Skip to main content
Methodology

What a small team can ship once the machine takes the repetitive part

We are not selling "we use AI": we show you the pipeline and the numbers from our own site. People deciding, agents executing, and a CI that refuses to let half-finished work through.

996
Published pages
5
Languages at parity
635
Technical articles
22
Automated checks

Soamee's methodology combines the CRAFT process (Consult, Research, Architect, Forge, Track) with AI-agent-assisted development and a continuous integration setup that blocks any incomplete delivery. Product, architecture and design decisions are always human; agents handle the repetitive, verifiable work: boilerplate, translations, migrations, tests and SEO checks. Every change goes through human review and 22 CI automations that verify translation coverage, images, SEO metadata, Schema.org, social cards and broken links before reaching production. The measurable result on our own repository: 996 pages published in five languages, 635 articles and 130 case studies kept at parity by a boutique team based in Madrid.

The pipeline

CRAFT, with an agent layer underneath

The process does not change: what changes is who does each task inside each phase. Above, the quality gates nothing skips. Below, what we delegate to agents.

Quality gates

Human review · Tests · CI · SEO audit · Deploy

01
Consult
Initial consulting

We learn the business and the problem. We leave with measurable goals and a preliminary scope.

02
Research
Research

We analyse users, workflows and existing systems. We decide what to build and what to integrate.

03
Architect
Architecture

We design the architecture, the data model and a delivery plan prioritised by business value.

04
Forge
Development

Two-to-three-week sprints with a demo at the end of each one. Working software from month one.

05
Track
Measure and evolve

We deploy, measure real usage and evolve the system: maintenance, improvements and new modules.

Agent layer

Nothing reaches production without clearing all five gates, no matter who wrote it.

Division of labour

What a person decides and what the machine accelerates

Every client asks the honest question: "if AI does it, why am I paying you?". Here is the answer, unvarnished.

Always human

We delegate none of this. It is where a project is won or lost.

  • What to build and in what order: scope, priorities and cuts
  • Architecture, data model and the decisions that are expensive to undo
  • Visual and product design — no generic templates
  • Review of every line of code before it merges
  • Direct contact with you: whoever writes the code is in the demo
  • Accountability for the outcome. The tool signs nothing

Accelerated by agents

Verifiable, repetitive, boring work. Exactly where a machine never tires.

  • Boilerplate and scaffolding from an architecture already decided
  • Translations into five languages, reviewed afterwards
  • Bulk migrations and mechanical refactors across hundreds of files
  • Tests, fixtures and CI scripts
  • Crawling third-party API documentation
  • Accessibility, technical SEO and metadata checks

We put it in writing: we published a post-mortem of our own repository with what worked and what we had to redo. Read the repository post-mortem →

Quality control

The gates nothing skips

Writing code fast is easy. The hard part is making sure nothing is left half-done at speed. That is why incomplete work never even reaches the main branch.

Translation coverage

If a page or an article ships in Spanish without its four translations, the push fails. No orphan content.

npm run check:translations

Verified images

Checks that every referenced image exists and that two different entries do not reuse the same file.

npm run check:images

SEO audit

Titles, descriptions, h1s, canonicals and hreflang for every built URL. No manual exceptions.

npm run check:seo

Schema.org

Validation of each template’s JSON-LD so search engines and LLMs understand the page.

npm run check:schema

Social cards

Every URL gets its own social card with its own copy, rendered on demand and verified in CI.

npm run check:og

Pre-push hook

The same checks run on your machine before anything is pushed. CI is the safety net, not the first warning.

.githooks/pre-push

On top of that run the scheduled audits: Lighthouse, broken links, metadata guard and ranking snapshots. 22 automations in total.

The proof

Our own site is the case study

We cannot show you our clients’ internal numbers. We can open up the soamee.com repository, which is built with exactly the same pipeline.

996
.astro pages

Published and maintained, dynamic routes excluded

130
Case studies

26 cases × 5 languages, always in sync

635
Articles

127 Spanish originals plus their 4 translations

67
Components

Our own design system, no bought templates

Published pages per language

Published pages per language Spanish: 238. English: 197. Portuguese: 192. Italian: 192. German: 192 Spanish 238 English 197 Portuguese 192 Italian 192 German 192

Multilingual parity is the most honest metric of a pipeline: it is the first thing any capacity-constrained team abandons.

What it means for you

What changes in your project

Three concrete consequences of working this way, with no promises we cannot keep.

More surface per sprint

What another agency parks in "phase 2" — the other languages, the admin panel, the documentation — usually fits inside the initial scope.

Less hidden debt

Automated checks catch daily what a human team only finds in next year’s audit.

No black box

We tell you which part an agent generated and which part a person reviewed. And the code is yours from the first commit.

FAQ

Frequently asked questions

The ones we get on the first call, answered before you have to ask.

Does AI write all the code in my project?
No. Agents generate a significant share of the repetitive code, but every change goes through human review before merging. Architecture, product and design decisions always belong to a person on the team.
If you use AI, is the code lower quality?
The risk is real, which is why we built the quality gates: mandatory human review, tests, and 22 automations that verify translations, images, SEO, Schema.org and links before every deploy. The bar is set by the process, not the tool.
Who owns the code?
You do, from the first commit. We work in your repository or transfer it at handover, with the full change history and the technical documentation.
Can I see which part an agent generated?
Yes. Commits with agent participation are marked in the git history, so you can audit the split whenever you want.
Does this methodology suit every project?
It pays off enormously on projects with repetitive patterns, multilingual content, migrations or a lot of boilerplate. On very complex business logic or original design the saving is smaller: there the weight stays human, and we say so upfront.
What about my confidential data?
It does not enter third-party tools without your express authorisation. We work with synthetic or anonymised data in development and sign the NDA before we start.
Our AI-assisted development methodology

Tell us your challenge. We'll propose a solution.

No commitment. Within 24 hours, you'll receive a proposal with scope, timeline and budget. No fine print.

Book a free call →