{"id":"a121795c-233d-4184-90f3-203b043a83ee","slug":"redhat-ai-workflow","kind":"skill","name":"redhat-ai-workflow","summary":"AI-powered workflow automation tools for Red Hat engineering","owner":"dmzoneill","repoUrl":"https://github.com/dmzoneill/redhat-ai-workflow","license":"Apache-2.0","licenseTier":"permissive","trust":"community","stars":5,"match":null,"fewStars":false,"format":"skill","createdAt":"2025-12-22T11:07:03.000Z","addedAt":"2026-10-21T16:30:14.585Z","logoUrl":"https://avatars.githubusercontent.com/u/15192260?u=855ffe444f8355eab9298f62b19fbc382c609daa&v=4","linkOnly":false,"collection":null,"skillPath":null,"categories":["writing"],"tags":["ai","automation","python","redhat","workflow"],"runtime":"python","local":true,"cloudCapable":false,"cloudCapability":"unknown","cloudReadyOnPlatform":false,"needsApiKey":false,"reviewed":false,"syncedAt":"2026-10-25T21:47:17.432Z","sample":false,"url":"https://conduits.dev/tools/redhat-ai-workflow","language":"Python","transports":["stdio"],"install":{"pypi":"ai-workflow"},"requirements":{"env":[],"upstreamMayCharge":false},"tools":null,"readme":"# AI Workflow\n\n
\n \n
\n\n\n \n \n\n\n
\n\n[](https://modelcontextprotocol.io/)\n[](https://www.python.org/)\n[](https://anthropic.com/)\n[](https://cursor.sh/)\n\n\n[](LICENSE)\n\n**Transform Claude into your personal DevOps engineer, developer assistant, and incident responder.**\n\n_Works with both **Claude Code** and **Cursor IDE**_\n\n[Getting Started](#quick-start) •\n[Commands](docs/commands/README.md) •\n[Skills](docs/skills/README.md) •\n[Personas](docs/personas/README.md) •\n[Tool Modules](docs/tool-modules/README.md) •\n[Architecture](docs/architecture/README.md)\n\n
\n\n---\n\n## ✨ What is This?\n\nAI Workflow is a **comprehensive MCP (Model Context Protocol) server** that gives Claude AI superpowers for software development:\n\n| Capability | Description |\n| ----------------------- | -------------------------------------------------- |\n| 🔧 **Execute Actions** | Create branches, update Jira, deploy code |\n| 🧠 **Remember Context** | Track your work across sessions |\n| 🎭 **Adopt Personas** | DevOps, Developer, Incident modes |\n| ⚡ **Run Workflows** | Multi-step skills that chain tools |\n| 🔄 **Auto-Heal** | Detect failures, fix auth/VPN, retry automatically |\n| 🔍 **Self-Debug** | Analyze and fix its own tools |\n\n---\n\n## Quick Start\n\n### 1️⃣ Clone & Install\n\n```bash\ngit clone https://github.com/yourusername/ai-workflow.git ~/src/ai-workflow\ncd ~/src/ai-workflow\n\n# Using UV (recommended - fast!)\nuv venv\nuv sync\n```\n\n> **Don't have UV?** Install it: `curl -LsSf https://astral.sh/uv/install.sh | sh`\n\nFor development tools (pytest, black, flake8, mypy), also run:\n\n```bash\nuv sync --extra dev\n```\n\n### 2️⃣ Configure Your IDE\n\n\n🔷 Claude Code (claude.ai/code)\n\nCreate `.mcp.json` in your **project root**:\n\n```json\n{\n \"mcpServers\": {\n \"aa_workflow\": {\n \"command\": \"bash\",\n \"args\": [\n \"-c\",\n \"cd ~/src/ai-workflow && source .venv/bin/activate && python3 -m server\"\n ]\n }\n }\n}\n```\n\nThen restart Claude Code or run `/mcp` to reload.\n\n\n\n\n⬛ Cursor IDE\n\nCreate `.cursor/mcp.json` in your **project directory**:\n\n````json\n{\n \"mcpServers\": {\n \"aa_workflow\": {\n \"command\": \"bash\",\n \"args\": [\n \"-c\",\n \"cd ~/src/ai-workflow && source .venv/bin/activate && python3 -m server\"\n ]\n }\n }\n}\n```text\n\nThen restart Cursor (Cmd/Ctrl+Shift+P → \"Reload Window\").\n\n\n\n> **Default Persona:** The server starts with the `developer` persona loaded by default (~78 tools). Use `persona_load(\"devops\")` to switch.\n>\n> **Tool Organization:** Tools are split into `_basic` (used in skills, 188 tools) and `_extra` (rarely used, 75 tools) to reduce context window usage by 30%.\n\n### 3️⃣ Restart and Go\n\n```text\nYou: Load the developer persona\n\nClaude: 👨💻 Developer Persona Loaded\n Tools: workflow, git_basic, gitlab_basic, jira_basic (~78 tools)\n\nYou: Start working on AAP-12345\n\nClaude: [Runs start_work skill]\n ✅ Created branch: aap-12345-implement-api\n ✅ Updated Jira: In Progress\n Ready to code!\n````\n\n---\n\n## 💬 Slack Bot Setup\n\nThe Slack bot is an autonomous agent that monitors channels, responds to queries, and investigates alerts.\n\n### 1. Get Slack Credentials\n\nThe bot uses Slack's web API. Extract credentials from Chrome:\n\n```bash\nuv add pycookiecheat\npython scripts/get_slack_creds.py\n```\n\n### 2. Configure\n\nAdd to `config.json`:\n\n```json\n{\n \"slack\": {\n \"auth\": {\n \"xoxc_token\": \"xoxc-...\",\n \"d_cookie\": \"xoxd-...\",\n \"workspace_id\": \"E...\",\n \"host\": \"your-company.enterprise.slack.com\"\n },\n \"channels\": {\n \"team\": { \"id\": \"C01234567\", \"name\": \"my-team\" }\n },\n \"alert_channels\": {\n \"C089XXXXXX\": { \"name\": \"alerts\", \"environment\": \"stage\" }\n }\n }\n}\n```\n\n### 3. Configure Claude AI (Optional)\n\nFor autonomous responses:\n\n```bash\n# Vertex AI (recommended)\nexport CLAUDE_CODE_USE_VERTEX=1\nexport ANTHROPIC_VERTEX_PROJECT_ID=\"your-gcp-project\"\n\n# Or Anthropic API\nexport ANTHROPIC_API_KEY=\"your-key\"\n```\n\n### 4. Run\n\n```bash\n# Test credentials\nmake slack-test\n\n# Foreground (Ctrl+C to stop)\nmake slack-daemon\n\n# Background with D-Bus control\nmake slack-daemon-bg\nmake slack-status\nmake slack-daemon-logs\nmake slack-daemon-stop\n```\n\nSee [Slack Persona docs](docs/personas/slack.md) for full setup guide.\n\n---\n\n## 🎭 Personas (Tool Profiles)\n\n> **Note:** \"Agents\" in this project are **tool configuration profiles** (personas), not separate AI instances. When you \"load an agent,\" you're configuring which tools Claude has access to.\n\nSwitch personas to get different tool sets. See [full persona reference](docs/personas/README.md).\n\n| Persona | Command | Tools | Focus |\n| ------------------------------------------ | ------------------------ | ----- | -------------------- |\n| [👨💻 developer](docs/personas/developer.md) | `Load developer persona` | ~78 | Daily coding, PRs |\n| [🔧 DevOps](docs/personas/devops.md) | `Load devops persona` | ~74 | Deployments, K8s |\n| [🚨 incident](docs/personas/incident.md) | `Load incident persona` | ~78 | Production debugging |\n| [📦 release](docs/personas/release.md) | `Load release persona` | ~91 | Shipping releases |\n| [💬 Slack](docs/personas/slack.md) | `Load slack persona` | ~85 | Slack bot daemon |\n\n```mermaid\ngraph LR\n DEV[👨💻 Developer] --> |\"persona_load\"| DEVOPS[🔧 DevOps]\n DEVOPS --> |\"persona_load\"| INCIDENT[🚨 Incident]\n INCIDENT --> |\"persona_load\"| DEV\n\n style DEV fill:#3b82f6,stroke:#2563eb,color:#fff\n style DEVOPS fill:#10b981,stroke:#059669,color:#fff\n style INCIDENT fill:#ef4444,stroke:#dc2626,color:#fff\n```\n\n---\n\n## Skills\n\nSkills are reusable multi-step workflows with **built-in auto-healing**. See [full skills reference](docs/skills/README.md).\n\n### Daily Workflow\n\n| Time | Command | What It Does |\n| ---------- | ----------------------- | ---------------------------------- |\n| ☕ Morning | `/coffee` | Email, PRs, calendar, Jira summary |\n| 💻 Work | `/start-work AAP-12345` | Create branch, update Jira |\n| 🚀 Submit | `/create-mr` | Validate, lint, create MR |\n| 🍺 Evening | `/beer` | Wrap-up, standup prep |\n\n### Popular Skills\n\n| Skill | Description | Auto-Heal |\n| -------------------------------------------------------- | -------------------------- | ------------- |\n| [☕ coffee](docs/skills/coffee.md) | Morning briefing | ✅ |\n| [🍺 beer](docs/skills/beer.md) | End-of-day wrap-up | ✅ |\n| [⚡ start_work](docs/skills/start_work.md) | Begin Jira issue | ✅ VPN + Auth |\n| [🚀 create_mr](docs/skills/create_mr.md) | Create MR + Slack notify | ✅ VPN + Auth |\n| [✅ mark_mr_ready](docs/skills/mark_mr_ready.md) | Mark draft as ready | ✅ |\n| [👀 review_pr](docs/skills/review_pr.md) | Review MR | ✅ VPN + Auth |\n| [🔄 sync_branch](docs/skills/sync_branch.md) | Rebase onto main | ✅ VPN |\n| [📋 standup_summary](docs/skills/standup_summary.md) | Generate standup | ✅ |\n| [🧪 test_mr_ephemeral](docs/skills/test_mr_ephemeral.md) | Deploy to ephemeral | ✅ VPN + Auth |\n| [🚨 investigate_alert](docs/skills/investigate_alert.md) | Triage alerts | ✅ VPN + Auth |\n| [🎫 create_jira_issue](docs/skills/create_jira_issue.md) | Create Jira issue | ✅ |\n| [✅ close_issue](docs/skills/close_issue.md) | Close issue with summary | ✅ VPN |\n| [📚 update_docs](docs/skills/update_docs.md) | Check/update documentation | ✅ |\n\n### 🔄 Auto-Heal: Tools + Skills\n\n**All MCP tools** include auto-healing via Python decorators. **All skills** also auto-retry with VPN/auth fixes.\n\n#### Tool-Level Auto-Heal\n\nWhen a decorated tool fails due to VPN or auth issues:\n\n1. **Detects** the failure pattern (network timeout, unauthorized, forbidden)\n2. **Fixes** by calling `vpn_connect()` or `kube_login()`\n3. **Retries** the operation automatically\n4. **Logs** the fix to `memory/learned/tool_failures.yaml` for learning\n\n```python\nfrom server.auto_heal_decorator import auto_heal\n\n@auto_heal() # Covers all tool types\n@registry.tool()\nasync def git_push(repo: str, branch: str = \"\") -> str:\n \"\"\"Push commits - auto-heals auth failures.\"\"\"\n ...\n```\n\n| Decorator | Use Case | Coverage |\n| ------------------------ | ------------------------------- | ----------------------- |\n| `@auto_heal()` | All tools (auto-detect cluster) | Git, GitLab, Jira + all |\n| `@auto_heal_ephemeral()` | Bonfire namespace tools | Bonfire |\n| `@auto_heal_konflux()` | Tekton pipeline tools | Konflux |\n| `@auto_heal_k8s()` | Kubectl tools | K8s, Prometheus |\n\n#### Skill-Level Auto-Retry\n\nSkills automatically retry failing tools after applying fixes:\n\n1. **Checks memory** for known fixes via `check_known_issues()`\n2. **Detects** auth/network patterns in error output\n3. **Applies** VPN connect or kube_login based on context\n4. **Retries** the tool call once after successful fix\n\nThis means skills like `start_work`, `create_mr`, and `deploy_ephemeral` self-heal transparently.\n\n---\n\n## 🎯 Slash Commands\n\n66 slash commands for quick access. See [full commands reference](docs/commands/README.md).\n\n| Category | Commands |\n| --------------------- | -------------------------------------------------------------------------------------------------------------------------- |\n| ☀️ **Daily** | `/coffee` `/beer` `/standup` `/weekly-summary` |\n| 🔧 **Development** | `/start-work` `/create-mr` `/mark-ready` `/close-issue` `/sync-branch` `/rebase-pr` `/hotfix` |\n| 👀 **Review** | `/review-mr` `/review-all-open` `/check-feedback` `/check-prs` `/close-mr` |\n| 🧪 **Testing** | `/deploy-ephemeral` `/test-ephemeral` `/check-namespaces` `/extend-ephemeral` `/run-local-tests` |\n| 🚨 **Operations** | `/investigate-alert` `/debug-prod` `/release-prod` `/env-overview` `/rollout-restart` `/scale-deployment` `/silence-alert` |\n| 📋 **Jira** | `/jira-hygiene` `/create-issue` `/clone-issue` `/sprint-planning` |\n| 📚 **Documentation** | `/check-docs` `/update-docs` |\n| 🔍 **Discovery** | `/tools` `/personas` `/list-skills` `/smoke-tools` `/smoke-skills` `/memory` |\n| 📅 **Calendar** | `/my-calendar` `/schedule-meeting` `/setup-gmail` `/google-reauth` |\n| 🔐 **Infrastructure** | `/vpn` `/konflux-status` `/appinterface-check` `/ci-health` `/cancel-pipeline` `/check-secrets` `/scan-vulns` |\n\n### Example Workflow\n\n```bash\n/coffee # Morning briefing\n/start-work AAP-12345 # Begin work on issue\n# ... code ...\n/update-docs # Check if docs need updating\n/create-mr # Create merge request (auto-checks docs)\n/deploy-ephemeral # Test in ephemeral\n/mark-ready # Remove draft, notify team (auto-checks docs)\n# ... review cycle ...\n/close-issue AAP-12345 # Wrap up\n/beer # End of day summary\n```\n\n---\n\n## 📚 Documentation Checks\n\nRepositories can have automatic documentation checks before creating MRs. Configure in `config.json`:\n\n````json\n\"my-repo\": {\n \"docs\": {\n \"enabled\": true,\n \"path\": \"docs/\",\n \"readme\": \"README.md\",\n \"api_docs\": \"docs/api/\",\n \"diagrams\": [\"docs/architecture/*.md\"],\n \"check_on_mr\": true\n }\n}\n```text\n\nWhen enabled, `/create-mr` and `/mark-ready` will:\n- Scan for changed files in the branch\n- Check README.md for broken links\n- Review API docs if endpoints changed\n- Check mermaid diagrams if architecture changed\n- Report issues and suggestions (non-blocking)\n\n---\n\n## Tool Modules\n\n**263 tools** across 16 modules, split into **188 basic** (used in skills, 71%) and **75 extra** (rarely used, 29%). See [full MCP server reference](docs/tool-modules/README.md).\n\n> **Performance:** Loading basic tools only reduces context window usage by **30%** while maintaining full functionality for common workflows.\n\n| Module | Total | Basic (Used) | Extra (Unused) | Description |\n|--------|-------|--------------|----------------|-------------|\n| [workflow](docs/tool-modules/workflow.md) | 18 | 18 | 0 | Core: agents, skills, memory, vpn, kube_login |\n| [git](docs/tool-modules/git.md) | 30 | 27 | 3 | Git operations (90% usage) |\n| [gitlab](docs/tool-modules/gitlab.md) | 30 | 16 | 14 | MRs, pipelines, code review (53% usage) |\n| [jira](docs/tool-modules/jira.md) | 28 | 17 | 11 | Issue tracking (61% usage) |\n| [k8s](docs/tool-modules/k8s.md) | 28 | 22 | 6 | Kubernetes operations (79% usage) |\n| [bonfire](docs/tool-modules/bonfire.md) | 20 | 10 | 10 | Ephemeral environments (50% usage) |\n| [konflux](docs/tool-modules/konflux.md) | 35 | 22 | 13 | Build pipelines (63% usage) |\n| [prometheus](docs/tool-modules/prometheus.md) | 13 | 5 | 8 | Metrics queries (38% usage) |\n| [kibana](docs/tool-modules/kibana.md) | 9 | 1 | 8 | Log search (11% usage) |\n| [alertmanager](docs/tool-modules/alertmanager.md) | 7 | 4 | 3 | Alert management (57% usage) |\n| [quay](docs/tool-modules/quay.md) | 7 | 5 | 2 | Container registry (71% usage) |\n| [slack](docs/tool-modules/slack.md) | 9 | 6 | 3 | Slack integration (67% usage) |\n| [google_calendar](docs/tool-modules/google_calendar.md) | 6 | 6 | 0 | Calendar & meetings (100% usage) |\n| [appinterface](docs/tool-modules/appinterface.md) | 7 | 4 | 3 | GitOps config (57% usage) |\n| [lint](docs/tool-modules/lint.md) | 7 | 1 | 6 | Python/YAML linting (14% usage) |\n| [dev_workflow](docs/tool-modules/dev_workflow.md) | 9 | 9 | 0 | Development helpers (100% usage) |\n\n> Plus **45+ shared parsers** in `scripts/common/parsers.py` and **config helpers** in `scripts/common/config_loader.py`\n\nSee [MCP Server Architecture](docs/architecture/README.md) for implementation details.\n\n---\n\n## 🛠️ Auto-Debug & Learning Loop\n\nWhen tools fail, Claude can fix them **and remember the fix forever**:\n\n```text\nTool: ❌ Failed to release namespace\n 💡 Known Issues Found!\n Previous fix for `bonfire_release`: Add --force flag\n\n 💡 Auto-fix: debug_tool('bonfire_namespace_release')\n```text\n\n### The Learning Loop\n\n```text\n┌────────────────────────────────────────────────────────────────┐\n│ Tool fails → Check memory → Apply known fix → ✓ │\n│ ↓ │\n│ Unknown? → debug_tool() → Fix code → learn_tool_fix() → ✓ │\n│ ↓ │\n│ Saved to memory forever │\n└────────────────────────────────────────────────────────────────┘\n```text\n\n### Key Tools\n\n| Tool | Purpose |\n|------|---------|\n| `check_known_issues(tool, error)` | Check if we've seen this before |\n| `debug_tool(tool, error)` | Analyze source and propose fix |\n| `learn_tool_fix(tool, pattern, cause, fix)` | Save fix to memory |\n\n### Session Start with Memory\n\nWhen you start a session with `session_start()`, the system automatically:\n\n1. **Loads current work state** - Active issues, branches, MRs\n2. **Loads learned patterns** - Shows count of patterns by category\n3. **Shows loaded tools** - Which tool modules are active\n4. **Provides guidance** - Prefer MCP tools over raw CLI commands\n\n```text\nYou: session_start(agent=\"developer\")\n\nClaude: 📋 Session Started\n 🧠 Learned Patterns: 12 patterns loaded\n - Jira CLI: 3 patterns\n - Error handling: 5 patterns\n - Authentication: 4 patterns\n 🛠️ Currently Loaded Tools: git, gitlab, jira (~78 tools)\n```text\n\n### Memory Files\n\n| File | Purpose |\n|------|---------|\n| `memory/learned/tool_fixes.yaml` | Tool-specific fixes from auto-remediation |\n| `memory/learned/patterns.yaml` | General error patterns and solutions |\n| `memory/learned/runbooks.yaml` | Operational procedures that worked |\n| `memory/learned/tool_failures.yaml` | Auto-heal history with success/failure tracking |\n| `memory/state/current_work.yaml` | Active issues, branches, MRs |\n| `memory/sessions/*.yaml` | Session logs for continuity |\n\n---\n\n## 🤖 Background Daemons\n\n6 background services provide autonomous functionality:\n\n| Daemon | Purpose | Service |\n|--------|---------|---------|\n| **Slack** | Real-time message monitoring & AI response | `bot-slack.service` |\n| **Sprint** | Automated Jira issue processing | `bot-sprint.service` |\n| **Meet** | Google Meet auto-join & note-taking | `bot-meet.service` |\n| **Video** | Virtual camera for meeting overlays | `bot-video.service` |\n| **Session** | Cursor chat synchronization | `bot-session.service` |\n| **Cron** | Scheduled job execution | `bot-cron.service` |\n\nAll daemons use D-Bus IPC for control. See [Daemons Guide](docs/daemons/README.md) for details.\n\n```bash\n# Quick start\nsystemctl --user start bot-slack bot-cron\n\n# Check status\npython scripts/health_check.py\n\n# Control via CLI\npython scripts/service_control.py status\n````\n\n---\n\n## 📁 Project Structure\n\n```text\nai-workflow/\n├── server/ # MCP server infrastructure\n│ ├── main.py # Server entry point\n│ ├── persona_loader.py # Dynamic persona loading\n│ ├── workspace_state.py # Multi-session management\n│ ├── state_manager.py # Runtime state persistence\n│ ├── websocket_server.py # Real-time skill updates\n│ ├── auto_heal_decorator.py # Auto-heal decorators\n│ ├── usage_pattern_*.py # Layer 5 learning (7 files)\n│ └── utils.py # Shared utilities\n├── tool_modules/ # 20+ tool plugins (aa_git/, aa_jira/, etc.)\n├── personas/ # Persona configs (developer.yaml, devops.yaml)\n├── skills/ # 95+ workflow definitions\n├── memory/ # Persistent context\n│ ├── state/ # Active issues, MRs, environments\n│ ├── learned/ # Patterns, tool fixes, usage patterns\n│ └── knowledge/ # Per-persona project knowledge\n├── extensions/ # IDE integrations\n│ └── aa_workflow_vscode/ # VSCode/Cursor extension (TypeScript)\n├── scripts/ # Daemons and utilities\n│ ├── slack_daemon.py # Slack monitoring daemon\n│ ├── sprint_daemon.py # Sprint automation daemon\n│ ├── meet_daemon.py # Meet bot daemon\n│ ├── cron_daemon.py # Scheduled jobs daemon\n│ ├── session_daemon.py # Session sync daemon\n│ ├── health_check.py # Service health monitoring\n│ ├── service_control.py # Unified CLI control\n│ └── common/ # Shared utilities\n│ ├── dbus_base.py # D-Bus daemon base class\n│ ├── parsers.py # 45+ shared parser functions\n│ └── config_loader.py # Config helpers\n├── systemd/ # Systemd service files\n├── docs/ # Documentation (140+ files)\n├── tests/ # Test suite (25 files)\n├── config.json # Main configuration\n├── .cursor/commands/ # 66+ slash commands (Cursor)\n└── .claude/commands/ # 66+ slash commands (Claude Code)\n```\n\n---\n\n## 📚 Documentation\n\n### Quick Reference\n\n| Document | Description |\n| ----------------------------------------------------- | ---------------------------------- |\n| [Commands Reference](docs/commands/README.md) | 66+ slash commands (Claude/Cursor) |\n| [Skills Reference](docs/skills/README.md) | 95+ workflow skills |\n| [Personas Reference](docs/personas/README.md) | 5 tool configuration profiles |\n| [Tool Modules Reference](docs/tool-modules/README.md) | 20+ tool plugins with 263 tools |\n\n### Architecture\n\n| Document | Description |\n| --------------------------------------------------------------------- | -------------------------------------- |\n| [Architecture Overview](docs/architecture/README.md) | System architecture with diagrams |\n| [MCP Implementation](docs/architecture/mcp-implementation.md) | Server code, persona switching, skills |\n| [Daemon Architecture](docs/architecture/daemons.md) | 6 background services with D-Bus IPC |\n| [Visual Studio Code Extension](docs/architecture/vscode-extension.md) | IDE integration details |\n| [Session Management](docs/architecture/session-management.md) | Multi-chat session handling |\n| [State Management](docs/architecture/state-management.md) | Persistence patterns |\n| [Usage Pattern Learning](docs/architecture/usage-pattern-learning.md) | Layer 5 auto-heal system |\n\n### Operations\n\n| Document | Description |\n| ---------------------------------------- | ---------------------------------- |\n| [Daemons Guide](docs/daemons/README.md) | Background daemon operations |\n| [Learning Loop](docs/learning-loop.md) | Auto-remediation + memory |\n| [IDE Extension](docs/ide-extension.md) | VSCode/Cursor extension setup |\n| [Development Guide](docs/DEVELOPMENT.md) | Contributing and development setup |\n\n---\n\n## 🤝 Contributing\n\n1. Fork the repository\n2. Create a feature branch\n3. Add tests for new functionality\n4. Submit a merge request\n\n---\n\n## 📄 License\n\nMIT License - See [LICENSE](LICENSE) for details.\n\n---\n\n\n \n \n\n\n
\n Built with ❤️ for developers who want AI that actually does things\n
![\"redhat-ai-workflow](\".github/logo.png\"){kind=logo}
\n