AI Innovation Design Lab
@aidesignlab.bsky.social
Personal hobby project exploring AI, software and product ideas by building things and learning along the way.
Current experiment: MessyData.app
aiinnovationlab.co.uk
Current experiment: MessyData.app
aiinnovationlab.co.uk
Pinned
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.
RenewalCheck started because I was going through my own insurance renewal and thought a small tool might help me check the documents.
Prototyping it made the privacy and trust questions obvious, without evidence the idea was worth pushing further.
So I stopped.
aiinnovationlab.co.uk/experiments
Prototyping it made the privacy and trust questions obvious, without evidence the idea was worth pushing further.
So I stopped.
aiinnovationlab.co.uk/experiments
Experiments — AI Innovation Design Lab
Live, paused and concluded software experiments from AI Innovation Design Lab, showing what I built and what happened when I built it.
aiinnovationlab.co.uk
September 15, 2026 at 11:34 AM
RenewalCheck started because I was going through my own insurance renewal and thought a small tool might help me check the documents.
Prototyping it made the privacy and trust questions obvious, without evidence the idea was worth pushing further.
So I stopped.
aiinnovationlab.co.uk/experiments
Prototyping it made the privacy and trust questions obvious, without evidence the idea was worth pushing further.
So I stopped.
aiinnovationlab.co.uk/experiments
I’ve been making the Lab website a better record of the experiments themselves.
I’ve now included live, paused and concluded projects, with a short note on what each one produced or why I stopped.
I think the dead ends are worth keeping visible too.
aiinnovationlab.co.uk/experiments
I’ve now included live, paused and concluded projects, with a short note on what each one produced or why I stopped.
I think the dead ends are worth keeping visible too.
aiinnovationlab.co.uk/experiments
Experiments — AI Innovation Design Lab
Live, paused and concluded software experiments from AI Innovation Design Lab, showing what I built and what happened when I built it.
aiinnovationlab.co.uk
September 11, 2026 at 11:50 AM
I’ve been making the Lab website a better record of the experiments themselves.
I’ve now included live, paused and concluded projects, with a short note on what each one produced or why I stopped.
I think the dead ends are worth keeping visible too.
aiinnovationlab.co.uk/experiments
I’ve now included live, paused and concluded projects, with a short note on what each one produced or why I stopped.
I think the dead ends are worth keeping visible too.
aiinnovationlab.co.uk/experiments
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...
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
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
AI is making it easier to turn an idea into working software. For me, that puts more weight on deciding what is worth building and what the evidence supports.
That is why I started the Lab.
👉 aiinnovationlab.co.uk/blog/why-i-s...
#aiinnovation #buildinpublic #ai #productdevelopment
That is why I started the Lab.
👉 aiinnovationlab.co.uk/blog/why-i-s...
#aiinnovation #buildinpublic #ai #productdevelopment
Why I Started the AI Innovation Design Lab
Why I created the AI Innovation Design Lab as a place to explore AI-enabled product leadership by combining product thinking, scientific rigour, business judgement and disciplined delivery.
aiinnovationlab.co.uk
August 14, 2026 at 12:40 PM
AI is making it easier to turn an idea into working software. For me, that puts more weight on deciding what is worth building and what the evidence supports.
That is why I started the Lab.
👉 aiinnovationlab.co.uk/blog/why-i-s...
#aiinnovation #buildinpublic #ai #productdevelopment
That is why I started the Lab.
👉 aiinnovationlab.co.uk/blog/why-i-s...
#aiinnovation #buildinpublic #ai #productdevelopment
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
A prototype doesn’t always need to prove an idea will work.
Sometimes it just needs to answer the next question.
- Will people understand it?
- Can it actually be built?
- Is the problem worth solving?
Build enough to learn something, then decide what comes next on the path to success.
Sometimes it just needs to answer the next question.
- Will people understand it?
- Can it actually be built?
- Is the problem worth solving?
Build enough to learn something, then decide what comes next on the path to success.
July 20, 2026 at 9:40 AM
A prototype doesn’t always need to prove an idea will work.
Sometimes it just needs to answer the next question.
- Will people understand it?
- Can it actually be built?
- Is the problem worth solving?
Build enough to learn something, then decide what comes next on the path to success.
Sometimes it just needs to answer the next question.
- Will people understand it?
- Can it actually be built?
- Is the problem worth solving?
Build enough to learn something, then decide what comes next on the path to success.
Building small software experiments means not every idea needs a huge commitment.
Just build enough to make it real. Put it in front of people. And learn what happens next.
Some ideas grow, some change direction, and some stop.
All three outcomes teach you something.
Just build enough to make it real. Put it in front of people. And learn what happens next.
Some ideas grow, some change direction, and some stop.
All three outcomes teach you something.
July 19, 2026 at 8:34 AM
Building small software experiments means not every idea needs a huge commitment.
Just build enough to make it real. Put it in front of people. And learn what happens next.
Some ideas grow, some change direction, and some stop.
All three outcomes teach you something.
Just build enough to make it real. Put it in front of people. And learn what happens next.
Some ideas grow, some change direction, and some stop.
All three outcomes teach you something.
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.
One thing I enjoy about building small AI products is discovering where not to add complexity.
The first version of MessyData is deliberately simple.
Every feature has to earn its place.
I think that’s easier to improve than starting with something clever but hard to understand.
The first version of MessyData is deliberately simple.
Every feature has to earn its place.
I think that’s easier to improve than starting with something clever but hard to understand.
July 15, 2026 at 8:45 AM
One thing I enjoy about building small AI products is discovering where not to add complexity.
The first version of MessyData is deliberately simple.
Every feature has to earn its place.
I think that’s easier to improve than starting with something clever but hard to understand.
The first version of MessyData is deliberately simple.
Every feature has to earn its place.
I think that’s easier to improve than starting with something clever but hard to understand.
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.
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.
1/ A closer look at the first live tool from AI Innovation Design Lab: MessyData.
The problem is simple:
Useful data often starts messy.
Copied from websites, PDFs, emails, notes, spreadsheets, reports, or internal systems.
The problem is simple:
Useful data often starts messy.
Copied from websites, PDFs, emails, notes, spreadsheets, reports, or internal systems.
July 6, 2026 at 7:41 AM
1/ A closer look at the first live tool from AI Innovation Design Lab: MessyData.
The problem is simple:
Useful data often starts messy.
Copied from websites, PDFs, emails, notes, spreadsheets, reports, or internal systems.
The problem is simple:
Useful data often starts messy.
Copied from websites, PDFs, emails, notes, spreadsheets, reports, or internal systems.
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.