Flagship service

IA Factory: from task to production.

A software factory with AI agents: repeatable, auditable and under human control. Work goes in one end and comes out finished at the other, with a person who reviews and merges every change.

Not to be confused with: an infrastructure “AI factory” (GPU data centers). This factory produces software.

The starting point

Coding with agents is no longer enough

With one chat per developer, the bottleneck is still the person who asks, watches and reviews.

Everything goes through someone

Every task waits for a person to request it, follow it and review it. Opening more chat windows does not change that.

Context gets lost

Every session starts from scratch: forgotten decisions, duplicated code and time spent re-learning the project.

Everyone does it their own way

Without a common process there is no way to audit what the agent did or to improve the whole team’s results.

What changes: from chatting with an agent to running a production line that someone designed and supervises.

What it is

Any repeatable, auditable process with AI inside

Repeatable

The same task always follows the same path.

Auditable

Every step leaves a trace: what went in, what came out and where it failed.

Three kinds of step

Code

Deterministic. Always does the same thing and cannot be skipped: tests, scans, blocking rules.

Agent

Reasons over its input: drafts the specification, builds, reviews.

Person

Approves what matters: high-impact changes and business decisions.

How it works

The production line, step by step

Every task follows the same path with its own identifier and its own branch; many can move in parallel.

  1. Step 1 Code

    Intake

    A production bug, an issue or a chat request. Everything comes in through the same place.

  2. Step 2 Agent

    Specification

    An agent writes down what will be done, after checking the project memory.

  3. Step 3 Agent

    Build

    Its own branch and tests first: write the test, then the code that passes it.

  4. Step 4 Agent

    Parallel review

    Security, code, UX and UI, with models different from the one that built it.

  5. Step 5 Agent

    Approver

    Gathers the reviews. If something fails, it sends the task back to build.

  6. Step 6 Code Person

    Risk gate

    Classifies the change by risk and sets how much human review it needs. A person merges.

↺ If a review fails, the Approver sends the task back to Build until it passes. Nothing moves forward with a review pending.

Project memory: decisions, architecture and constraints every agent checks before acting.
Log: every step leaves a trace: what went in, what came out, which model did it and who approved.

The foundations

The four pieces that hold up the factory

This is what SISCON already delivers as Harness Engineering; the factory puts it to work on every task.

Project memory

Decisions, architecture and constraints documented in a structured way and shared by the whole team.

Constitution

Rules the agent cannot skip because they are enforced in code: never to the main branch, never to production without approval.

Reusable tools

Scripts and connectors built once and reused, instead of improvised on every task.

Tests and evals

Tests before code and continuous evaluation, so quality is measured instead of left to luck.

Why it matters: without these foundations, more agents just produce more code nobody can maintain. Learn about Harness Engineering; AI Evaluation provides the line’s evals.

Human control

A person reviews and merges every change

The factory classifies every change by risk and adjusts how deep the review goes.

RiskExample changesWhat the factory does
LowCopy, styles, interface tweaks, documentationLight human review; automatic merge only if the client authorizes it
MediumBug fixes, well-scoped featuresPull request reviewed by a person
HighDatabase, security, payments, core business logicMandatory human approval and controlled deployment

SISCON’s position: mandatory human review

  • It is our method. Just as in Agentic Software Development: a person reviews and merges every change; agents do not decide on their own what goes to production.
  • Rules in code. Risk classification is not left to the agent alone.
  • Optional autonomy. Automatic merge exists only for low-risk changes, if the client authorizes it and results support it.

Method and service

IA Factory and Agentic Software Development

Agentic Software Development

The method SISCON builds with: specification before code, one test per clause and mandatory human review.

See the method →

IA Factory

The service that sets up and runs the complete production line with that method, in your repository and under your rules.

Where it runs

In the cloud, hybrid or inside your network

The production line is the same; what changes is where the models live and, with that, what leaves your network.

In the cloud

Commercial models via API.

Advantage
Greater model capability and immediate start.
To consider
Code and context travel to a provider.
Who it is for
Code without confidentiality restrictions.

Hybrid

Local models for sensitive work, cloud for the rest.

Advantage
Balance between capability and privacy.
To consider
Clear rules on what goes where.
Who it is for
Repositories with critical parts.

On-premise

On Local Node, Private Platform or Governed Sovereign AI.

Advantage
Nothing leaves your network; logs under your control.
To consider
Quality with local models is measured first.
Who it is for
Regulated sectors and proprietary code.
With local models, scope is committed after measuring their quality with evals on your own code. Compare the three on-premise AI architectures →

Risks and controls

What can go wrong and how it is controlled

Every risk has a control on the line, not a promise.

RiskControl in the factory
A change breaks productionRisk gate, mandatory tests and a rollback plan for every deployment
Generated code with security flawsSecurity reviewer on a different model, plus automated scanning
Loss of control over the architectureProject memory and constitution every agent must check
Agents with too many permissionsIsolated environments, minimal and short-lived credentials
Token costs spikeA limit per task and a model suited to each kind of step
Dependence on one model providerInterchangeable models per step, including local models
The team stops understanding its own codeReadable specifications, human review and living documentation

How we deliver it

From a manual process to your first line in operation

We start with a single process, with full human review, and open up autonomy according to results.

  1. 01

    Diagnostic

    Candidate processes, a baseline of cycle times and risk level.

  2. 02

    Harness

    Memory, constitution, tools and evals in your repository.

  3. 03

    First line

    A factory for one process, with every task reviewed by a person.

  4. 04

    Gradual autonomy

    The risk gate opens as results support it, and only with your authorization.

  5. 05

    Operation

    KPIs, new lines and continuous improvement.

Measured by: cycle time · tasks resolved without intervention · defects reaching production · cost per task. KPIs are set against your baseline in the diagnostic; we do not promise figures before measuring.

What the market is doing

Three published cases, one pattern

Engineering companies already work this way and have documented it publicly during 2026.

Stripe

More than 1,300

pull requests merged per week, produced by its agents and reviewed by people.

Source: stripe.dev · February 2026

OpenAI

About 1 million

lines of code in an internal beta product, with no hand-written code. They call it harness engineering.

Source: openai.com · February 2026

StrongDM

0

human code reviews in its factory: it replaces review with scenario-based validation. SISCON does not follow that model: we keep human review.

Source: factory.strongdm.ai · February 2026

Figures published by each company; they are not SISCON results. The common pattern: deterministic steps that cannot be skipped, agents in isolated environments and automated validation.

FAQ

Frequently asked questions

Does IA Factory replace my development team?

No. It changes their work: people specify, review and approve, and the factory handles the repeatable steps. A person merges every change.

Can the factory merge changes without human review?

Only as an option for low-risk changes —copy, styles, documentation— and only if you authorize it and results support it. Medium- and high-risk changes always go through a person.

Which processes are good candidates?

Those done more than once a week, with a clear input and output, that can be reviewed: bug fixes, well-scoped features, module migration, interface tweaks or documentation.

Does it work with local models, inside my network?

Yes, on any of our three on-premise AI architectures. With local models, scope is committed after measuring their quality with evals on your own code.

How is it different from Agentic Software Development?

Agentic Software Development is the method we build with: specification before code, one test per clause and mandatory human review. IA Factory is the service that sets up and runs the complete production line with that method.

How do you measure whether it works?

With KPIs defined in the diagnostic: cycle time, tasks resolved without intervention, defects reaching production and cost per task. We do not promise figures before measuring your baseline.

Next step

Start with a single process

A free discovery session to choose the candidate process, review your repository and define how your first line would be measured.