Posts by AIAppsAPI
@AIAppsAPI
Paul Crinigan
AI Agents, Tools And How To Make Sense Of It All
Posts by AIAppsAPI
Most of us here have written a scraper or an automated test that ran clean for a week and then started drowning in challenges out of nowhere. This is the part of that story that took me the longest to understand, so I am writing it down for anyone wh...
Most of us here have built a chatbot at some point, and going from text to voice looks like it should just be two more API calls, one on each end. It is not, and the reason is a single latency number that reorganizes the whole pipeline.
A voice agen...
Most of us here have shipped something that calls a model and then spends half its code cleaning up whatever came back. This is the writeup I wish I had the first time I wired an LLM into a real pipeline, so I am leaving it here for anyone about to d...
A lot of the agent questions on here come down to the same one: which framework should I start with, and how badly will I regret it in six months. This is the order I make that call in, and where the regret usually comes from.
Language Comes First
...
Most of us here treat deletion as a database problem: the row goes away and the job is done. Digital forensics has spent thirty years demonstrating that the row is only one of the places that data lives, and I think the field has a lot to teach anyon...
Most of us pick a gateway on API quality and docs, which is fair, that is the part we live in. The fee side usually gets treated as a business problem until someone asks why the numbers stopped working at scale, so here is the short version of how th...
A lot of the web game questions that land on here come down to picking a library before working out what kind of problem you actually have. This one catches people often enough that it is worth writing down for anyone about to start a browser game.
...
Most of us debug things that ride on electromagnetic waves all day without ever looking at the physics underneath. This is the short version, written for developers, of why radio, WiFi and visible light are literally the same phenomenon.
One Force, ...
Most of us here have shipped something that ran perfectly on a laptop and then came apart the first week it met real traffic. Agents have the same problem with a fresher coat of paint, so this is a look at what actually separates a working demo from ...
Most of us here debug for a living, and the habit that has helped me the most did not come out of software at all, it came out of lab method. The overlap is closer than it looks, so it seemed worth writing up for this crowd.
Change One Thing, Then L...
Most of the prompt discussion I see around here is about wording, so I want to share the part that actually changed my results, which is the measurement around the prompt. If you are shipping anything LLM backed, this is the piece that saves you from...
Most of us here build tools rather than buy them, but plenty of you also ship for small business clients who ask which AI tools are worth paying for. This is the filter I keep coming back to when that question lands.
The AI capabilities that are gen...
Most of us have written a one off parser for somebody else's ugly export format, and most of us have written the same parser twice. I want to lay out a pattern that made that problem go away for me, because it generalises well past the specific case ...
Most of us here have shipped something that works beautifully while we sit and watch it run. This is about what changes the first night it runs on a schedule with nobody watching, because that is where the surprises actually live. Our guide to AI aut...
Most of the wasm material floating around is about the toolchain: install Emscripten, pass these flags, ship the .wasm. The decision that comes before it gets far less attention, and for this crowd it is the more interesting one, so here is the versi...
Most of us here have either built a text-to-SQL layer or been asked to. The demos always look great and the production version is the one that quietly returns the wrong number, so here is what actually separates the two.
The Schema Is The Feature, N...
Most of us here have shipped something on an agent framework in the last year, and a fair number of those frameworks have already changed names or maintainers. This is a look at the parts of Microsoft's AutoGen that were worth keeping, written for an...
Most of us here write software for products, but a surprising amount of the same work happens in labs and research groups, written by people who were never taught to write code. If you have ever inherited a research script and wondered why it does wh...
Most of us end up speccing a box for local models because an API bill or a privacy requirement made the decision for us, not because we wanted a hardware project. This is the sizing math I keep coming back to, aimed at developers who want a working s...
chevron_left