Skip to content
createIF Labs
kontakt@createif-labs.de Intro call

00, Company

A full stack software company specialising in AI agents

We build complete systems: backend, frontend, infrastructure, operations. And agents, up to autonomous ones, following approaches that have held up in production. One partner for the whole system, not just for the model.

Depth
full stack
Stages
01 to 04
Deployment models
5 options
Infrastructure
our own GPUs

00.1

Four things, not five

The shortest description of our work that still holds.

Full stack
Architecture, backend, frontend, data, infrastructure and operations from one team.
Agents in production
Evaluation, guardrails, observability and cost control from the start, not bolted on after the prototype.
Sovereign operation
LLMs run locally, in your own data centre, hosted in Germany or as a cloud API. Your data stays where you want it.
Small to large
From a single model inside an existing process to an autonomous agent system inside a product.

00.2

The difference between a demo and production

An agent that works in a pitch and an agent that still works after six months in production are not the same system. The difference is created in week one, not at the end.

Demo logic

  • Success is demonstrated, not measured
  • The prompt gets adjusted until the example works
  • Tools without defined failure behaviour
  • Cost per request unknown
  • Decisions cannot be reconstructed afterwards
  • No operating concept for the day after launch

Production logic

  • Test set and automated evaluation from day one
  • Context deliberately controlled instead of patched later
  • Tools with defined failure and abort behaviour
  • Cost per request as a metric in monitoring
  • Full tracing of decisions and tool calls
  • Versioning and regression tests on every model change

Every point in the left column can be addressed before the first line of code. Retrofitting each one costs a multiple.

00.3

Four stages, four entry points

The stages describe increasing autonomy, not a mandatory path. Each one makes sense on its own and reads as an entry point.

StageWhat it isTypical entryPrerequisite
01 Single modelA tightly scoped model for exactly one task in an existing processClassification, extraction, text preparationSample data from the real process
02 Agent on the webTool access in a web interface for a defined user groupInternal assistant, research across existing dataSystem access, role model
03 Agent in the processCarries out work steps independently, with approval pointsCreating records, preparing replies for approvalA documented process, approvals settled
04 Autonomous in a productA scalable agent system as part of a product, multi tenantAgent features inside a SaaS product, high throughputLoad profile, tenant model, operating concept

All stages in detail →

00.4

Your data stays where you want it

We run our own GPU infrastructure and know these deployment models from daily operation. None of them is better in general. Which one fits follows from your constraints.

ModelData controlOperating effortTypical case
Local, at your sitecompletewith youData must not leave the building
On premise, your data centrecompletesharedIntegration into existing operations
Hosted in Germanycontractually clearwith usGDPR clarity without owning hardware
Cloud or APIwith the providerminimalSpeed and model quality come first
Hybridby data classsharedSensitive work local, uncritical load external

Full comparison across all dimensions →

00.5

How we build agents

Ten steps, in this order. Starting at step three means paying a multiple for step two later.

01 Use case
We start with the process and a measurable target, not with the model.
02 Evaluation
The success measure and the test data are settled before implementation.
03 Context
Deliberate control over what the agent sees at which point.
04 Tools
Tightly scoped, robust, documented, with defined failure behaviour.
05 Scope of action
Permissions, validation, abort conditions.
06 Approvals
Human sign off where mistakes are expensive.
07 Observability
Tracing of decisions, tool calls and cost.
08 Cost and latency
Model choice per subtask, caching, smaller models where possible.
09 Operations
Versioning, regression tests on model changes.
10 Scope of delivery
A small usable stage first, then extend.

The approach in full →

00.6

An agent at work, instead of a claim

A runtime panel shows an agent at work: tool calls with their latencies, one blocked access, a draft reply appearing character by character, and readouts for calls, cost and elapsed time running alongside. Before the first write the run stops and waits for an approval. You can decide yourself, but you do not have to.

Open the demo →

00.7

Agents that get better in production

Every approval, every rejection and every correction becomes a test case. A candidate runs against the live version on the same set, and only what is better without becoming worse elsewhere is rolled out. The previous version stays available as a fallback. Without that loop a system does change, but nobody can say in which direction.

The loop in detail →

00.8

We run what we sell

The TimeTracking AI Agent connects to existing time tracking software, including legacy systems without a usable interface. People book their hours in a chat instead of a form. A product of our own in continuous operation is the one proof of operational capability that cannot be delivered as a slide.

About the product →

00.9

Let us talk about the case, not the model

Thirty minutes in which we place your project. Including the answer that it does not need an agent, if that is the honest one.

Book an intro call →

Agents: 4 in production Deployment models: 5 options Infrastructure: our own GPUs +49 172 6942603