Curriculum vitae
Updated Aug 2026

Joakim Riedel

AI Solutions Architect · Founder-Engineer · Governed Production AI

Brussels since 2020 · Swedish (EU) citizen · open to relocation

joakim@monotio.comlinkedin.com/in/joakimriedel

Span
  1. 1997First consultancy
  2. 2007Boreda
  3. 2014Almi
  4. 2017Propstreet / Monotio
Profile

From high-value use case to governed operation.

Founder-engineer and hands-on architect: production software since 1997, production AI since 2023. Co-founded two commercial real-estate platforms — Boreda, acquired in 2012, and Propstreet, a venture-backed AI-native dealmaking platform. I take organisations from AI experimentation to governed, scaled adoption: scoping high-value use cases with business users, weighing architecture trade-offs across security, data sensitivity, cost, scalability, interoperability and governance, and carrying solutions from concept through proof of concept into operation. Workshop leader and speaker; curious by default and quick to adopt what works.

Impact

Evidence over theatre.

  • Governed frontier AI. Production agents with 70+ authorization-gated tools, human approval gates, ~1,000 eval assertions across 41 suites, full cost governance and observability — serving paying B2B customers since 2023.
  • Built to exit. Engineered Boreda from first product to acquisition by Värderingsdata in 2012, then stayed two years through integration into VD Pro — today part of MSCI.
  • Built adoption. Led customer discovery and rollout at Propstreet; delivered commissioned AI-engineering workshops to Swedish tech companies; invited speaker at Solvay Brussels School.
  • Built for interoperability. Shipped an external MCP server, 21 versioned public APIs and four MIT-licensed open-source AI tools; contributor to the promptfoo eval framework.
Experience

Production, product and adoption.

Co-Founder & CTO · Propstreet AB

Venture-backed AI-native B2B platform for commercial real estate · Stockholm / Brussels

2017–2026

Operational CTO through Aug 2026 · board member from Sep 2026

  • Principal interface between engineering and business users: mapped broker, investor and domain-team workflows, turned recurring field needs into prioritised AI use cases, and guided adoption from first release to daily production use.
  • Designed and shipped Propstreet Agent on the OpenAI Responses API: streaming multi-step execution, parallel tool calls, 70+ authorization-gated tools, strict structured outputs and single-flight concurrency.
  • Implemented safeguards against prompt injection, data leakage and hallucination propagation through permission-aware tool access, approval gates, schema-enforced outputs and operational guardrails.
  • Built the retrieval and research stack: embeddings, vector search, reranking and calibrated scoring; hosted web search; progressive-disclosure skills; vision/OCR over deal documents.
  • Made the platform measurable with per-request cost ledgers, quotas, budgets, retries, kill switches, prompt-cache accounting and OpenTelemetry GenAI traces.
  • Established eval-driven development: 41 promptfoo suites and ~1,000 deterministic, JSON-schema and LLM-judged assertions tied to production prompt snapshots, gating prompt and model rollouts.
  • Codified reusable patterns into an external MCP server, 21 versioned public APIs, four MIT-licensed tools and scheduled or event-triggered agents.
  • Built and operated the full B2B SaaS across C#/.NET, TypeScript/Vue and Azure, backed by 11,000+ automated tests, converting each frontier-model release into customer-facing features.

AI capability building & speaking

Commissioned workshops and invited speaking

2025–2026
  • Commissioned AI-engineering workshops for Swedish e-commerce, fintech and SaaS companies: hands-on sessions for engineers, product teams and leadership on agentic development, MCP, evals, quality gates and production adoption; audiences up to ~100 engineers.
  • Invited speaker, BATIBOUW Business Insights / Solvay Brussels School (2025). Client names and references available on request.

Financing Advisor, Startup & Growth Finance · Almi Företagspartner

Swedish state-owned lender · Gothenburg region

2014–2016

Ran a portfolio of ~100 companies: business plans, financials and creditworthiness; credit decisions and follow-up under the government-backed lending programme; advice to founders on growth and investment readiness.

Co-Founder & CEO · Boreda AB

Commercial-property valuation and analytics software

2007–2014

Built a web-based valuation, analytics and data-mining product, owning development, delivery, customer dialogue and go-to-market. Acquired by Värderingsdata in 2012; stayed two years to integrate the product into VD Pro — today part of MSCI.

Independent IT & Internet consultant · own consultancy

Sweden

1997–2007

Founded while in high school; helped Swedish businesses get online with websites, email systems and early business IT as the commercial Internet emerged.

Toolbox

Hands-on across the stack.

AI platforms
OpenAI Responses API, agents and embeddings in production since 2023; Anthropic Claude and MCP; Azure OpenAI; model-agnostic architecture across proprietary and open-weight models.
AI engineering
Agent orchestration, tool calling, strict structured outputs, RAG, embeddings, hosted web search, vision/OCR, prompt and context engineering, eval engineering (promptfoo contributor).
Safeguards
Authorization-gated tools, human approval gates, filtering, schema enforcement, quotas, budgets, cost ledgers, kill switches, retries and OpenTelemetry GenAI observability.
Software & cloud
C#/.NET, TypeScript/JavaScript, Vue 3, Python, SQL/EF Core, REST/OpenAPI, xUnit, Vitest, Azure SQL and OpenAI, Pinecone, Hangfire and SignalR.
Delivery
Use-case discovery and scoping, system design, rapid prototyping, production rollout and adoption, technical workshops and cross-functional stakeholder communication.
Capability to value

Each model shift became a working capability.

  1. 2023

    Embeddings and function calling: semantic matching and conversational retrieval turned into customer workflows.

  2. 2024

    GPT-4o and text-embedding-3-large: stepped up speed and quality of the production copilot and matching stack.

  3. 2025

    Reasoning models and the Responses API: core workloads moved into stateful, multi-step agent loops.

  4. 2026

    Hosted web search, MCP and vision/OCR: autonomous research, external agent access and document intelligence, instrumented for cost and traceability.

Foundation

Education, languages and eligibility.

Education
University of Gothenburg — B.B.A., Business Administration; complemented by 29 years of continuous engineering practice.
Languages
Swedish native; English fluent; German conversational; French conversational and actively advancing toward professional working proficiency.
Eligibility
Swedish citizen — national of an OECD and NATO member country; eligible for national security clearance.