What I build with all this.

Revenue Cloud · Quote-to-Cash

End-to-end Quote-to-Cash on Revenue Cloud (RLM + CLM + Industries CPQ) for a fictional DACH B2B supplier, built in a real Developer Edition org. Expression Sets qualify products before configuration and pricing; tiered discount approvals keep their thresholds in Custom Metadata and route by role, never by person. The order then travels through ten external systems via Apex and MuleSoft — SAP S/4HANA, Stripe, DocuSign, and the German finance stack (lexoffice, DATEV, CAMT.053) — with idempotency and signed-webhook verification. 33 architecture decision records.

Revenue Cloud · ISV

My own Salesforce ISV product — a managed package on Revenue Lifecycle Management. When the catalog doesn’t carry what the customer wants, the rep describes it in plain language and it is built directly on the quote, without touching the catalog; the catalog only grows when the business has earned it. The model extracts intent and never touches money — every quantity, price and discount is parsed by code. Prepared for AppExchange Security Review, not yet submitted.

Agentforce · Data 360

A live, deployed Agentforce agent for HanseWatt — a fictional DACH energy retailer (demo org; the company is invented, the agent and its grounding are real). It identifies the customer, explains a consumption anomaly grounded in Data 360, and logs the support Case itself — grounded, not guessing, and taking real action under the Einstein Trust Layer.

Multi-agent · MCP

A complete Salesforce org built by an agent loop I designed — seven objects, triggers and tests — over six custom MCP deployment tools. The verifier is the test runner, not the model: deploy → test → read the real failures → fix → repeat until green. The same org carries a second agent: a router over three specialists — records, triage, scheduling — each owning one job, all called in a single turn.

Static analysis · GDPR

A static analyzer that computes what an agent’s code can really reach — not what it’s allowed to, but what its Apex actually resolves to at runtime. It caught a GDPR-labelled field escaping past the running user’s permissions into the model, at zero credits. And the judge isn’t me: a runtime oracle deploys each case into a real org and checks the analyzer’s own prediction.

Einstein AI · MCP

An AI document-classification engine (an Einstein Prompt Template that reads each partner document into structured JSON and closes the matching compliance request), plus two Agentforce actions also exposed to Claude as MCP tools — so one plain-language request can qualify a lead or spin up a full deal.

Agentforce · Compliance engine

A German charging-law compliance engine with an Agentforce agent on top. The engine decides and the agent explains: legal status is a formula field a compliance officer can sort in a list view, and a transcript gate fails if the agent cites a paragraph no action returned. Twenty-five real Berlin charge points, imported live from OpenStreetMap, all come back UNBEKANNT — because a missing date is not a clean bill of health.

Agent safety · Red-team

I built the agent — then built the thing that tries to break it. A pre-registered German attack corpus (committed first, so git is the notary) drives a live red-team run, and a deterministic verifier decides pass or fail — the model never grades itself. It found a real weakness in my own agent, and reported it honestly.

Pre-install evidence · ARI

Before anyone builds an agent, PreFlight scans 12–24 months of the customer’s real closed cases — LLM-free, zero credits, read-only — and scores whether the history can carry an agent at all: a six-component Agent Readiness Index plus a board-ready German evidence report where every number is tagged Measured, Observed, Derived or Projected. 79/79 tests green, 93% coverage.

Runtime root cause · Observability

Salesforce Observability tells you WHAT happened — Nabz (Turkish for “pulse”) tells you WHY. It correlates a live agent’s quality drops with the org’s change stream — including agent edits nobody filed a ticket for — and names the strongest candidate cause with an evidence grade A–E, never a bare “root cause”. Fixes are proposed, never applied.

EU AI Act · Article 26

The legal output layer of Agent Blast Radius: it turns an agent’s operational traces into an EU AI Act Article 26 evidence pack, judging every obligation on two axes — is it documented, and does the trace show it actually ran. Zero LLM, zero network, and it ships with two deliberate gaps, because an audit report where everything is green is marketing, not evidence.