Agents

In Flow, agents are governed AI personas for chat and automation. You configure each one in Admin → Agents with its own model, tools, skills, and Knowledge Graph boundaries. Every tool call is audited; every agent runs inside the permissions you set.

Agent definitions follow the open AGENTS.md pattern. You can edit each agent as a structured form or as one raw document; both views produce the same portable definition your team can version, review, and adapt for production.

Shipped defaults

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

Workflow Architect (orchestrator) - default chat agent for clarifying intent, planning work, querying workflows and data, managing task lists, and delegating specialised tasks. It does not mutate the canvas directly.
Canvas agent - specialist for building and editing workflow graphs (nodes, edges, ports, and canvas config), typically invoked by delegation from the orchestrator.

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

Configure each agent

In Admin → Agents, you control how each persona behaves in production:

Setting	What you control
Id and display name	Stable identity and the label users see in chat
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	Allowlisted entries from the audited catalog; see Tools and MCP
Scopes	Where the agent may run (for example Flow chat vs internal programmatic calls)
Sub-agents	Delegation targets that run work in child threads
Handoff agents	Same-thread transfer targets when the conversation needs a different specialist; see Agent Interop
Skills	Assigned instruction packages; see Skills
Knowledge Graph namespaces	Which governed corpora the agent may search and retrieve
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 - fast vector search over assigned namespaces before each message, so likely-relevant approved documents are already in context.
Agentic search - during the work, agents can search again, explore ranked matches, and pull full text only for documents that support the current step.

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.