How we build

An SDLC rebuilt around AI

Three loops carry an idea from a rough brief to a product running in production, and keep it running. People stay where judgment matters, in the spec. AI takes the work that rewards repetition: building against tests, shipping, and watching what happens next.

The loop

Each circle produces something the next one needs. Human involvement is heaviest at the start and lightest at the end, which is what the color shift tracks. Nothing here is a phase gate you pass through once.

SPEC & PROTOTYPE STILL AGILE Human + AI SOFTWARE FACTORY 24/7, THREE SHIFTS AI + E2E Tests DEPLOY & OBSERVE CONTINUOUS AIOps what production teaches goes back into the spec People and AI refine the spec until a working prototype proves it Tests define done. AI builds against them until the product is functional Ship continuously, with AI watching production and catching drift

What happens in each circle

The split is deliberate. Judgment stays with people, repetition goes to the machines, and the handoff between them is a written artifact rather than a meeting.

Circle one

Human + AI

The spec is the product at this stage. People bring domain knowledge and taste, AI drafts, argues, and builds throwaway prototypes fast enough that you can find out you were wrong in an afternoon.

  • Rough brief becomes a written, testable spec
  • Prototypes settle arguments instead of opinions
  • Exit when a running prototype proves the idea

Still Agile. Nothing about the way your team works gets thrown out. Sprints, a backlog, and review still set the rhythm. AI joins that rhythm instead of replacing it, which is why this is the one circle that keeps human pace.

Circle two

AI + E2E Tests

End-to-end tests turn the spec into a definition of done a machine can check. AI builds against that definition on a loop, so progress is measured by tests passing rather than by status updates.

  • Tests written from the spec, before the build
  • AI implements until the suite is green
  • A functional product, continuously, not at a milestone

24/7, three shifts. The factory does not keep office hours. Where your team works one shift, agents work three, so the build moves overnight and you come back to a green suite rather than a status update.

Circle three

AIOps

Shipping and watching are the same job. Deployment runs continuously, and AI reads the telemetry it produces, catching regressions and drift long before a dashboard would surface them.

  • Continuous deploy with automated rollback
  • AI monitors logs, metrics, and cost
  • Findings return to circle one as spec changes

Continuous. There is no release window to wait for and no one watching a dashboard at 3am. Deployment and monitoring both run on their own, and a person is paged only when judgment is actually needed.

Why it is shaped this way

The spec is the bottleneck, so people stay there

AI writes code faster than any team can decide what the code should do. Moving people to the front of the loop puts them where the constraint actually is.

Tests are the contract between human intent and machine work

An agent needs a definition of done it can verify by itself. That is what end-to-end tests give it, and it is why they come before the build rather than after.

Production is an input, not an endpoint

What a system does under real load is information the spec never had. The loop closes so that information arrives while it is still worth acting on.

We run this on our own work

Goish and kvlm are both built this way. The measured verdicts and port statistics on their pages come out of circles two and three.

Put this loop on your product

Tell us what you are building and we will show you where your team sits in the loop today, and what it takes to close it.

hello@cogentica.ai