KlicForge Docs
Agents

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.

An agent's name and description are internal — used for the dashboard's agent list, for routing and delegation, and as system context the model sees. What a customer sees on the widget's welcome screen is a separate, optional field; see the web widget.

Managing agents

In the dashboard at app.klicforge.ai:

  • List agents — open My Agents in the sidebar and select Manage agents to see every agent with its status, model and description. See finding your way around.
  • Create an agentCreate new 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 the agent's Sandbox tab, or the preview on the agent's Widget tab.

The agent editor

TabWhat it controls
OverviewMetadata, current model, attached skills, tools and knowledge sources
ModelThe model this agent runs on, plus fallback models
SkillsWhich skills are attached
ToolsWhich tools the agent may call
GuardrailsPer-agent safety controls
System PromptThe four core prompt files
ChannelsConnect Telegram, WhatsApp and other channels
ConversationsA read-only index of every conversation with this agent
Scheduled TasksProactive and recurring messages
EvaluationsTest suites and runs for this agent
WidgetWidget appearance and the embed snippet
SettingsName, description, session behaviour, escalation, memory and versioning

Knowledge sources are chosen when you create the agent. To change them afterward, ask the in-dashboard assistant rather than looking for a Knowledge tab.

Editing with the assistant

Instead of working through the editor tabs, you can describe the change to the in-dashboard assistant — "make replies shorter", "add a starter question about refunds", "stop it offering follow-ups".

The assistant proposes a change set: a card in the chat listing what would change, with a risk level (low for cosmetic or additive edits, medium for behavioural ones, high for destructive or breaking ones). Review it, then approve to apply or discard. Nothing is applied without approval, and the card keeps its status — approved, applied or discarded — when you come back to the conversation later.

A change set can touch the core prompt files, communication style, starter questions, name and description, model and fallbacks, skills, tools, knowledge sources, guardrails and escalation — knowledge sources included, even though editing them isn't available from the editor tabs. For a versioned agent, an applied change set edits the draft — production stays on the published version until you publish.

The same approval flow covers edits to your custom skills — the card names the skill it changes rather than an agent.

Status

StatusBehaviour
activeAccepts messages and responds normally
inactiveRejects incoming messages with an unavailable notice
draftVisible 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.

Voice and point of view

The Communication Style card controls how an agent sounds, including its point of view:

Point of viewEffect
Speaks as the businessAnswers use "we" and "our" — "our rates start at…"
Neutral assistantAnswers as a helpful third party rather than a representative
UnsetNo instruction is added; the agent's wording is governed by its prompts

Content retrieved from your knowledge sources is always treated as your workspace's own material, so an agent does not describe your business from the outside regardless of this setting.

Activity display

The Settings tab controls what a contact sees while the agent works:

  • Activity display mode — from nothing but a typing indicator through to a step-by-step timeline with timings.
  • Collapse activity after response — hide the activity block once the answer arrives.
  • Send an interim reply — the agent opens with one short line about what it is doing, written for that specific question in its own voice. Off by default, and unavailable when activity display is off.

Memory and intelligence

The Settings tab groups the intelligence features:

  1. Business domain — tells the platform what kind of business this agent serves. Must be set before memory can be enabled, and gives Business Intelligence a head start, though it is optional there. See domain packs.
  2. Memory — persistent per-contact memory across conversations. Requires a business domain and a plan that includes it. See memory.
  3. Business intelligence — structured event extraction and a self-building vocabulary of your business, on every plan with nothing to configure first. See Intelligence.

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.

Was this page helpful?

On this page