Convoship ships two complementary bot types. They appear as separate items in the workspace sidebar — Assistants under /app/assistants and Agents under /app/agents — and you can chain them together in Workflows.
At a glance
| Assistant (scripted) | Agent (agentic) | |
|---|---|---|
| Sidebar label | Assistants | Agents |
| Route | /app/assistants | /app/agents |
| How it decides | Intent match → fixed sub-flow graph | LLM reasons, picks tools, asks for missing info |
| Best for | Regulated, repeatable journeys (KYC, intake forms) | Open-ended tasks with APIs (lookup, transfer, advise) |
| You design | Intents, entities, canvas nodes, publish versions | Mission, tasks, tools, persona, guardrails |
| Runtime | Deterministic node execution | ReAct-style loop with tool calls and trace |
| Empty workspace | Shows “New assistant” hero — no demo data seeded | Shows “New Agent” card — no demo data seeded |
When to use an Assistant
- Every turn must follow an approved path you can audit node-by-node.
- You already have a Draw.io or BPMN sketch to import as intents.
- Compliance requires explicit prompts, entity capture, and published versions.
- Channels need a simple web widget with predictable fallback and no-input handling.
When to use an Agent
- Users phrase requests many different ways and the bot must infer intent.
- The bot should call workspace tools (HTTP APIs) and combine results.
- You want persona, memory slots, guardrails (auth, redact, budget), and a playground.
- You need conversation traces showing think → tool → ask steps for debugging.
Mixing both in Workflows
Workflows support two editors: primitive chains (triggers, Assistants, Agents, decide, webhook, human, notify) and legacy React Flow graphs (flow-agent, instruction_agent, router, tool, nested workflow nodes). A common pattern: an Agent qualifies the user and hands off to a scripted Assistant for the regulated intake form.
Creating each type
| Step | Assistant | AI Agent |
|---|---|---|
| Start | Assistants → New assistant wizard (blank or import) | Agents → New Agent wizard (/app/agents/new) |
| Configure | Intents, flow canvas, entities, tools, publish | Mission, tasks, tools, persona, guardrails |
| Test | Floating simulator on any agent tab | Playground tab with live trace |
| Ship | Publish version + Channels cdp_* deployment token | Publish on Deploy tab + publicToken embed (see /docs/agentic-publish-deploy) |
Naming in the product
“Assistants” always means scripted flow bots. “Agents” (or AI Agents) always means the agentic runtime. Counts in the sidebar are live from your workspace — nothing is pre-seeded.
Next steps
- Build a scripted bot — see Assistants and Flow builder docs.
- Build an agentic bot — /docs/agentic-ai, tool handlers, publish & embed, production settings.
- Orchestrate both — see Workflows for chain editor and primitives.