Skip to content
Stefan Manja
01 / selected work

Selected work

Delivery choices, system shape, and outcomes from real internal AI work.

These write-ups are intentionally selective: enough to show the problem shape, system approach, and proof of execution, without exposing internal material that should stay internal. Current public cases draw from in-house work at Delta Holding; external client work is added when disclosure allows.

A credit-risk decision-support workflow built in-house at Delta Holding, combining public-company risk signals with internal operating context into structured, analyst-ready recommendations.

Context
B2B credit-risk analysis and limit-setting workflow inside a multi-entity enterprise finance function.
Outcome
Observed workflow outcomes included ~75% faster analysis, 4.4/5 analyst-rated quality, and 90%+ recommendation acceptance.
PythonLLM APIsWorkflow designStructured decision support

A self-hosted internal knowledge assistant built in-house at Delta Holding, with Azure AD-scoped access, operator/admin surfaces, feedback loops, and usage and cost observability built in from the first version.

Context
Internal enterprise knowledge-access system serving multiple business units, with requirements around access control, quality governance, and operational visibility.
Adoption and feedback signal
Deployed across roughly 1,500 eligible users, with 300+ actual users and 85%+ positive explicit feedback on thumbs-up/down responses.
FlaskDockerPostgreSQLpgvectorLangChainAzure AD SSO

Workflow review

If you have a similar internal AI workflow to build or harden, I can review the workflow shape.

A short note on the workflow, users, current stage, and constraints is usually enough to tell whether build or advisory work makes sense.