous agent.
July 7, 2026 at 3:14 PM
Nice! MessyData is simpler at this stage.
The core stack is: Next.js on Vercel, server-side OpenAI call, no database or agent architecture for the core flow.
Workflow is: pasted text → structured JSON → table → CSV export
So for now it’s more structured parser than autonomous agent.
The core stack is: Next.js on Vercel, server-side OpenAI call, no database or agent architecture for the core flow.
Workflow is: pasted text → structured JSON → table → CSV export
So for now it’s more structured parser than autonomous agent.
I’ve been reshaping the Lab website so the experiments and the thinking behind them sit together.
MessyData now links directly to the article on why I built it. Over time I’d like the site to become a record of what I built, why, and what happened next.
aiinnovationlab.co.uk
#ai #innovation
MessyData now links directly to the article on why I built it. Over time I’d like the site to become a record of what I built, why, and what happened next.
aiinnovationlab.co.uk
#ai #innovation
AI Innovation Design Lab — A personal AI & software experiment lab
A personal hobby project for exploring AI, software and product ideas by building things out of curiosity and sharing what happens.
aiinnovationlab.co.uk
August 20, 2026 at 12:18 PM
I’ve been reshaping the Lab website so the experiments and the thinking behind them sit together.
MessyData now links directly to the article on why I built it. Over time I’d like the site to become a record of what I built, why, and what happened next.
aiinnovationlab.co.uk
#ai #innovation
MessyData now links directly to the article on why I built it. Over time I’d like the site to become a record of what I built, why, and what happened next.
aiinnovationlab.co.uk
#ai #innovation
A core design choice in MessyData is that it works from pasted text. It doesn’t upload or parse PDFs directly.
Text copied from a PDF may work, but multi-column layouts would probably scramble the reading order.
Curious if future work would benefit from document support.
Text copied from a PDF may work, but multi-column layouts would probably scramble the reading order.
Curious if future work would benefit from document support.
August 26, 2026 at 8:00 PM
A core design choice in MessyData is that it works from pasted text. It doesn’t upload or parse PDFs directly.
Text copied from a PDF may work, but multi-column layouts would probably scramble the reading order.
Curious if future work would benefit from document support.
Text copied from a PDF may work, but multi-column layouts would probably scramble the reading order.
Curious if future work would benefit from document support.
One question behind MessyData is whether a focused tool is useful when a general AI assistant can already structure messy text.
I’m testing whether removing the prompt-writing and wrapping the task in review and export makes the workflow easier.
messydata.app
I’m testing whether removing the prompt-writing and wrapping the task in review and export makes the workflow easier.
messydata.app
MessyData — Convert Messy Data into Clean Tables
Paste messy data from emails, PDFs, websites, documents, spreadsheets, or AI outputs and convert it into a clean structured table. Copy the result or download it as CSV.
messydata.app
August 25, 2026 at 12:38 PM
One question behind MessyData is whether a focused tool is useful when a general AI assistant can already structure messy text.
I’m testing whether removing the prompt-writing and wrapping the task in review and export makes the workflow easier.
messydata.app
I’m testing whether removing the prompt-writing and wrapping the task in review and export makes the workflow easier.
messydata.app
MessyData started with a fairly ordinary frustration: information can make perfect sense to a person while still being awkward to get into a spreadsheet.
That looked like a useful place to test whether AI could help.
I wrote about how that became MessyData:
aiinnovationlab.co.uk/blog/why-i-b...
That looked like a useful place to test whether AI could help.
I wrote about how that became MessyData:
aiinnovationlab.co.uk/blog/why-i-b...
Why I Built MessyData
Why I built MessyData as a focused experiment in using AI to turn awkward, unstructured data into a simpler spreadsheet-ready workflow.
aiinnovationlab.co.uk
August 21, 2026 at 12:06 PM
MessyData started with a fairly ordinary frustration: information can make perfect sense to a person while still being awkward to get into a spreadsheet.
That looked like a useful place to test whether AI could help.
I wrote about how that became MessyData:
aiinnovationlab.co.uk/blog/why-i-b...
That looked like a useful place to test whether AI could help.
I wrote about how that became MessyData:
aiinnovationlab.co.uk/blog/why-i-b...
In this workshop-cost example I posted, one entry was marked “amount pending” and the formatting varied between rows.
MessyData still structured the table, but surfaced those issues for review rather than treating every inferred value as certain.
That's the benefit of AI to infer &/ ask questions.
MessyData still structured the table, but surfaced those issues for review rather than treating every inferred value as certain.
That's the benefit of AI to infer &/ ask questions.
Here is a concrete example of what MessyData does.
This fictional input contains copied expense notes with inconsistent dates, separators and a missing amount.
MessyData turns the pasted text into a table, highlights points to check, and exports it as CSV.
messydata.app
This fictional input contains copied expense notes with inconsistent dates, separators and a missing amount.
MessyData turns the pasted text into a table, highlights points to check, and exports it as CSV.
messydata.app
August 18, 2026 at 10:51 AM
In this workshop-cost example I posted, one entry was marked “amount pending” and the formatting varied between rows.
MessyData still structured the table, but surfaced those issues for review rather than treating every inferred value as certain.
That's the benefit of AI to infer &/ ask questions.
MessyData still structured the table, but surfaced those issues for review rather than treating every inferred value as certain.
That's the benefit of AI to infer &/ ask questions.
Getting MessyData working answered a technical question: can AI turn awkward pasted text into a useful table?
What it hasn't answered is whether enough people have that problem, or whether the workflow is useful enough to keep developing.
That is what I'm curious to learn next.
#ai #innovation
What it hasn't answered is whether enough people have that problem, or whether the workflow is useful enough to keep developing.
That is what I'm curious to learn next.
#ai #innovation
August 17, 2026 at 1:36 PM
Getting MessyData working answered a technical question: can AI turn awkward pasted text into a useful table?
What it hasn't answered is whether enough people have that problem, or whether the workflow is useful enough to keep developing.
That is what I'm curious to learn next.
#ai #innovation
What it hasn't answered is whether enough people have that problem, or whether the workflow is useful enough to keep developing.
That is what I'm curious to learn next.
#ai #innovation
I’ve enjoyed building MessyData by keeping the core workflow simple.
Paste messy input, make a server-side AI call, return structured data, review, then export.
No need for a database.
It’s been useful seeing how much can be built around a fairly small bit of AI functionality.
Paste messy input, make a server-side AI call, return structured data, review, then export.
No need for a database.
It’s been useful seeing how much can be built around a fairly small bit of AI functionality.
Col Nathan R Jessep: It's That Simple
ALT: Col Nathan R Jessep: It's That Simple
static.klipy.com
August 11, 2026 at 4:11 PM
I’ve enjoyed building MessyData by keeping the core workflow simple.
Paste messy input, make a server-side AI call, return structured data, review, then export.
No need for a database.
It’s been useful seeing how much can be built around a fairly small bit of AI functionality.
Paste messy input, make a server-side AI call, return structured data, review, then export.
No need for a database.
It’s been useful seeing how much can be built around a fairly small bit of AI functionality.
MessyData is featured on Uneed today.
I submitted it as a small experiment in getting something I’ve built out to places where people might discover it.
I’m curious whether directories like this generate any useful feedback.
www.uneed.best/tool/messy-d...
I submitted it as a small experiment in getting something I’ve built out to places where people might discover it.
I’m curious whether directories like this generate any useful feedback.
www.uneed.best/tool/messy-d...
Discover MessyData on Uneed
Discover MessyData on Uneed - Turn messy data into a clean formatted table in seconds. | AI in Development (Freemium)
www.uneed.best
August 7, 2026 at 8:57 AM
MessyData is featured on Uneed today.
I submitted it as a small experiment in getting something I’ve built out to places where people might discover it.
I’m curious whether directories like this generate any useful feedback.
www.uneed.best/tool/messy-d...
I submitted it as a small experiment in getting something I’ve built out to places where people might discover it.
I’m curious whether directories like this generate any useful feedback.
www.uneed.best/tool/messy-d...
A hard part of MessyData is defining when not to trust the AI interpretation.
It works best with repeated patterns, not long prose or unrelated notes, so review, warnings and safe-use limits are part of the product.
It quickly becomes a fuzzy boundary though!
It works best with repeated patterns, not long prose or unrelated notes, so review, warnings and safe-use limits are part of the product.
It quickly becomes a fuzzy boundary though!
August 4, 2026 at 9:50 AM
A hard part of MessyData is defining when not to trust the AI interpretation.
It works best with repeated patterns, not long prose or unrelated notes, so review, warnings and safe-use limits are part of the product.
It quickly becomes a fuzzy boundary though!
It works best with repeated patterns, not long prose or unrelated notes, so review, warnings and safe-use limits are part of the product.
It quickly becomes a fuzzy boundary though!
Here is a concrete example of what MessyData does.
This fictional input contains copied expense notes with inconsistent dates, separators and a missing amount.
MessyData turns the pasted text into a table, highlights points to check, and exports it as CSV.
messydata.app
This fictional input contains copied expense notes with inconsistent dates, separators and a missing amount.
MessyData turns the pasted text into a table, highlights points to check, and exports it as CSV.
messydata.app
July 26, 2026 at 1:35 PM
Here is a concrete example of what MessyData does.
This fictional input contains copied expense notes with inconsistent dates, separators and a missing amount.
MessyData turns the pasted text into a table, highlights points to check, and exports it as CSV.
messydata.app
This fictional input contains copied expense notes with inconsistent dates, separators and a missing amount.
MessyData turns the pasted text into a table, highlights points to check, and exports it as CSV.
messydata.app
MessyData : Transform messy data into clean, structured tables instantly with MessyData's AI assistance. Messy Data Cleaner helps teams ship faster with modern tools
pitchwall.co/product/mess...
pitchwall.co/product/mess...
MessyData
Transform messy data into clean, structured tables instantly with MessyData's AI assistance. Messy Data Cleaner helps teams ship faster with modern tools
pitchwall.co
July 20, 2026 at 1:00 PM
MessyData : Transform messy data into clean, structured tables instantly with MessyData's AI assistance. Messy Data Cleaner helps teams ship faster with modern tools
pitchwall.co/product/mess...
pitchwall.co/product/mess...
One thing building MessyData has taught me:
The first version of a product isn’t just there to validate the idea.
It’s there to teach you how to explain it.
The questions people ask often reveal more than the features they request.
The first version of a product isn’t just there to validate the idea.
It’s there to teach you how to explain it.
The questions people ask often reveal more than the features they request.
July 17, 2026 at 8:32 AM
One thing building MessyData has taught me:
The first version of a product isn’t just there to validate the idea.
It’s there to teach you how to explain it.
The questions people ask often reveal more than the features they request.
The first version of a product isn’t just there to validate the idea.
It’s there to teach you how to explain it.
The questions people ask often reveal more than the features they request.
The best feedback I’ve had building MessyData has been the questions I’ve received:
“Does it handle PDFs?”
“What’s the tech stack?”
“Why not agents?”
Good questions expose assumptions you didn’t realise you made.
Addressing confusion can be more valuable than adding features.
“Does it handle PDFs?”
“What’s the tech stack?”
“Why not agents?”
Good questions expose assumptions you didn’t realise you made.
Addressing confusion can be more valuable than adding features.
July 16, 2026 at 8:13 AM
The best feedback I’ve had building MessyData has been the questions I’ve received:
“Does it handle PDFs?”
“What’s the tech stack?”
“Why not agents?”
Good questions expose assumptions you didn’t realise you made.
Addressing confusion can be more valuable than adding features.
“Does it handle PDFs?”
“What’s the tech stack?”
“Why not agents?”
Good questions expose assumptions you didn’t realise you made.
Addressing confusion can be more valuable than adding features.