I build Quote‑to‑Cash on Revenue Cloud — and the agents on top.

• Quote-to-Cash

  Revenue Cloud, end to end

  Product catalog — bundles, selling models, price book entries — qualification with Expression Sets, configuration, pricing, quotes and orders, tiered approvals, contracts (CLM) and Industries CPQ. Then the integrations that carry the order onward: SAP S/4HANA, DATEV, CAMT.053 bank statements, payments and e-signature, through Apex and MuleSoft. Built in TechnoStore, a Quote-to-Cash org for a fictional DACH supplier, and in Configra, my own RLM managed package.

  See the Quote-to-Cash build

• Agentforce

  Agentforce on the revenue process

  Agents grounded in the org's own data that act through Apex. A natural-language deal builder inside my own RLM package. Apex exposed to models as MCP tools, and a router orchestrating three specialist agents. One rule runs through all of it: the language model extracts intent, code sets the numbers.

  See the live agent

• Assurance

  Agents you can trust with money

  Agent Blast Radius — public, MIT — statically analyses what an agent's code can really reach, with a live org as the judge. Around it: a pre-registered German red-team bench, a runtime root-cause watchdog, and EU AI Act evidence built from the agent's own traces. The reason a finance or sales leader can let an agent near a quote.

  See the analyzer

Eleven Salesforce builds, ordered as a story.

• 2025

  TechnoStore — Revenue Cloud Quote-to-Cash for the DACH market

  Quote-to-Cash on Revenue Cloud — RLM, CLM and Industries CPQ, with tiered discount approvals and Expression Set qualification — carried into SAP, DATEV and bank reconciliation across ten external systems.

  ApexRevenue Lifecycle Management

  View project
• 2026Security Review next

  Configra — AI deal & configuration builder for Revenue Cloud

  My own managed package on Revenue Lifecycle Management: a rep describes a missing product in plain language and it is built on the quote — without touching the catalog, and without the model ever setting a price.

  Revenue Lifecycle ManagementEinstein Models API (GPT-4o mini)

  View project
• 2026Live agent

  HanseWatt — Agentforce & Einstein AI service for DACH energy

  A live, deployed Agentforce agent that explains a customer's bill grounded in Data 360 — then logs the support Case itself.

  Service CloudAgentforce (ReAct planner)

  View project
• 2026

  Hospital Org — a Salesforce org built by an AI agent loop I designed

  A complete Salesforce org built by an agent loop I designed — six MCP tools, with the test runner as the verifier, not the model.

  Model Context Protocol (Salesforce-hosted)Loop engineering

  View project
• 2026Live-tested

  Agent Blast Radius — the data an Agentforce agent can really reach

  A static analyzer that computes what an agent's code can really reach — and, on an Agent Script agent, traces a GDPR field from the database column into the model's prompt, at a line number.

  Agentforce (authority analysis)Agent Script (.agent) — Salesforce's own parser

  View project
• 2024

  Urla Shoes — AI document-compliance engine + multi-feature Salesforce platform

  Einstein classifies partner documents into structured JSON — and two Apex actions are exposed to Claude as MCP tools.

  Apex (Queueable, Schedulable)Lightning Web Components

  View project
• 2026

  VoltStream Mobility — a charging-law compliance engine, with an agent that cannot invent law

  A German charging-law compliance engine with an Agentforce agent over it — and a gate that fails if the agent cites a paragraph no action returned.

  Agentforce (Agent Script)GenAiPlannerBundle

  View project
• 2026Live-tested

  Prüfstand — the test bench that proves an Agentforce agent is safe

  I built the agent, then built the thing that tries to break it: a German red-team corpus and a verifier the model can't sweet-talk.

  Agentforce (evals & red-teaming)Agent Script (.agent) + tree-sitter AST

  View project
• 2026ARI · Zero-credit scanIn development

  PreFlight — the pre-installation evidence scan for Agentforce

  Before anyone builds an Agentforce agent on a customer org, PreFlight scans 12–24 months of real closed cases — LLM-free, zero credits, read-only — and scores whether the history is good enough to prove an agent would succeed: a six-component Agent Readiness Index plus a board-ready German evidence report in which every number is tagged Measured, Observed, Derived or Projected.

  Apex (with sharing) + Queueable orchestrationAgent Readiness Index — 6 components, frozen weights 25/20/15/15/15/10

  View project
• 2026Root cause · κ-gateIn development

  Nabz — the runtime root-cause layer for live agents

  An in-org, zero-egress root-cause watchdog for live Agentforce agents: Nabz (Turkish for 'pulse') correlates a deterministic conversation-quality time series with the org's change stream and names the strongest candidate cause with an evidence grade A–E — never a bare 'root cause' — proposing fixes a human must approve.

  Apex + 6 Lightning Web ComponentsEWMA control band + changepoint detection — deterministic, no ML

  View project
• 2026AI Act · Art. 26

  Aktenlage — the EU AI Act Article 26 evidence layer

  The legal output layer of Agent Blast Radius: a pure-Python tool that 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.

  EU AI Act — Article 26 (deployer obligations)Pure Python — zero LLM, zero network, zero credits

  View project