Coding is where AI stopped being an assistant first. The tools below are not autocomplete curiosities; they are why the price of custom software has fallen hard enough that this site sells a Software Factory built on them. Even if nobody in your firm will ever open an editor, the category is worth ten minutes: it changes what you can afford to commission.
The three categories at a glance:
| Category | The developer’s role | Leading examples | What a buyer should know |
|---|---|---|---|
| In-editor assistants | Drives every keystroke | GitHub Copilot | Table stakes for any supplier |
| Agentic tools | Directs and reviews | Claude Code, Cursor | Where the cost collapse lives |
| App builders | Describes and curates | Fast-moving field | Superb for prototypes, unsafe for production |
Category one: in-editor assistants
The assistant watches a developer type and completes the next lines, answers questions and explains unfamiliar code. GitHub Copilot defined the category and remains the workplace default, woven into the world’s most common developer tooling; every major provider’s models now power similar features across editors. Real, measured productivity gains, but bounded ones: the developer still drives every step. For a firm buying software, a supplier using assistants is table stakes rather than a differentiator.
Category two: agentic tools, where the change lives
Agentic coding tools are given tasks rather than keystrokes: read this codebase, implement this feature, run the tests, fix what fails, and show me the result. The developer becomes a director, reviewing and gating rather than typing. Claude Code is the strongest of these in my daily use, and the claim is checkable rather than promotional: it is how the systems on this site’s Labs page get built, inside the specification-and-gates method the factory page describes. Cursor brings the same agentic posture into an AI-first editor, and the frontier labs all now ship agent modes of their own. This category is why build timelines compressed from quarters to weeks; the agentic AI cluster explains the supervision discipline that keeps it safe.
Category three: app builders
The newest category turns plain-English descriptions into running web applications: interfaces, databases and logic scaffolded in minutes. The products iterate too fast for a durable list, but the category is stable, and its honest business use is sharper than the demos suggest. As production systems, builder output tends to fail the unglamorous tests: security, data protection, edge cases, upkeep. As prototypes, they are superb: a working mock of the tool you want, built in an afternoon, is the best specification a commissioning firm has ever been able to hand a builder. Prototype cheap, then build properly.
What a non-technical firm should take from this
- Re-price the shelf. The system you assumed unaffordable may no longer be; the wish-list build you shelved years ago deserves a fresh quote in this new world.
- Change the supplier question. Ask candidates how they use agentic tools and, more importantly, what review, testing and security gates sit around them, because the tools amplify whatever discipline exists.
- Read the risk honestly. AI-built code without human review ships mistakes faster too; method, not tooling, is what you are really buying. ::: The consultancy-choosing guide gives you the questions.
Where I fit in
This category is my workshop. The Software Factory is these tools plus the discipline: written specifications, human review on every change, security gates before go-live and monitoring after. If there is a system your business wants and has never priced in this new world, bring it to a discovery call; re-quoting shelved ideas is quietly one of the most satisfying parts of the job.