002: What has shipped so far

Thu, 12 Nov 2026 09:00:00 +1000

The first entry promised a dated record of what I tried, what broke and what I changed my mind about. This is the first instalment. It covers the two products that have shipped, Fig and Codeword, and I should say at the start that they aren’t the only things I’ve been building, only the ones that are public.

Fig is the older of the two. It’s an app for reviewing calls handled by AI agents, with the recording, the transcript and the context together in one place. The ideas behind it had been sitting at the back of my mind for years without going anywhere. What opened the door was ElevenLabs, a company that makes AI voice technology. I was looking at what they offered, the APIs in particular, which are the hooks other software builds on, and noticing what was available now. It was a small crack, and one thing led to another.

I started on 15 August 2026 under the working name ElevenLabs Call Explorer and renamed it Fig the same day, because I didn’t want the product tied to one provider, and because a name like Fig can mean whatever I want it to mean. It went live on Apple’s App Store on 8 November, twelve weeks later, and that number needs some context, because it wasn’t twelve weeks of Fig.

A working version was in TestFlight, Apple’s channel for trying an app before release, eight days after I started. After that the time was shared with a day job, which comes first because I have to make a living, and with several other projects that are still in flight. I think most of my free time went into all of this, which meant late nights, early mornings and a large part of the weekends.

I’m spelling this out because I’m sceptical of stories that make this kind of thing sound easy, and just as sceptical of ones that dress it up as hardship. When I was younger I believed most of what I was told, the way you do when you’re young and willing to chase anything, and some of it sent me down the wrong path and cost me a lot of time. A lot of those stories were maybe ten per cent truth and the rest sugar-coating. They give people false hope, and I don’t want to do the same to anyone reading this.

Fig’s share of that time went into the distance between something that works and something I’d put my name on: rebuilding it properly, letting people delete their account and download a copy of their data, encrypting the recordings, and going through Apple’s review more than once. It took way longer than I expected, and longer than it should have, partly because I don’t have all the processes in place yet.

Privacy took a good part of it. Fig holds recordings of real calls, so I spent quite a bit of time on how to protect that data, on the technical side and on the privacy policy itself. There were two aims. One was to handle people’s data with as much care as I can. The other was to protect myself, because if I fail them I’ve failed myself too, and it looks bad for me. I also wanted the policy to be useful to the person reading it and not something written to tick a box, so a lot of time went into simplifying the language, with no obfuscation and no coded wording, so that no one gets left out. The testing back and forth took time as well.

I don’t want to give the impression that Fig has got there. Putting my name on it is the standard I try to hold to, and I don’t believe Fig meets it yet. This version is the best I could do for this iteration, and there is plenty left to do. That is why IronLab is called a lab. A lab doesn’t claim to be perfect, it’s a place where you experiment and try things, and the work carries on from one iteration to the next. I think of all of it as an investment that I hope pays off one day.

The Android version is pretty much ready. What’s left is the deployment, and by the time you read this it is probably already available, so have a look at the Fig site at fig.ironlab.ai.

Codeword started very differently. I follow a lot of content creators on Instagram, and they often say “link in bio”. You go to the link in their profile and it points to their website, or to something else, and then you’re searching for the exact video they were talking about. It wastes time, and I’d known about the problem for a long time. The last time it happened I wasn’t in the best of moods, and when it irritated me again I thought, let’s try and solve it. It wasn’t a big project, so I thought I’d try to get it done.

I started on 21 October. Codeword lives at codeword.link and does one thing: you type the code from a creator’s post and land on exactly what they shared. It’s live, it’s free and you can use it straight away. Opening a code needs no account, and a creator can make their own page. I just haven’t done the marketing for it. The only thing to know is that I don’t scale it automatically, because it’s free, so if it ever fills the infrastructure it runs on, new people go on a waitlist while I decide whether to add more.

So one of them came from years of thinking and a trigger, and the other from a small annoyance that repeated often enough.

Nothing has surprised me since either of them went live, and the reason is simple: there are no customers using them yet.

What broke is easier to answer. I build these with AI doing most of the hands-on work. The main one is Claude, made by Anthropic, which did the majority of it. To give credit where it’s due, there were times I turned to Codex and ChatGPT, both from OpenAI, and to Grok, from xAI. I see no reason to hide any of that. If AI did most of the work, the honest thing is to say that AI did most of the work. The thing that disappointed me with Claude was regression, which is when something that was working stops working after a later change. It happened continuously, and it happened despite having tests in place. A lot of what failed was very basic, the kind of thing that doesn’t need extensive testing or great engineering skill to get right. That surprised me, because Claude did some amazing and sophisticated work on these projects, and then on rudimentary things it failed again and again. My frustration comes from that disconnect: something so powerful, able to pull off amazing things, failing at very simple tasks. It didn’t make sense to me.

The clearest example is navigation in the iOS app, which is about as simple as an app gets. It kept failing when it shouldn’t have. It would get fixed and then fail again, or get fixed in one place and fail somewhere else, sometimes in two or three places at once.

The question I kept asking is what I can do so this doesn’t happen again: what process, what prompt, what skill. I wasn’t particularly worried about navigation itself. I was thinking about it as a system, because whatever lets this happen in one place will let it happen in others, and I wanted to solve it at that level. I don’t have it ironed out. The AI has been helpful with that in some areas and not so helpful in others. I don’t think it gets fixed in one hit. It’s going to take continuous analysis and retrospectives, fixing the processes we have, defining new ones and building new tools and skills, and working it out as we go.

As for what I’d do differently, I can’t answer that honestly yet, because it depends on what comes out of analysing everything that’s been done so far. That analysis has started.

001: Why I'm writing this down

Wed, 11 Nov 2026 09:00:00 +1000

I’ve been more excited about technology four times in my life.

The first was finding out computers existed. The second was the day one came home. I was not a good student for most of my schooling, not for lack of ability, I just wasn’t one, and my parents set two conditions. I had to do exceptionally well in the national exam, and I had to choose between a full printed set of Encyclopaedia Britannica and a family computer. I wanted the Britannica badly. A salesman had done his job on me, and I read far more then than I do now. I got the highest available grade in every subject, and I still don’t know whether that was because of the computer or a combination of things. But the choice itself was never a choice. It was an Intel 286 desktop PC, a beige box under a CRT monitor with one megabyte of RAM, which is a few thousand times less than the phone in your pocket. It wasn’t close.

The third was reading about the internet in the Straits Times, Singapore’s main newspaper, which arrived at our apartment in Brunei along with the local one. It ran recurring pieces on what the internet was and what you could do with it, and I read them almost every day for years before I could touch it. For a while it also carried a column by Bill Gates answering readers’ questions. In one of them he said that anyone who could get through Donald Knuth’s The Art of Computer Programming should send him a résumé. I didn’t know who Knuth was, but I remembered the name. I knew what the internet was long before I knew what it felt like.

The fourth was finally getting online, in New Zealand, on a dial-up account I split with a schoolmate across the road. Neither of our parents knew what the internet was. Only one of us could be connected at a time, so logging in kicked the other off, and so did my mum picking up the phone.

Then for a long time nothing came close. There were interesting things and useful things, a whole career’s worth of them, but not that feeling. This is the fifth.

I didn’t have to make myself learn about AI. I couldn’t stop. That’s the honest version of why I’ve spent the last stretch of time going as deep as I can, into training runs and model internals and the maths I skipped the first time round, knowing full well that absorbing all of it is impossible and that making the effort anyway is a different thing from absorbing it.

There’s a second reason, and I’d rather name it than pretend it isn’t there. I’ve always wanted to build something of my own that’s worth paying for. That hasn’t gone away, and it never does. The pull toward the technology and the pull toward making something out of it are two separate things that feed each other, and neither is the real one.

Looking back at that first choice, I think I was already picking the thing you make answers with over the thing that contains them. I’m making the same choice now. So that’s what I’m doing: building things with this technology, and writing down what happens.

I want to be clear about what this isn’t. It isn’t a success story, because there isn’t one yet. I’m not going to tell you what I’ve learnt about building AI products, because so far I’ve mostly learnt what doesn’t work, and not enough of it to be useful. What I can do is keep a dated record of what I tried, what broke and what I changed my mind about, and let it accumulate into something.

Everything here will have a date on it, because what I think today is not what I’ll think in a year. When I change my mind I’ll say so, in the open, next to the thing I used to think. Let’s see what happens.

Rasel Jabbar

002: What has shipped so far

001: Why I'm writing this down