# Documentation - [KlicForge documentation](/): Build, configure and operate AI agents for your business — guides for everyone from first-time users to developers integrating KlicForge. - **Use KlicForge** - Getting started - [Quickstart](/getting-started): Sign up, create an agent, test it and put it on your website — the short version. - [Finding your way around](/getting-started/dashboard-navigation): A map of the dashboard sidebar — what each section holds and where to find the thing you are looking for. - [Create your first agent](/getting-started/create-your-first-agent): A detailed walkthrough of building, grounding, testing and publishing a working agent. - Agents - [Agents](/agents): What an agent is, how it is configured, and what each tab in the agent editor controls. - [Agent creation wizard](/agents/creation-wizard): The three routes for creating an agent — templates, a written description, or manual configuration — and when to use each. - [Agent templates](/agents/templates): Pre-built agents for common jobs, copied into your workspace and fully editable. - [Core prompt files](/agents/core-prompt-files): IDENTITY, SOUL, AGENTS and USER — the four files that define how an agent behaves, and how to write each one. - [Agent versioning](/agents/versioning): Edit a draft while production keeps serving the last published version, with history and one-click rollback. - [Models](/agents/models): The model catalog, model tiers, and connecting your own provider account with bring-your-own-key. - [Domain packs](/agents/domain-packs): Tell KlicForge what kind of business an agent serves, so memory and business intelligence extract the right things. - Knowledge - [Knowledge sources](/knowledge): Ground your agent's answers in your own documents — creating sources, uploading files, and choosing how content is retrieved. - [Import a website as knowledge](/knowledge/import-a-website): Scan a website for free, choose how many pages to bring in, and review every generated document before it becomes agent knowledge. - [Assets](/knowledge/assets): Private, reusable files an agent can find and send in chat, distinct from knowledge sources used for grounding answers. - Intelligence - [Intelligence](/intelligence): What KlicForge automatically learns about your business from every conversation — extracted events, a self-building vocabulary, and what still needs review. - Marketplace - [Marketplace](/marketplace): Browse and install agent templates, built-in skills and built-in tools without leaving the page you're on. - Skills and tools - [Skills](/skills-and-tools): Reusable instruction modules that shape how an agent responds, and how they differ from tools. - [Tools](/skills-and-tools/tools): Functions an agent can call to look things up and take actions, including custom webhook tools you define without code. - Data tables - [Data tables](/data-tables): Structured storage your agents can read from and write to — fields, personal data handling, and per-agent permissions. - Channels - [Channels](/channels): How people reach your agent — the web widget, Telegram, WhatsApp and the inbox. - [Web widget](/channels/web-widget): Embed the chat widget on your website, control how it looks, and restrict which domains may load it and who may chat. - [Public demo links](/channels/demo-links): Share a live preview of an agent floating over a prospect's own website, with an editable written summary of what it does — before embedding anything. - [Telegram setup](/channels/telegram): Connect a Telegram bot to your agent, including the slash commands users get automatically. - [WhatsApp setup](/channels/whatsapp): Connect WhatsApp Business messaging, including the two Meta requirements that most often break the integration. - [Escalate to human](/channels/handoff): Let an agent hand a conversation to a human operator when it cannot help, or the user insists on one. - Contacts - [Contacts](/contacts): The people your agents talk to — how they are identified, how their personal data is protected, and what you can do with their records. - Memory - [Memory](/memory): How an agent remembers a contact across conversations, what has to be enabled first, and how to manage what is stored. - Guardrails - [Guardrails](/guardrails): Per-agent safety controls enforced by the runtime — what each setting does, and which ones you cannot turn off. - [Answer modes](/guardrails/answer-modes): The four settings controlling where an agent is allowed to source its answers, and how to choose between them. - Evaluations - [Evaluations](/evaluations): Test an agent's quality before customers see it — suites, test cases, scoring, and publish gates. - Scheduled tasks - [Scheduled tasks](/scheduled-tasks): Have an agent reach out proactively — one-off reminders and recurring check-ins delivered to a contact's existing channel. - [Audience messages](/scheduled-tasks/audience-messages): Message everyone in a data table who matches your filters — one message per row, no AI processing. - Conversations - [Conversations](/conversations): Read what your agents and customers said, take over a live chat, and diagnose why an agent answered the way it did. - [KlicForge Inbox](/conversations/inbox): Handle live conversations from your phone — see which ones need a person, take over, reply, and get alerted the moment an agent asks for help. - **Operate** - Workspace - [Workspace](/organization): Members and roles, plans and limits, usage tracking, and the security controls available to administrators. - [Security and privacy](/organization/security-and-privacy): What KlicForge holds, how long it is kept, which AI providers see your conversations, and what you are responsible for as the workspace running the agent. - [Fair use policy](/organization/fair-use-policy): How KlicForge protects platform stability on a shared platform, and what happens if usage is unusually high. - [Affiliate program](/organization/affiliate): How the KlicForge referral program pays recurring commissions, and how to join. - [Notifications](/organization/notifications): Alert your own team when something happens in KlicForge, across inbox, email, webhook, web push, Telegram and Slack. - **Build** - Build - [Developer overview](/build): What you can integrate with today — the widget SDK, custom webhook tools, and MCP servers — and what KlicForge does not yet offer. - [Widget SDK](/build/widget-sdk): Embed and control the KlicForge chat widget from JavaScript — installation, configuration, methods and events. - **Reference** - Reference - [Interaction counting](/reference/interaction-counting): How KlicForge counts interactions against your monthly plan allowance, with worked examples. - [Plan limits](/reference/plan-limits): Agents, interactions, storage and other allowances included with each plan. - [Built-in tools](/reference/built-in-tools): The tools an agent can be given, grouped by what they act on. - [Skills catalogue](/reference/skills-catalog): Every skill you can attach to an agent, grouped by category. - [Data table field types](/reference/data-field-types): Every column type a data table supports, and which can be encrypted. - [Guardrail settings](/reference/guardrail-settings): Every guardrail an agent has, its default, and whether you can change it. - [Glossary](/reference/glossary): KlicForge terminology, including the common alternative names people search for. - Troubleshooting - [Troubleshooting](/troubleshooting): Common problems by symptom, with the usual cause and where to fix it. - [Frequently asked questions](/troubleshooting/faq): Answers to common questions about matching a chatter to their own data, and how attachments count toward usage. - [Getting help](/troubleshooting/support): Where to report bugs, ask questions, and submit privacy requests.