AI agent payments have produced four competing specifications, two industry foundations and an enormous amount of coverage in about a year. What they have not yet produced, for the overwhelming majority of merchants, is revenue. The gap between the noise and the numbers is the useful part to understand, because the...
AI Integration
Articles, guides and tutorials on integrating AI into software products, covering APIs, language models and practical AI implementation strategies.
Most teams call a model provider straight from application code. The API key sits in an environment variable, the SDK call is three lines, and it works first time. Cloudflare AI Gateway exists because of what happens next. The bill arrives and nobody can say which feature caused it. The provider has a bad afternoon and...
Agentforce is priced by consumption, and that single fact should change how you budget for it. Most Salesforce buyers arrive with a seat-licence mental model, ask what an agent costs per user per month, and get a number that does not describe their bill. The bill is a function of how many actions the agent takes, and...
WordPress 7.0 shipped on 20 May 2026 under the release name Armstrong, six weeks later than the date on the original 2026 schedule, and it is the most consequential core release for agencies since the block editor. The headline is that core can now talk to generative AI models. The detail that matters more is that core...
Drupal AI has stopped being a scatter of provider-specific contributed modules that whoever needed them bolted on separately. It is now one coordinated project with an abstraction layer underneath it, a security-team-covered release cycle, and a packaged product in Drupal CMS that offers to switch parts of it on during...
AI agents for business are the current version of a familiar story: a demo that works beautifully in ten minutes, followed by six months of trying to make it work reliably enough to leave unattended. The gap between those two states is where almost all the budget goes, and almost none of the marketing material...
The fine-tuning vs RAG question usually arrives as a statement: “we need to fine-tune a model on our data.” It is one of the most expensive sentences in enterprise AI, and it is usually wrong. Not always, but usually. The request nearly always means one of two things: the model does not know about our business, or the...
The case for moving off OpenAI got considerably stronger during 2026. Open-weight models reached a level where the quality gap on ordinary production work became narrow, published pricing undercut the frontier providers, and the weights themselves became downloadable, which turns a supplier relationship into an option....
Self-hosting Kimi K3 became technically possible on 27 July 2026, when Moonshot AI published the weights for a 2.8-trillion-parameter model alongside production inference support. A great many organisations read that news and concluded they could now run frontier-class reasoning on their own hardware and stop paying...
The Kimi K3 API arrived with an unusual combination behind it: frontier-adjacent benchmark results, aggressive pricing, and downloadable weights. Moonshot AI published those weights on 27 July 2026, which makes K3 the largest openly available model released so far and the first time a model at this scale has been...