Skip to content
Back to

Overview

Fontana AI gives you governed agents for Flow chat, workflow automation, and operational tasks. You choose which gateways and models are approved, scope API keys with BYOK, attach Knowledge Graph namespaces for retrieval, and extend agents with Skills, built-in tools, and MCP integrations. Every tool call and delegation can leave audit metadata aligned with your compliance posture.

You open Administration (/admin) for workspace and AI configuration (users, teams, agents, gateways, embeddings, TTS, and the rest). Standalone chat is /ai/chat. Visiting /ai or /ai/overview redirects to /admin.

Topics

Section titled “Topics”
  • Gateways - 20 LLM gateways with BYOK routing, from unified routers (OpenRouter, LLM API) to direct vendor APIs, AWS Bedrock, and Custom & Self-Hosted endpoints.
  • Models - 300+ frontier and open-weight models in an Admin-approved catalogue, all routed through the gateways and keys you configure.
  • Text-to-speech - AI Chat voice: browser native, platform Kokoro, or OpenAI-compatible cloud speech configured from Administration.
  • Knowledge Graph - An agent-native knowledge engine combining full-text search, a document outline tree, a typed entity graph, and vector similarity in one governed, namespace-scoped graph, so agents retrieve approved, cited context instead of rediscovering rules every run.
  • Agents - Configurable in-app personas for Flow chat and automation, each with its own model, tools, skills, Knowledge Graph boundaries, and workflow-aware context. Shared threads show unread markers in chat history, and the header Notification Center lists unread threads so you can reopen them where they lived (workflow Graph view with the AI panel, or standalone /ai/chat when no host context is known).
  • Agent schedules - Package-authored UTC cron definitions you activate so a chosen agent runs on a persistent chat thread.
  • Human in the Loop - Approval gating for AI operations: structured askHuman forms, deferred CITL execution, canvas suggestion apply, and NL Operations compile review.
  • Skills - Uploadable agentskills.io folders (SKILL.md plus optional references, scripts, and assets) that extend agents with governed, on-demand procedures.
  • Tools and MCP - Built-in tools for workflows, data, canvas editing, and documents, plus Model Context Protocol (MCP) integrations and isolated OpenSandbox execution.
  • Agent Interop - Delegate to specialist agents, hand off conversations in-thread, or federate with external agent platforms over A2A, ACP, and related open protocols with full audit coverage.
  • Chat Channels - Chat with your agents from Slack and Microsoft Teams with linked identities, Flow-side approvals, and the same governed runtime as in-app chat.
  • Bring Your Own Key (BYOK) - API keys you control in per-workspace Vault, scoped at org, team, or person level, with no shared Fontana-operated model account.
  • Zero Data Retention (ZDR) - Align LLM routing with your retention and no-training requirements through provider policies and your BYOK gateway settings.
  • Growth engineering - Institutional learnings in docs/solutions/ that MiniSpec and MegaSpec consult and grow on each ship.
Section titled “Related documentation”