Unique AI Conduct Space — Unique AI Documentation
Unique AI Conduct Space
5 min read
Overview
Unique AI Conduct is a space type that provides users with a fully autonomous AI agent capable of executing code, processing files, and completing complex multi-step tasks. Unlike Unique AI Chat — which is a conversational agent that answers questions — Conduct gives the agent a sandboxed coding environment (Python and Bash), access to organizational tools, and the ability to work through long-running tasks independently.
Conduct is designed for workflows where the AI needs to do work, not just provide answers: data analysis, file transformation, report generation, research synthesis, and any task that benefits from code execution and autonomous multi-step planning.
Who is it for?
Data analysts, developers, compliance officers, operations teams, and any professionals whose work involves data processing, file manipulation, code execution, or complex multi-step tasks. Conduct is for teams that need the AI to produce deliverables — not just answer questions.
Who should have access
To create and configure Conduct spaces, you need the admin.space.write Zitadel authorization. Consult your IAM administrator for access.
Conduct spaces are best suited for users who work with data, documents, and multi-step workflows. Consider your organization's use cases when deciding which teams get access.
Benefits
Autonomous task execution — The agent plans, codes, and delivers results without requiring step-by-step user guidance
Full coding environment — Python and Bash in a sandboxed container, with common data science and file processing libraries pre-installed
Long-running workflows — Handles complex, multi-step tasks that would be impractical in a basic chat interaction
Skills extensibility — Pre-packaged capability bundles can be loaded into the agent's environment to specialize its behavior for domain-specific workflows
Organizational tool access — Knowledge base search and web search (within egress policies) complement the coding capabilities
Use Cases
How Conduct differs from other space types: Chat provides a conversational agent for Q&A. Agentic Tables handles structured data extraction at scale. Translator handles multi-language workflows. Conduct is for autonomous, code-driven task execution — the agent gets a full environment and works through complex tasks independently.
Analyst workspace: Upload financial reports, run analysis with Code Interpreter, generate charts and summary workbooks
Compliance review: Process regulatory documents, extract key data points, cross-reference with internal policies
Data engineering: Clean messy datasets, transform file formats, merge data sources, produce standardized outputs
Research synthesis: Search the knowledge base, gather information across multiple documents, compile structured findings
Reporting automation: Generate formatted reports from raw data using Skills and code execution
Step-by-Step Guide
Step 1: Create a New Conduct Space
- Navigate to the Admin Interface → Spaces
- Click Create Space
- Select the Swappable Intelligence space type
Naming note: In the current release, this space type appears as "Swappable Intelligence" in the Admin Interface. It will be renamed to "Unique AI Conduct" in an upcoming release. The functionality is identical.
- Enter a name for the space.
Step 2: Select the Agent Harness
A harness is the agent runtime that powers the Conduct space. It determines which AI provider and models are used, how the agent executes code, and what SDK capabilities are available. The harness is the "swappable intelligence" — the same sandbox infrastructure can serve different agent runtimes.
Available Harnesses:
| Harness | Status | AI Provider | Description | Models |
|---|---|---|---|---|
| Claude Code | Experimental | Anthropic (via LiteLLM or Bedrock) | Autonomous coding agent powered by the Claude Agent SDK. Plans, writes code, processes files, and uses MCP tools. The primary and recommended harness. | claude-opus-4-6 |
claude-sonnet-4-6 |
||||
claude-haiku-4-5 |
||||
| Pi Agent | Planned | — | Future alternative harness. Not yet available. | |
| Codex | Planned | — | Future alternative harness. Not yet available. |
- As of today, you can find the Harness settings under Configuration > Advanced Settings > Coding Agent. Here you can adjust parameters such as Model, Thinking Level, Max Turns, Budget and Compaction.
Step 3: Configure Tools
Swappable Intelligence automatically has code execution and skill tools built in. You can directly interact with these via the agent and ask about availability.
- Navigate to the Tools section. For Conduct spaces, the included tools are Internal Search and Web Search.
Tips & Tricks
| Tip | Details |
|---|---|
| Start with Skills | If your team repeats the same workflows (report generation, data cleaning), package them as Skills. This gives consistent, high-quality results. |
| Set container timeout appropriately | For teams doing quick analysis, 10 minutes may suffice. For longer workflows, use the maximum 20 minutes. |
| Monitor model costs | Conduct tasks use more tokens than Chat conversations. Claude Opus is the most capable but pricier — consider Claude Sonnet for balanced cost/performance or Haiku for routine tasks. |
FAQs from Users
Q: How is this different from Unique AI Chat?
A: Chat answers questions. Conduct does work — it writes and runs code, processes files, and completes multi-step tasks autonomously. If you need a quick answer, use Chat. If you need the AI to produce something, use Conduct.
Q: Why did my session expire?
A: Container sessions expire after the configured inactivity timeout (max 20 minutes). Download your files before stepping away. The next message starts a fresh session.
Q: Can the agent access the internet?
A: The agent can use the Web Search tool within your organization's egress policies, but it cannot browse the open web or make arbitrary external requests.
Q: Can I install Python packages?
A: No. The container comes with common libraries pre-installed (pandas, matplotlib, numpy, etc.), but arbitrary pip install is not available for security reasons.
Security
- All code execution runs in Kata Containers microVMs — hardware-level isolation with a dedicated guest kernel per session
- Identity is stored as Kubernetes pod labels, not environment variables — a compromised sandbox cannot read its own identity or forge platform API calls
- Containers have default-deny network egress — all external traffic routed through a dedicated Egress Gateway with TLS inspection and DLP logging
- Each sandbox is scoped to a single user and chat session — no cross-tenant or cross-session data leakage
- Workspaces are ephemeral — all data is destroyed when the session ends; cross-turn persistence via zip checkpoint only
automountServiceAccountToken: false— the sandbox pod cannot access the Kubernetes API
API
Space creation and configuration is available via the GraphQL API using the CreateAssistant mutation. See the SDK documentation in the Developers section.
Limitations
- Harness-dependent models — Compatible models are determined by the selected harness. Currently only Claude models are supported (Opus, Sonnet, Haiku).
- No persistent workspace storage — v1 uses emptyDir + zip checkpoint. PVC-backed persistence is planned for a future release.
- Restricted egress — No open web browsing, no arbitrary API calls. All external traffic goes through the Egress Gateway.
- One workspace per chat — Workspaces are scoped to
chat_id, not per-user or per-space. - Concurrent turns serialized — Only one turn at a time per chat session.
- File upload limits — Max 10 files, 100MB per file. Checkpoint max 100MB.