AI and machine learning
Training, fine-tuning, retrieval, agents — and knowing when not to.
Four to sixteen weeks.
Put AI into a product without it being a gimmick
Start from a task the feature has to do, and a definition of wrong. Retrieval over your own content with a citation trail, so an answer can be checked. Guardrails, fallbacks and a measured cost per request. Where a model is not the right tool, we say so.
The problem
Everyone wants an assistant in the product, and most of them are a chat box bolted to a landing page that answers questions wrong with total confidence.
How we approach it
Start from a task the feature has to do, and a definition of wrong. Retrieval over your own content with a citation trail, so an answer can be checked. Guardrails, fallbacks and a measured cost per request. Where a model is not the right tool, we say so.
What changes
A feature that does a specific job, cites where its answers came from, degrades sensibly when it does not know, and has a cost per request you can forecast.
The service this falls under
Software development
Web apps, SaaS platforms, APIs and the systems underneath them.
Six to twenty weeks depending on scope.
Industries where this comes up
Software and technology companies
Security review, automated usability testing, vulnerability scanning in CI, and the edge and bot policy that keeps a product reachable but not scrapeable.
Media, entertainment and creators
Interactive fiction and character platforms, automated ad and video production, live streaming, and in-browser media tooling.
Last reviewed · Site changelog