Agents
What an agent is, how it is configured, and what each tab in the agent editor controls.
An agent combines an identity, a model, skills, tools, knowledge sources and safety guardrails into one deployable unit. Agents are configured entirely in the dashboard — creating or changing one requires no code.
Managing agents
In the dashboard at app.klicforge.ai:
- List agents — select Agents in the sidebar to see every agent with its status, model and description.
- Create an agent — New Agent opens the creation wizard.
- Edit an agent — select any agent to open its detail view.
- Change status — use the status control on the Overview tab.
- Test — use Widget Sandbox in the sidebar, or the preview on the agent's Widget tab.
The agent editor
| Tab | What it controls |
|---|---|
| Overview | Metadata, current model, attached skills, tools and knowledge sources |
| Model | The model this agent runs on, plus fallback models |
| Skills | Which skills are attached |
| Knowledge | Which knowledge sources the agent can retrieve from |
| Tools | Which tools the agent may call |
| Guardrails | Per-agent safety controls |
| System Prompt | The four core prompt files |
| Channels | Connect Telegram, WhatsApp and other channels |
| Scheduled Tasks | Proactive and recurring messages |
| Evaluations | Test suites and runs for this agent |
| Widget | Widget appearance and the embed snippet |
| Settings | Name, description, session behaviour, escalation, memory and versioning |
Status
| Status | Behaviour |
|---|---|
active | Accepts messages and responds normally |
inactive | Rejects incoming messages with an unavailable notice |
draft | Visible in the dashboard, not reachable from the widget or a channel |
Model and fallbacks
Each agent runs on one model chosen from the catalog. You can add fallback models so the agent automatically retries with an alternative if the primary is unavailable.
Temperature (0.0–1.0) controls consistency. Lower values produce more precise, repeatable answers; higher values are more conversational. Support and factual agents generally want 0.1–0.4.
Sessions
- Session TTL — how long a conversation stays active without activity. Once it expires, the next message starts a fresh conversation. Defaults differ per channel.
- Max messages — how much conversation history is carried as context.
Memory and intelligence
The Settings tab groups the intelligence features:
- Business domain — tells the platform what kind of business this agent serves. Must be set before memory or business intelligence can be enabled.
- Memory — persistent per-contact memory across conversations. See memory.
- Business intelligence — structured event extraction and analytics.
Both memory and business intelligence stay locked until a business domain is selected, and each requires a plan that includes it.
Versioning
By default every edit goes live immediately. Turning on versioning lets you edit a draft while production keeps serving the last published version, with history and rollback. See agent versioning.