Agents

In Flow, agents are governed AI personas for chat and automation. You configure each one as a filesystem package under AI → Agents (AGENT.md with YAML frontmatter plus a Markdown system prompt, optional schedules.json, optional avatars/ image pointed at by frontmatter avatar, and sibling files). Every tool call is audited; every agent runs inside the permissions you set.

Agent definitions follow the open AGENTS.md pattern. The Agents explorer opens the correct editor card for each path; saving re-ingests the derived runtime catalog.

Shipped defaults

Fontana ships ready-to-use agents you can tailor for your organisation:

Fontana agent (system/fontana-agent) - top-level default chat agent for /ai/chat, unmapped routes, and general routing (including agent schedules).
Page agents - one primary agent per major Flow surface (for example system/workflow-agent on /workflow, system/kg-agent on Knowledge Graph, system/skills-agent on Skills, plus placeholders for dashboard, files, admin routes, and more). On each navigation, the new-chat picker selects that page’s agent. You can change the agent before the first send; your choice sticks until you navigate again.
Canvas agent - specialist for building and editing workflow graphs (nodes, edges, ports, and canvas config). It remains a sub-agent of system/workflow-agent, typically invoked by delegation.

When you send a message on an existing thread from a different page than the thread’s current owner, Flow switches the thread to that page’s agent automatically. Intentional non-page transfers still use handoff (chat_handoffThread) to allowlisted agents. Chat history is per-user across pages (not siloed by workflow).

On Skills, system/skills-agent can manage namespaces, packages, and files with the same RBAC as the Skills UI. Page selection (namespace, folder, file) is sent as structured chat context. When you ask to open a named skill, Fontana agent and dashboard agent resolve it via the skill catalog and navigate to that skill’s SKILL.md (not only the Skills home page).

On Agents, system/agents-agent creates and manages portable agent packages the same way: it picks a non-reserved namespace (user when only Fontana system exists; otherwise it asks), writes AGENT.md with role-ready system prompts and defaults that include handoff to system/fontana-agent for Fontana product requests, and opens the package in the explorer. It does not author into the reserved system namespace (or legacy default if present). Fontana-shipped agents live under system/.

You can clone these defaults, adjust prompts and tool allowlists, and assign additional Skills as your operating model requires.

For recurring scheduled prompts on a persistent chat thread, see Agent schedules.

Configure each agent

In AI → Agents, you edit the package files that define each persona:

Setting	What you control
Id and display name	Stable identity and the label users see in chat
Avatar	Optional picture stored under the package `avatars/` folder; frontmatter `avatar` points at the file. Upload or remove from the agent card header (same crop control as your profile). Shown in chat and agent pickers.
Description and system prompt	Short summary plus Markdown instructions that define tone, scope, and operating rules
Language model	Approved model override; leave empty to use the deployment default
Tools	Capability tiles (Workflow, Knowledge, Data, Chat, Agent, Skills, Channels, Coding, plus one tile per extra MCP connection you add) with an Advanced view for the full audited tool list; selections persist as trailing-star patterns where applicable. See Tools and MCP
Scopes	Where the agent may run (for example Flow chat vs internal programmatic calls)
Sub-agents & handoff	Namespace tiles for delegation and same-thread transfer targets; Advanced view for per-agent allow-lists and `*`. See Agent Interop
Skills	Namespace tiles for assigned agentskills.io packages; Advanced view for the full folder/skill tree. See Skills
Knowledge Graph namespaces	Namespace tiles (yellow open-book accent, same as Knowledge in the sidebar) for which governed corpora the agent may search; Advanced view for `*` and per-namespace rows
Vector source	Keywords that help route and discover this agent and related workflow templates
Call settings	Optional JSON for temperature, topP, maxOutputTokens, and related LLM parameters
Reasoning effort	Agent default; per-thread chat controls can override
Context window slots	How much recent transcript the agent keeps in context; per-thread overrides available
KB injection score threshold	Minimum similarity score for automatic Knowledge Graph injection on each turn; per-thread overrides available

Automatic and agentic context

Agents receive Knowledge Graph context in two ways, described fully on Knowledge Graph:

Automatic pre-turn injection - vector search over assigned namespaces before each message, gated by the agent’s KB injection score threshold, so likely-relevant approved documents are already in context.
Agentic search - during the work, agents can call Knowledge Graph retrieval directly: hybrid search (full-text, vector, and relationship expansion), outline tree-walk over long structured documents, and entity navigation, each returning path citations back to the exact source section.

You assign namespaces per agent so regulated corpora stay segregated and retrieval stays least-privilege.

Workflow-aware assistance

Agents can search community workflow templates by semantic similarity and, with user consent, read workflow configuration from the canvas. That lets assistants help you design and refine pipelines with awareness of graph structure, node types, and connections.

Runtime execution data is queried separately from canvas configuration, so design assistance and live run results stay strictly separated.

Delegation and handoff

Complex work can span multiple agents without losing governance:

Sub-agents run delegated tasks in child threads while the parent conversation continues under audit.
Handoff transfers the same thread to another in-app agent when the task surface changes (for example from planning to canvas editing).

Peer-agent federation with external platforms uses separate interop protocols. See Agent Interop for A2A, ACP, and related patterns.