Skip to main content

Build an answer agent

Agents

Answer & assist builds one conversational agent that answers questions, searches your documents, queries a database or writes research. This page covers the wizard for the Answer questions and Search your docs kinds; the database and research kinds add sections of their own and have their own pages.

Who can use it: the Builder role or higher, in a tenant licensed for agents. Publishing needs an Owner team.

VideoBuild an answer agent3:00

Recorded on .

  1. Start

    New agent opens the chooser. We pick Answer & assist. Then the kind: Search your docs, for an Expense Policy Assistant grounded in finance policy. We start Blank, to see every section ourselves, and Continue to build.

  2. Identity

    The builder opens on Identity: Setup, Test and Deploy at the top, the eight sections down the left. The Agent draft rail on the right sums the agent up as you build. A Display name. The slug comes from it and becomes the API path and the Slack mention. One sentence of description. Under Ownership & routing, the Owner team is required. We pick Finance Ops.

  3. Behavior

    Behavior. Generate from Identity & template drafts a starter prompt from the name and description. Edit it here, Browse Prompt Studio for a versioned prompt, or Preview merged prompt the model receives. Then the Model tier: Fast, Balanced or Smart. The AI Gateway resolves the concrete model at run time, so the prompt stays portable.

  4. Tools

    Tools come from MCP servers an administrator registered. None is connected here yet, and a policy assistant needs none. Agents attaches other agents this one can call inside a turn.

  5. Skills

    Skills are versioned instructions from your library. We attach support-triage. Each published version freezes the skill text it was built with; edits reach this agent at the next publish.

  6. Knowledge

    Knowledge is where the answers come from. Each source shows its connector, size and freshness, and a stale one is marked. We attach Company Policies, the Employee Handbook and Finance Documents. At run time the retriever grounds every answer in the closest passages.

  7. Memory

    Memory. Persistent keeps history across sessions and expires on a schedule. Per user keeps each person's memory separate.

  8. Guardrails

    Guardrails. A profile binds the rails an administrator created in the Control Room to every turn. Without one, the agent publishes ungoverned. We pick PII-strict: five of five rails on. Mask is what happens when a rail trips.

  9. Advanced

    Advanced overrides the tier's Sampling and picks the Execution strategy: tool calling, or ReAct.

  10. Verify

    Back on Identity: five of eight sections started, green dots on the rail, three knowledge bases and one skill in the Agent draft. Next, open Test to run the draft.

Prerequisites​

  • A team you belong to, chosen as the agent's owner.
  • Anything the agent should use: knowledge sources synced in Knowledge, MCP servers registered by an administrator, skills in your library. You can attach them later.

The wizard, section by section​

The Answer & assist wizard on Identity: the build header with Setup, Test and Deploy, the sections count, the Wizard and Code lenses and Publish; the Setup rail listing Identity, Behavior, Tools, Skills, Knowledge, Memory, Guardrails and Advanced; the Identity form with Display name, Workspace, Agent name (slug), the API endpoint and Slack mention preview, Description, Owner team and Default locale; and the Agent draft rail on the right.The Answer & assist wizard on Identity: the build header with Setup, Test and Deploy, the sections count, the Wizard and Code lenses and Publish; the Setup rail listing Identity, Behavior, Tools, Skills, Knowledge, Memory, Guardrails and Advanced; the Identity form with Display name, Workspace, Agent name (slug), the API endpoint and Slack mention preview, Description, Owner team and Default locale; and the Agent draft rail on the right.
Identity names the agent. The slug becomes part of the API path and the Slack mention, so it is fixed once published; the draft rail on the right summarises the agent as you build.

The build header shows the draft's name and status, the Setup, Test and Deploy tabs, how many of the eight sections you have started, the Wizard and Code lenses and Publish. A dot on the Setup rail marks a section that still needs attention. The Agent draft rail carries Studio suggests and the Safe by default note: drafts stay private until you publish, and the current version keeps serving until then.

Identity​

Display name is what chat headers, the registry and the Slack agents list show. Agent name (slug) is lowercase with hyphens. Description is one sentence of up to 160 characters, shown wherever people pick an agent. An empty Owner team list means you are in no team yet; ask an administrator, and the list refreshes on its own. Default locale hints downstream surfaces or detects the language per turn; Tags takes suggested chips or your own.

Behavior​

The Behavior section: the System prompt card with Freeform and Structured, Preview merged prompt and Browse Prompt Studio, the token budget line, Generate from Identity & template and four starter presets, then the Model tier card with Fast, Balanced (recommended) and Smart each giving an estimated cost per turn, a monthly projection at a daily volume, the Resolves to line naming the model, and Pin a specific model.The Behavior section: the System prompt card with Freeform and Structured, Preview merged prompt and Browse Prompt Studio, the token budget line, Generate from Identity & template and four starter presets, then the Model tier card with Fast, Balanced (recommended) and Smart each giving an estimated cost per turn, a monthly projection at a daily volume, the Resolves to line naming the model, and Pin a specific model.
Behavior holds the system prompt and the model tier. The AI Gateway picks the concrete model for the tier at run time, so prompts stay portable; pin a model only when you need one.

The System prompt card takes a Freeform or Structured prompt, and the bar above the editor shows how the token budget is spent between prompt, skills, examples and history. Generate from Identity & template needs the name and description filled in; four presets start from a style. Compare tiers explains the three model tiers and Pin a specific model fixes one when you need it.

Tools​

Connected servers lists the MCP servers registered in the Control Room; pick the tools this agent may call, and note that write actions get an approval gate by default. Function tools run inside Katonic. An attached Agent answers inside your turn, unlike a coordinator, which hands the whole turn to one specialist.

Skills​

Pick skills offers Attached only, sort and vertical filters. Attached skills are added to the agent's instructions when it is published, or loaded on demand when progressive skills are enabled.

Knowledge​

The Knowledge section: Pick knowledge bases with the attached count, sort options, connector filter chips, and one row per knowledge source with its connector, document count, agent count and refresh time.The Knowledge section: Pick knowledge bases with the attached count, sort options, connector filter chips, and one row per knowledge source with its connector, document count, agent count and refresh time.
Knowledge attaches the sources the agent retrieves from at run time. Filter by connector, sort by adoption or freshness, and attach the ones this agent should ground its answers in.

Filter the sources by connector chip, sort by adoption, freshness, size or name, and switch a source on to attach it. Pair the retriever with the cite-with-sources skill to enforce citations.

Memory​

The Memory section: the storage, active conversations and last cleared tiles with Clear memory, the Retention card with Stateless, Session, Persistent (recommended) and Vector recall each showing added latency and cost, the Stores to line, and Privacy & scope with Per user, Per user per agent and Shared across workspace.The Memory section: the storage, active conversations and last cleared tiles with Clear memory, the Retention card with Stateless, Session, Persistent (recommended) and Vector recall each showing added latency and cost, the Stores to line, and Privacy & scope with Per user, Per user per agent and Shared across workspace.
Memory decides what the agent keeps between turns and sessions. Each mode shows its latency and cost; scope decides whose memory is shared.

The tiles show storage used, active conversations and the last clear, with Clear memory. Retention is Stateless, Session, Persistent (recommended) or Vector recall, each with its added latency and estimated cost; the Stores to line shows the retention and retrieval window the agent will publish with. Privacy & scope is Per user, Per user, per agent or Shared across workspace. PII is scrubbed by the guardrails and the pii-scrubber skill, not by a switch here.

Guardrails​

The Guardrails section: the Guardrail profile card with the no-profile warning and three profiles, PII-strict with all five rails on, Tool-safety with three and Answers-only PII with one, the rails that are off struck through, then When a guardrail trips with Block, Mask (default), Log only and Human review.The Guardrails section: the Guardrail profile card with the no-profile warning and three profiles, PII-strict with all five rails on, Tool-safety with three and Answers-only PII with one, the rails that are off struck through, then When a guardrail trips with Block, Mask (default), Log only and Human review.
Guardrails bind a profile to the agent. Without one the agent publishes ungoverned: the cards below are stored with the agent, but only the selected profile is enforced at run time.

The cards under the profile (When a guardrail trips, PII handling, Prompt injection, Topic blocklist, Custom rules) are saved with the agent and used by Test against a prompt, but at run time only the selected profile's rails and their actions are enforced.

Advanced​

Sampling overrides the tier's temperature and maximum output tokens. Tool-calling lets the model decide when to call tools and when to answer; ReAct is a reason-then-act loop. Suppress chat hints for this agent hides the first-use coaching tooltips. Environment variables are saved as plain text and not yet delivered to the running agent, so put no secrets here.

Verify​

The header count moves as you fill sections in, and the rail dots turn from red to green. Open Test to run the draft; see Test, publish and versions.

Troubleshooting​

  • Fill in name + description in Identity first. Generate from Identity & template needs both.
  • No MCP servers connected yet. An administrator registers servers in the Control Room's Tools page first.
  • No profile selected. Pick a guardrail profile, or create one in the Control Room's Guardrails page, before you publish.

Describes the platform as of .

Was this page helpful?