Merge pull request #2 from itk-dev/feature/agentic-orchestration-studio

Feature/agentic orchestration studio

Author: yepzdk

CHANGELOG.md

@@ -33,6 +33,14 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 - Interactive HTML mock: Salary negotiation workflow with three tabs (personaleleder, HR-behandling, chefgodkendelse)
 - Mocks listing page
 
+### Added — Agentic Orchestration Studio Project
+- Main research report with pitch, problem statement, and recommendations
+- Open source landscape analysis across 5 categories (orchestration, BPM, agents, RPA, integration)
+- Feature comparison matrix of 15+ open-source tools
+- Two architecture options: full composed stack and minimal viable stack
+- Considerations document covering roles, security, OS2Forms, scalability, and funding
+- Denmark/OS2 public sector alignment analysis
+
 ### Changed
 - Rebranded site from "AI Research — Aarhus Kommune" to "ITKdev Research"
 - Replaced green theme with neutral black/grey palette

CLAUDE.md

@@ -28,7 +28,7 @@ requirements.txt                   # Python dependencies
 ## Conventions
 
 - All content is written in Markdown
-- Interactive mocks are self-contained HTML files (no external dependencies)
+- Interactive mocks are self-contained (no external dependencies). Small mocks use a single HTML file. Larger mocks may split CSS and JS into co-located files with the same base name (e.g. `unified-platform.html`, `.css`, `.js`)
 - Images are PNG screenshots of the mocks
 - Every project document starts with a project label: `<small>**Project:** Project Name</small>`
 - Use MkDocs Material admonitions (`!!! info`, `!!! warning`) for callouts

docs/index.md

@@ -34,3 +34,19 @@ Kan vi erstatte Excel-baseret lønforhandling med et struktureret system der tr
 
 - [Pitch og løsningsbeskrivelse](projects/salary-negotiation/index.md) — problem, løsning, integrationer og tekniske forudsætninger
 - [Interaktiv prototype](projects/salary-negotiation/mocks.md) — personaleleder, HR-behandling og chefgodkendelse
+
+---
+
+### [Agentic Orchestration Studio](projects/agentic-orchestration/index.md)
+
+**Status:** Draft | **Started:** April 2026
+
+Can we build a shared, open-source platform for mapping, automating, orchestrating, and measuring business processes across Aarhus Kommune?
+
+Inspired by TwoDay's commercial AOS, this project researches the open-source landscape and proposes an architecture for a self-hosted orchestration platform covering AI agents, RPA, workflow automation, and human-in-the-loop.
+
+**Key deliverables:**
+
+- [Open source landscape analysis](projects/agentic-orchestration/open-source-landscape.md) across 5 tool categories
+- [Architecture options](projects/agentic-orchestration/architecture.md) — full and minimal composed stacks
+- [Considerations](projects/agentic-orchestration/considerations.md) — roles, security, OS2, funding

docs/projects/agentic-orchestration/architecture.md

@@ -0,0 +1,216 @@
+<small>**Project:** Agentic Orchestration Studio</small>
+
+# Architecture Options
+
+Two proposed architectures for an open-source orchestration platform, from comprehensive to minimal.
+
+---
+
+## Option A: Full Composed Stack
+
+Maximum flexibility. Covers all four capabilities (Map, Automate, Orchestrate, Analyze) with best-of-breed tools at each layer.
+
+### Components
+
+| Layer                        | Tool                    | Role                                                                                         |
+| ---------------------------- | ----------------------- | -------------------------------------------------------------------------------------------- |
+| **Process engine**           | Flowable                | BPMN 2.0 process execution, CMMN case management, DMN decision tables, human task management |
+| **Process modeler**          | BPMN.io                 | Web-based visual BPMN editor, embeddable in our UI                                           |
+| **Agent orchestration**      | LangGraph               | AI agent workflows — classification, summarization, decision support, with human-in-the-loop |
+| **Integration & automation** | n8n                     | 400+ connectors to external systems (forms, case management, email, APIs)                    |
+| **RPA**                      | Robot Framework         | Desktop/browser/API automation for legacy systems                                            |
+| **Operations monitoring**    | Grafana + OpenTelemetry | Infrastructure health, alerting, detailed analytics (IT/admin only)                          |
+| **Data store**               | PostgreSQL              | Shared database for process state, audit logs, analytics                                     |
+| **Identity**                 | Keycloak                | Single sign-on, role-based access, municipal AD integration                                  |
+
+### How it fits together
+
+```
+┌─────────────────────────────────────────────────────────┐
+│                    Web Frontend                          │
+│        (Process maps, dashboards, task inbox)            │
+├────────────┬────────────┬────────────┬──────────────────┤
+│  BPMN.io   │  Task UI   │  Dashboard │   Admin          │
+│  (modeler) │  (inbox)   │  (custom)  │   (config)       │
+├────────────┴────────────┴────────────┴──────────────────┤
+│                   API Gateway                            │
+├────────────┬────────────┬────────────┬──────────────────┤
+│  Flowable  │  LangGraph │    n8n     │ Robot Framework  │
+│  (BPMN/    │  (agents)  │  (integr.) │ (RPA)            │
+│   CMMN/    │            │            │                  │
+│   DMN)     │            │            │                  │
+├────────────┴────────────┴────────────┴──────────────────┤
+│              Keycloak (identity/SSO)                     │
+├─────────────────────────────────────────────────────────┤
+│    PostgreSQL    │    OpenTelemetry    │    Grafana      │
+│    (state/audit) │    (telemetry)      │    (dashboards) │
+└─────────────────────────────────────────────────────────┘
+                          │
+            ┌─────────────┼─────────────┐
+            │             │             │
+        ┌───┴───┐   ┌────┴───┐   ┌────┴───┐
+        │ KMD   │   │ SBSYS  │   │OS2Forms│
+        │       │   │        │   │        │
+        └───────┘   └────────┘   └────────┘
+         (external systems / backends)
+```
+
+### Interaction patterns
+
+1. **Process designer** uses BPMN.io to model a process visually
+2. **Flowable** executes the BPMN process, routing between automated steps and human tasks
+3. At an "agent step", Flowable delegates to **LangGraph** which runs the AI agent(s)
+4. At an "integration step", Flowable triggers **n8n** workflows to talk to external systems
+5. At an "RPA step", Flowable triggers a **Robot Framework** job for legacy system automation
+6. **Human-in-the-loop** tasks appear in a task inbox UI, powered by Flowable's task service
+7. The **platform dashboard** (custom, built into the web frontend) shows process stats, task counts, hours saved, and ROI to all users
+8. **OpenTelemetry** collects infrastructure metrics from all components; **Grafana** provides detailed operational dashboards, alerting, and ad-hoc analytics for IT/admins
+9. **Keycloak** handles authentication and role-based access across all components
+
+### Strengths
+
+- Full coverage of Map, Automate, Orchestrate, Analyze
+- Each component is replaceable (no vendor lock-in)
+- Scales independently per layer
+- Standards-based (BPMN 2.0, OpenTelemetry, OIDC)
+
+### Risks
+
+- Integration complexity — 6+ components to connect and maintain
+- Requires strong DevOps capability
+- More moving parts = more potential failure points
+- Longer time to first value
+
+---
+
+## Option B: Minimal Viable Stack
+
+Fastest path to a working platform. Three components covering the core needs.
+
+!!! info "See the mock"
+    The [Unified Platform mock](mocks/unified-platform.html) demonstrates how these three components can feel like a single seamless platform.
+
+### Components
+
+| Layer                            | Tool     | Role                                           |
+| -------------------------------- | -------- | ---------------------------------------------- |
+| **Process engine + human tasks** | Flowable | BPMN execution, case management, task inbox |
+| **Integration & automation** | n8n | External system connectors, simple automations |
+| **Platform dashboard** | Custom (built-in) | Process stats, task overview, hours saved — for all users |
+| **Operations monitoring** | Grafana + OpenTelemetry | Infrastructure health, alerting, ad-hoc analytics — for IT/admins |
+
+### How it fits together
+
+```
+┌─────────────────────────────────────┐
+│            Web Frontend              │
+│    (Process maps, task inbox,        │
+│     dashboards)                      │
+├──────────────┬──────────────────────┤
+│   Flowable   │        n8n           │
+│  (BPMN +     │   (integrations      │
+│   tasks +    │    + automations)    │
+│   dashboard) │                      │
+├──────────────┴──────────────────────┤
+│     PostgreSQL    │  OpenTelemetry  │
+├───────────────────┤  + Grafana     │
+│   (state/audit)   │  (ops only)    │
+└───────────────────┴─────────────────┘
+                  │
+        ┌─────────┼─────────┐
+        │         │         │
+    ┌───┴──┐  ┌──┴───┐  ┌──┴────┐
+    │ KMD  │  │SBSYS │  │OS2Forms│
+    └──────┘  └──────┘  └───────┘
+```
+
+### What you get
+
+- **Map:** BPMN process modeling via Flowable's built-in modeler (or BPMN.io added later)
+- **Automate:** n8n handles integrations and simple automations
+- **Orchestrate:** Flowable manages process execution and human-in-the-loop
+- **Analyze:** Platform dashboard shows process stats and ROI to all users; Grafana provides operational monitoring for IT
+
+### What you don't get (yet)
+
+- AI agent orchestration (add LangGraph when ready)
+- RPA for legacy desktop apps (add Robot Framework when needed)
+- Advanced analytics / ROI measurement (evolve the platform dashboard)
+
+### Strengths
+
+- Three components — manageable to operate
+- Fast to stand up (weeks, not months)
+- Proves the concept before investing in the full stack
+- Each component has a large, active community
+
+### Growth path
+
+```
+Minimal stack (Phase 1)
+  └─ + LangGraph (Phase 2: AI agents)
+       └─ + Robot Framework (Phase 3: RPA)
+            └─ + Keycloak (Phase 4: SSO/roles)
+                 └─ + BPMN.io (Phase 5: visual modeler)
+```
+
+---
+
+## Two Dashboard Layers
+
+An important distinction: the platform has **two kinds of dashboards** serving different audiences.
+
+### Platform dashboard (built into the app)
+
+This is what all users see — process owners, caseworkers, managers. It shows:
+
+- Active processes, completion rates, task counts
+- Hours saved, estimated ROI
+- Process bottlenecks (where are things stuck?)
+- Personal task overview
+
+This is a custom-built part of the web frontend, pulling data from Flowable's process engine and PostgreSQL. It does not require Grafana.
+
+### Operations dashboard (Grafana — IT/admins only)
+
+This is where IT monitors the platform itself. It shows:
+
+- Infrastructure health — is Flowable responding? n8n queue depth? Database connections?
+- Error rates and alerting — "n8n automation X has failed 3 times in the last hour"
+- Detailed analytics — ad-hoc queries like "average completion time for building permits by month over the last year"
+- SLA monitoring — "3 tasks have breached their 48-hour SLA"
+- Resource utilization — CPU, memory, disk across all components
+
+Grafana connects to OpenTelemetry (for infrastructure metrics) and PostgreSQL (for process data). It's accessible via a separate URL or linked from an admin section in the platform.
+
+| | Platform dashboard | Grafana (ops) |
+|---|---|---|
+| **Audience** | Everyone | IT / admins |
+| **Purpose** | Business value, task overview | Infrastructure health, alerting |
+| **Data source** | Flowable + PostgreSQL | OpenTelemetry + PostgreSQL |
+| **Built by** | Us (part of the app) | Configuration (Grafana dashboards) |
+| **Access** | Main navigation | Admin section / separate URL |
+
+---
+
+## Deployment
+
+Both options should be deployed as containers (Docker/Kubernetes) for consistency and scalability. All components support containerized deployment.
+
+### Infrastructure requirements (minimal stack)
+
+| Component  | CPU         | Memory    | Storage   |
+| ---------- | ----------- | --------- | --------- |
+| Flowable   | 2 cores     | 4 GB      | 10 GB     |
+| n8n        | 1 core      | 2 GB      | 5 GB      |
+| Grafana    | 1 core      | 1 GB      | 5 GB      |
+| PostgreSQL | 2 cores     | 4 GB      | 50 GB     |
+| **Total**  | **6 cores** | **11 GB** | **70 GB** |
+
+This fits comfortably on a single server or a small Kubernetes cluster.
+
+---
+
+## Recommendation
+
+**Start with Option B.** Get a working platform with one real process running end-to-end. Use it to demonstrate value and build organizational buy-in. Then grow toward Option A based on actual needs, not assumptions.