Agent-builder field reference

In one line. Every control in the agent editor, tab by tab. You’ll be able to. Look up the exact name, type, range, and behaviour of any field in the agent builder. Where this lives. Studio > Agents > Agent Toolkit > Agents — open any agent to edit it.

The concepts behind these fields — what each tab is for, how to build a working agent end to end — are taught in Your first agent. Come here when you need the full list.

Saving is always deliberate: there is a Save Agent button and no autosave, and the button stays disabled while anything on the form is invalid.

The shape of the editor

The editor is two panes side by side: the builder on the left, carrying an 8-tab strip, and the Playground on the right, where you try the agent as you build it. Each tab below lists every control, what it does, and what a builder should put there.

Most fields carry an in-app help bubble — hover the i beside a field for a one-line explanation.

Tab 1 — Persona

Who the agent is and what it does, in plain language.

Field	Type	What it does / what to put
Name	text (required)	The agent’s display name across Studio and lists. Keep it task-named: “Invoice Extractor”.
Description	textarea	One or two lines a teammate can scan. Surfaces in the Agents list row.
Instructions	14-row textarea (required)	The system prompt / persona — the heart of the agent. Says who it is, what to do, how to behave, what to return. Supports global-variable placeholders `{{scope.X}}`.
Co-pilot (✦)	button beside Instructions	Type a one-line seed (“extract invoice fields and flag overdue ones”) and it expands a fuller draft you then edit.

Tab 2 — Model

Which language model powers the agent and how it reasons. The models you can choose from are the ones registered for the project under Studio > Agents > Agent Toolkit > Language Models.

Field	Type	What it does / what to put
LLM Model	multi-select	One or more of the project’s registered models. Multiple selections form a failover pool.
Agent Mode	select	Auto / Fast / Thinking. Auto is the default — the agent decides per question (Fast for simple lookups, Thinking for analysis). Pick Fast or Thinking yourself when you want every run to behave the same way. Fast = single-pass, low latency; Thinking = multi-step reasoning before answering.
Enable thinking budget	toggle	Caps how much reasoning the model may spend (Thinking mode).
Thinking budget	slider (−1 to 24576)	Token budget for reasoning. −1 = uncapped / model default; higher = more deliberation, more cost and latency.
Advanced sampling (expander)	—	Tune output randomness — leave default unless you have a reason.
↳ Temperature	slider (0–2)	Higher = more varied wording. For extraction, keep low (0–0.3).
↳ Top P	slider	Nucleus sampling cap.
↳ Max tokens	number (0–4000)	Hard cap on answer length.
↳ Frequency penalty	slider (−2 to 2)	Discourages repeated tokens.
↳ Presence penalty	slider (−2 to 2)	Discourages repeating topics.
↳ Seed	number	Fix for reproducible outputs while testing.

Tab 3 — Knowledge

What the agent is allowed to read. Three source sub-tabs.

Sub-tab / field	Type	What it does / what to put
Views ▸ View	select	A saved, filtered slice of a collection the agent may query. Views are defined under `Studio > Data > Views`.
Views ▸ Filter by view	toggle	Restrict the agent to only the documents inside that View.
Datasheets ▸ Datasheet	select	A table from `Studio > Data > Datasheets` the agent may query.
Knowledge collections ▸ select	multi-select	Attach the Knowledge collections this agent may read. The attached list shows a readiness dot per collection, so you know its index is built before you rely on it. If you don’t see this option, ask your administrator.
Knowledge lock	toggle	The agent answers only from attached knowledge — no general world knowledge.
Exact-match lock	toggle	Forces exact-match retrieval rather than semantic similarity.

Tab 4 — Capabilities

What the agent can do — its tools, MCP connections, and skills. Everything you pick here is something already registered for the project: tools under Studio > Agents > Tools, servers under Studio > Agents > MCP Servers, skills under Studio > Agents > Skills.

Section / field	What it does / what to put
Tools — + Add tool	Opens the tool picker; selected tools render as cards (remove per card). A tool is a callable: SQL search, a retriever, a custom API.
MCP servers — + Add MCP server	Menu of registered MCP servers, each with a badge showing whether the server was registered for the whole platform or for this workspace. Cards show the connection.
Skill Packs — + Pin pack	Pin a reusable skill bundle. Cards show “Pack”, N skills, and the same scope badge.
Skills — + Pin skill	Pin individual skills. Cards show a Pinned badge, the runtime, and an “also in pack X” collision badge if a pinned skill is already in a pinned pack.
Restrict this agent to pinned skills only	Checkbox. When on, the agent may use only pinned skills — it ignores otherwise-discoverable in-scope skills.
Auto-discoverable in this scope	A faint list under the pinned ones: skills the agent can find by itself, each with a Pin button to promote it. Tick the restrict checkbox above and this list is shown as suppressed.

Tab 5 — Output

The shape of what the agent returns. Five mode cards at the top (toggles).

Field	Type	What it does / what to put
Table output	mode toggle	Return rows/columns rather than prose.
Standardization	mode toggle	Normalize values to a canonical form (single-agent only).
Structured output	mode toggle	Extract typed fields against a schema — turns on the sub-form below. This is the invoice/extraction mode. See Collections & schema for building the schema itself. If the toggle is missing, ask your administrator.
Section classification	mode toggle	Classify each section of the document.
Auto-annotate document	mode toggle	Write extracted values back as annotations on the source document.
Taxonomy / learner	searchable select	(Structured) the schema whose Labels/Fields the agent fills.
Without Hierarchy / Select All labels	checkboxes	(Structured) shortcuts for flat schemas / extracting every label.
Process unit	segmented (Page / Section / Image)	(Structured) the chunk the agent reasons over at a time.
Merge pages	toggle	(Structured) treat multi-page docs as one unit.
Images per batch / Parallel batches	numbers	(Structured, image unit) throughput controls.
Send text with images	toggle	(Structured, image unit) include OCR text alongside page images.
Quality check agent	toggle + instructions	(Structured) a second pass that QC-checks the extraction.
Labels list — Add / Add all	rows	(Structured) per-field rows: Label select + Description (the per-field instruction that most improves accuracy).
Enable Reasoning / Confidence Score / References	toggles	(Structured) return the why, a 0–1 confidence per field, and source citations. Confidence drives “needs review” routing.
Limit rows to display	number	Cap rows returned (table/structured).
Use download filename	toggle	Name exports from the source filename.

Tab 6 — Governance

The rules the agent must obey, and where a human signs off.

Section / field	What it does / what to put
Guard rails — + Add	Attach the guard rails this agent must obey (chips, removable). You write them under `Studio > Agents > Agent Toolkit > Guard Rails`.
Approvals ▸ Tools (n)	Per-tool rows: approval state (Approval required / Auto), a settings icon to tune the approval prompt (type Form / Multi-Select + approval-card text), and an enable toggle.
Approvals ▸ Team agents (n)	Per-member approval toggle. Disabled unless the agent has team members (Subagents tab).

This tab decides when a human is asked. Who may answer is decided by the project’s people and personas — see Access & roles and Studio > Governance > Access > Users & Access.

Tab 7 — Context

Fine control over what context gets assembled into each prompt. Advanced — the Profile template default is fine for most agents.

Section / field	What it does / what to put
Profile template	A named context recipe; editing any field flips it to “Custom”.
Sources table	Per provider: On checkbox, Source, Tier (1/2/3), Priority (0–100). Tier-1 sources are spent first.
Variables allowed	Scope chips (checkboxes) — which `{{scope.X}}` variables the agent may read.
Token budgets	Per-tier token caps (Tier 1/2/3 number inputs).
Truncation	Strategy (auto / last_messages / summary_compact), Max prompt tokens, Recent turns kept, History rows fetched, Summariser model (when summary_compact).
Preview — Run preview	Renders the final assembled instructions, spend-by-tier, and which blocks were kept or dropped — before you ever run the agent.

Tab 8 — Subagents

Turning this agent into a team coordinator that delegates to member agents.

Section / field	What it does / what to put
Coordination mode	Select (shown when at least one subagent exists) — how the leader sequences members.
Subagents list — + Add subagent	Per row: Agent select (team-tagged agents), Prefix instructions textarea (member-specific guidance), Reasoning toggle, remove.
Empty state	No subagents = a normal single agent. Adding the first subagent makes it a coordinator.

Save Agent — disabled when the form is invalid; shows “Saving…” while in flight. No autosave.
The editor remembers which tab you were on and whether you had a pane collapsed, so you return where you left off.
*Ctrl/Cmd + * toggles the Playground pane; *Ctrl/Cmd + Shift + * toggles the builder pane (never both collapsed at once).

The Playground pane

A two-tab group — Playground | Task & metrics.

Playground tab

Control	What it does
Chat transcript	Markdown answers, tables, charts, thinking blocks, tool-attachment download links.
Approval panels	When a tool or step needs sign-off: Reject / Review (leave feedback) / Approve & Execute.
Input Type radios	Text / Document / Project — what the agent runs against.
Enable Chat History	Toggle — carry prior turns into context. Hidden while Structured output is on, because each run is judged on its own.
Document picker / Page Numbers	(Document input) pick a doc and optional page range.
Attachment (+)	Attach photos and files inline.
Question textarea	Your prompt. Enter to send.
Send	Runs the agent and streams the answer.

There is no mode control in the Playground — set Fast or Thinking on the Model tab, then re-run.

Task & metrics tab

Section	What it does
Input & Output Formats (accordion)	Sample Input + Sample Output + Validate (checks the output conforms).
Evaluation Rule Setup	Freeze Task & Metrics toggle; Task select + Auto-Detect (analyses your agent and proposes a task); Metrics grouped Primary / Optional / Irrelevant checkboxes with descriptions. Feeds `Studio > Agents > Quality > Evaluations` — if that entry is not in your menu, ask your administrator.

Human approvals — one dialog

Approvals are configured in one place: Governance ▸ Approvals. The settings icon on a tool row opens the approval-card dialog, where you set Request approval (enable), Approval type (Form / Multi-Select), and the Approval card text the reviewer sees.

At run time the agent pauses at that step and surfaces a Reject / Review / Approve & Execute panel — in the Playground while you are testing, and in the live run for the people using the solution.