[{"data":1,"prerenderedAt":202},["ShallowReactive",2],{"notes":3,"profile":45,"note-when-software-becomes-an-actor":200},[4,13,21,28,34,40],{"slug":5,"title":6,"topic":7,"status":8,"published":9,"summary":10,"minutes":11,"href":12},"developer-tools-for-normal-teams","Developer tools for normal teams","AI","published","2026-09-24","Every team using AI is about to hit problems software teams solved years ago. The fix is the same four tools, in plainer clothes.",4,"\u002Fnotes\u002Fdeveloper-tools-for-normal-teams",{"slug":14,"title":15,"topic":16,"status":8,"published":17,"updated":9,"summary":18,"minutes":19,"href":20},"ai-makes-software-cheaper","AI makes software cheaper. Systems thinking becomes more valuable.","Software","2026-09-23","Models make code cheap to write. They don’t make systems cheap to own, and that gap is where the valuable work moves.",2,"\u002Fnotes\u002Fai-makes-software-cheaper",{"slug":22,"title":23,"topic":24,"status":8,"published":17,"updated":9,"summary":25,"minutes":26,"href":27},"jev-tiny-models-strange-interfaces","JEV, tiny models and strange new interfaces","Experiments","Small, fast models that pick one option from a fixed set don’t chat. They decide, and that invites interfaces that don’t look like chat at all.",1,"\u002Fnotes\u002Fjev-tiny-models-strange-interfaces",{"slug":29,"title":30,"topic":7,"status":8,"published":17,"summary":31,"minutes":32,"href":33},"what-i-learned-giving-agents-memory","What I learned giving agents memory","Memory is not a transcript. On selection, lifetimes, forgetting and what persistent agents change about software.",6,"\u002Fnotes\u002Fwhat-i-learned-giving-agents-memory",{"slug":35,"title":36,"topic":37,"status":8,"published":17,"updated":9,"summary":38,"minutes":19,"href":39},"when-software-becomes-an-actor","What finance looks like when software becomes an actor","Finance","When software can act on money, not just record it, the hard questions stop being technical and become about permission and accountability.","\u002Fnotes\u002Fwhen-software-becomes-an-actor",{"slug":41,"title":42,"topic":16,"status":8,"published":17,"updated":9,"summary":43,"minutes":19,"href":44},"why-i-still-prototype-things-myself","Why I still prototype things myself","Building the first version myself is still the fastest way I know to find out what a product should be, and where it will break.","\u002Fnotes\u002Fwhy-i-still-prototype-things-myself",{"name":46,"meta":47,"statement":48,"lede":51,"description":52,"readout":53,"current":69,"work":113,"trajectory":145,"notes":171,"about":174,"contact":184},"Chris Wijnia","Engineer · Founder · Bali \u002F 2026",{"text":49,"accent":50},"I build software and companies.","companies.","I’m a Dutch engineer and co-founder of Agio Digital. Since the early 2000s I’ve designed, built and shipped products across the web, financial technology and whatever came next.","Dutch engineer and co-founder of Agio Digital. I design, build and ship products across the web, financial technology and AI.",[54,57,60,63,66],{"label":55,"value":56},"Base","Bali",{"label":58,"value":59},"Origin","Netherlands",{"label":61,"value":62},"Current","Agio Digital",{"label":64,"value":65},"Work","Software \u002F Finance \u002F AI",{"label":67,"value":68},"Status","Building",{"title":70,"accent":71,"records":72},"What I’m working on.","working on.",[73,88,102],{"id":74,"label":75,"headline":76,"accent":77,"paragraphs":78,"facets":81,"period":87},"agio","01 \u002F Agio Digital","Building financial software.","financial software.",[79,80],"I co-founded Agio Digital, where I’m Chief Innovation Officer.","I work across product, engineering and R&D, from financial infrastructure and digital assets to automation and AI. I still write code and stay close to the systems we ship.",[82,83,84,85,86],"Financial software","Digital assets","Product","Engineering","R&D","2019–Now",{"id":89,"label":90,"headline":91,"accent":92,"paragraphs":93,"facets":96,"period":101},"ai","02 \u002F AI & software","Finding useful things to do with new models.","new models.",[94,95],"I spend a lot of time on agents, developer tools, automation and new ways of building software.","I’m less interested in demos than in what holds up once real users, existing systems and messy constraints get involved.",[97,98,99,100],"Agents","Developer tools","Automation","Applied AI","2024–Now",{"id":103,"label":104,"headline":105,"accent":106,"paragraphs":107,"facets":110,"period":112},"independent","03 \u002F Independent work","Building things to see where they go.","where they go.",[108,109],"Small software projects, open-source work, trading systems, strange interfaces and ideas that start as a repository before they have a business case.","Some become useful. Some answer a question. That’s enough.",[16,111,24],"Open source","Ongoing",{"title":114,"accent":115,"outro":116,"projects":117},"A few things I’ve worked on.","worked on.","The work has changed a lot over the years. The habit of making things hasn’t.",[118,122,127,133,139],{"no":119,"name":62,"area":120,"period":87,"slug":121},"01","Financial software \u002F Digital assets","agio-digital",{"no":123,"name":124,"area":125,"period":101,"slug":126},"02","AI systems","Agents \u002F Automation \u002F Developer tools","ai-systems",{"no":128,"name":129,"area":130,"period":131,"slug":132},"03","1GRAM","Blockchain \u002F Wallet infrastructure","2018","1gram",{"no":134,"name":135,"area":136,"period":137,"slug":138},"04","MVRDV","Digital platform \u002F Team Foster","2016","mvrdv",{"no":140,"name":141,"area":142,"period":143,"slug":144},"05","Archive","Products \u002F Websites \u002F Design \u002F Software","2005–2023","archive",{"title":146,"accent":147,"eras":148},"Moving down the stack as the web evolved.","evolved.",[149,153,155,157,160,164,167],{"year":150,"name":151,"line":152},"2000s","Design","Learning the web by making things.",{"name":84,"line":154},"Design became code.",{"name":85,"line":156},"Code became systems.",{"year":131,"name":158,"line":159},"Crypto","Programmable ownership and money.",{"year":161,"name":162,"line":163},"2019","Financial infra","Building systems where software meets regulation.",{"year":165,"name":7,"line":166},"2024","Software that increasingly builds and operates software.",{"year":168,"name":169,"line":170},"Now","Convergence","What happens when these things converge?",{"title":172,"intro":173},"Notes","Things I’m working on, learning or trying to understand.",{"title":175,"accent":176,"paragraphs":177},"I’ve been making things on computers for most of my life.","life.",[178,179,180,181,182,183],"I grew up in the Netherlands and started building for the web as a teenager.","I began as a designer. Design pulled me into frontend development, then engineering, product architecture and eventually company-building.","Over the years I’ve worked on websites, consumer products, blockchain infrastructure, financial systems and now AI. I don’t draw hard lines between design, engineering and product. They’re different ways of looking at the same problem.","At Agio Digital I spend most of my time building, prototyping, reviewing systems and figuring out what we should do next.","I like small teams, ambitious projects, good engineering and people who can disagree without making it tedious. I still enjoy opening an empty repository and figuring something out.","I’m based in Bali and work internationally. Outside work I train Muay Thai, like [chess](\u002Fexperiments\u002Fchess960), and build things that occasionally have no sensible commercial purpose.",{"title":185,"accent":186,"intro":187,"links":188},"Making something interesting?","interesting?","For companies, collaborations, technical discussions, speaking, new ventures, or a good reason I haven’t thought of.",[189,191,194,197],{"label":190},"Email",{"label":192,"href":193},"LinkedIn","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fchris-wijnia-1364a29b",{"label":195,"href":196},"GitHub","https:\u002F\u002Fgithub.com\u002Fcwdx",{"label":198,"href":199},"X","https:\u002F\u002Fx.com\u002FChrisWijnia",{"slug":35,"title":36,"topic":37,"status":8,"published":17,"updated":9,"summary":38,"minutes":19,"href":39,"html":201},"\u003Cp>For most of its history, financial software has been a ledger with a user interface. It records what people decided. Someone approves the payment, someone places the trade, and the software keeps track.\u003C\u002Fp>\n\u003Cp>That’s changing. Software can now propose, decide and act: move funds when conditions are met, rebalance a portfolio, respond to a request at three in the morning. The question is no longer only whether the numbers are right. It’s who, or what, was allowed to act.\u003C\u002Fp>\n\u003Ch2 data-no=\"01 \u002F 04\">From records to decisions\u003C\u002Fh2>\n\u003Cp>Programmable money made the first step possible. Assets that can be held and moved by code mean the rules can live next to the value instead of in a separate process. Models add the second step: software that can read a situation and choose an action within those rules.\u003C\u002Fp>\n\u003Cp>Put together, you get an actor. Not a person, not a tool, but something in between that holds permissions and uses them.\u003C\u002Fp>\n\u003Ch2 data-no=\"02 \u002F 04\">Permission is the product\u003C\u002Fh2>\n\u003Cp>When software acts, the interesting design problem is the permission model:\u003C\u002Fp>\n\u003Cul>\n\u003Cli>\u003Cstrong>Scope.\u003C\u002Fstrong> What exactly may it do, with how much, and for how long?\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Limits.\u003C\u002Fstrong> Hard caps that no instruction can override, enforced where the money lives, not in the prompt.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Approval.\u003C\u002Fstrong> Which actions need a human, and how that human sees enough context to say yes quickly and safely.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Undo.\u003C\u002Fstrong> Money often can’t be pulled back, so the checks have to happen before the action, not after.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp>Good financial infrastructure already thinks this way about people. Delegated access, spending limits and multi-party approval are old ideas. The new part is applying them to something that acts at machine speed and never gets tired.\u003C\u002Fp>\n\u003Ch2 data-no=\"03 \u002F 04\">Accountability doesn’t move\u003C\u002Fh2>\n\u003Cp>Regulation doesn’t care whether a person or a program made the call. Someone is still responsible. That’s healthy: it forces clear lines between what the software proposes and what an accountable party authorises.\u003C\u002Fp>\n\u003Cp>The systems that work will make those lines visible. Every action traced to a permission, every permission traced to a person, and a log you could show an auditor without rewriting it first.\u003C\u002Fp>\n\u003Ch2 data-no=\"04 \u002F 04\">Open questions\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>How much autonomy will customers actually want over their own money, once it’s on offer?\u003C\u002Fli>\n\u003Cli>What does a useful audit trail look like for a decision made by a model?\u003C\u002Fli>\n\u003Cli>Where should limits live: in the model, the application, or the asset itself?\u003C\u002Fli>\n\u003C\u002Ful>\n",1790298605806]