Skip to content
Boxed Online, home

How we work

Software in days,with a senior person in charge.

AI agents do much of the typing. The speed comes from the process around them: a written goal, small packages, tests on every change and a person reading all of it. That is also why the documentation and governance a board expects are not skipped.
  • Every change read by a person
  • Tests on every change
  • You keep every document

Why it is faster

Most of a software estimate is coordination, not building. AI agents do the typing; an experienced engineer does the thinking. Every change is planned, reviewed and tested before it ships, so work quoted in weeks ships in days.

What it means for the business

Faster delivery, without cutting corners.

  • Days, not months

    Builds estimated at between 5.5 and 29 weeks of effort were delivered, built and tested, in hours or days. The log is public.

  • You know what you are getting

    A written goal and definition of done are agreed before anything is built, so the result is checked against your words.

  • Lower risk, not higher

    Tests and security scanning on every change, and a person reads every change before it is merged.

  • You own all of it

    Code, documents and decisions are yours. Take them in-house or to another supplier whenever you like.

The loop

One process, every build.

The same loop runs whether the job is a free proof or a full product. If our review finds a problem, it goes back to the builders as a fix, and round again.

The saffron line is the fix loop.

  1. Written goal and definition of doneAgreed in writing before anything is built
  2. Architect agent plans work packages in wavesEach package small enough to test on its own
  3. Builder agents work in parallelSeparate lanes, separate workspacesFour lanes at a time, for example
  4. Tests and code scanning on every changeAutomated, every time, no exceptions
  5. We review every changeA human reads it before it is mergedAnything found goes back to the builders as a fix.
  6. Completeness reviewChecked against the definition of done
  7. ShipBuilt and tested; hardening follows

The document chain

Four documents, each one yours.

Before anything is built, the thinking is written down. You keep every document, whoever builds from them.
  1. Step 1 / PCD

    Product Concept

    Frames the problem and tests whether it is worth building at all.

    You receive

    • The problem in plain words
    • An honest view on whether to build it
    • An investment case and payback model
  2. Step 2 / FDD

    Functional Design

    Turns the concept into something buildable and testable.

    You receive

    • Processes and user journeys
    • Numbered requirements and permissions
    • Screens, data and a traceability matrix
  3. Step 3 / SBD

    Solution Blueprint

    The technical design for how it will be built, run and handed over.

    You receive

    • Architecture, data model and security
    • Integrations, hosting and running costs
    • Decision records, phasing and exit
  4. Step 4 / Pack

    Branded delivery pack

    The same documents, finished to send to a board or a supplier.

    You receive

    • Word and PDF versions, branded
    • Cover, contents and consistent layout
    • Yours to keep, whoever builds it

Guardrails

Fast, but fenced in.

Speed is only worth having if it does not put your data, systems or reputation at risk. These rules apply to every build.
  • Every change is reviewed

    We read every change before it is merged. The agents propose; we decide.

  • Tests on every change

    Automated tests run each time, and work is checked against the written definition of done.

  • Code scanning

    Static analysis and security scanning run on every change, not just at the end.

  • Nothing deleted that the agents did not create

    Agents may only remove what they made themselves. Your existing data and files are off limits.

  • Secrets stay in vaults

    Keys and credentials live in a proper secrets store, never in code or in a prompt.

  • Client data stays in covered services

    Your data only goes to services that sit under a data processing agreement.

Honesty

What AI is bad at.

Independent research is mixed on AI and developer speed. Knowing the weak spots is what lets the process work around them.
  • Knowing what you meant. Vague requirements get filled with confident, plausible guesses, so the goal is written down first.

  • Your history and politics. It does not know why the last project failed or who has to agree before anything changes.

  • Saying it is unsure. Wrong answers arrive in the same tone as right ones, which is why every change is read by a person.

  • Judgement on novel trade-offs. Architecture decisions with real consequences stay with us.

  • Staying on course over a long task. Work is cut into small packages so drift is caught early.

Questions

AI and safety.

Is AI-built software safe to run my business on?

It is as safe as the process around it. Every change is planned, reviewed by an experienced engineer, and proven by automated tests before it merges. Code scanning and security analysis run on every change. The AI does the typing; we are accountable for the result.

How do you keep our data private when using AI?

Your data stays in services covered by a data processing agreement, with enterprise AI endpoints that don't train on your data. We set out exactly where data goes before any build, and we use the least data needed for the job.

Where does AI not help?

Where the process itself is broken, where the data is poor, or where a simple rule would do. Many of the best outcomes we deliver are a process change or a better use of software you already own. We'll tell you when that's the case.

Tell us what's stuck.

In 30 minutes you'll know whether to fix it, buy it, build it or leave it. No pitch deck.

We reply within 2 business days.