Internal Agents are purpose‑built assistants you and your team use inside the platform. They do analysis on calls, help with reporting, and handle back‑office tasks. Unlike Flows (which power customer‑facing voice, SMS, and chat experiences), internal agents never face customers and don’t get published to channels. They’re available from the Flows page for convenience, so your team can manage everything in one place. Agents listed alongside flows

When to use an Agent vs a Flow

Use an Agent when you need:
  • Conversation/search analysis (e.g., “find all transcripts with rebill disputes last week”).
  • Internal operations (e.g., “tag these 20 calls as ‘Outage’ and summarize top reasons”).
  • Back‑office tasks driven by function calls (reporting, data lookups, ticket updates).
Use a Flow when you need:
  • Customer‑facing conversations (voice, SMS, chat, web).
  • Stateful logic, events, and channel integrations.
  • Publishing and testing across platforms.
Bottom line: Agents are for your team; Flows are for your customers.

Creating a New Agent

There are two entry points:
  1. Go to Build → Flows, click Create Agent (top‑right).
  2. Or open Build → Agents (if enabled in your workspace) and click New.
Create Agent

Fields

  • Name – What your team will see on the card in the Flows grid.
  • Description – One‑line purpose statement.
  • Prompt – The system instructions that define the agent’s role, guardrails, tools, and workflow.
  • Tools – Select which functions the agent is allowed to call (see below).
Click Save. Your agent now appears in the Flows grid next to your flows.

Agent Details Page

The Agent Details view is where you define the agent’s job and capabilities. Agent Details A good pattern is to include:
  • Role – What the agent is (e.g., “conversation insights analyst”).
  • Goals – What outcomes it’s responsible for.
  • Capabilities – What it can do (search, count, retrieve, tag, summarize, reference docs).
  • Tool rules – What to call, when, and how to confirm.
  • Tone & constraints – Brief, accurate, no speculation, ask before doing risky actions.

Prompt template (copy/paste)

Act as a <ROLE> within our AI contact center platform. You will help internal staff quickly find,
filter, and understand customer conversations. You must:
- Prefer facts from tool calls over assumptions.
- Use the tools listed below to search, count, retrieve, tag, and summarize transcripts.
- Ask for missing inputs once, then proceed with best‑effort defaults.
- If a tool is marked “Requires Approval”, ask for confirmation before running it.
- Be concise and structured: short bullets, callouts, and one clear next step.

Workflow:
1) Understand the request and list the tools you’ll likely need.
2) Collect key filters (date range, keywords, tags, agent, flow).
3) Call tools step‑by‑step; cite what you used and why.
4) Return a short answer and what you can do next on request.
Tip: Use direct language like “must” and “will” instead of “should/can,” and avoid over‑detailed examples that the agent might copy literally.

Tools & Approvals

Open Show Tools to choose the functions this agent can call. Tool selection and approvals
  • Enable/Disable – Check the box to allow a tool.
  • Approval – Set No Approval Needed or Requires Approval. When approval is required, the agent will ask you to confirm before executing the function.
Common examples you might enable for a Conversation Analyst Agent:
  • listTranscripts – Search using filters (keywords, tags, dates, agent, flow).
  • countTranscripts – Return counts for filters (trend checks, QA sampling).
  • getTranscriptReport – Stats like length, turns, and message counts.
  • getReadableTranscript – Customer‑friendly transcript view on request.
  • getTagsForTranscript – Retrieve tags for review or QA.
  • Domain‑specific tools (e.g., getAllCampaigns) as needed.
Keep the tool list tight. The more tools you permit, the more the agent must reason about which one to use. Fewer tools = cleaner behavior.

Using an Agent (Chat)

Open the agent card from the Flows page to launch a built‑in chat panel. In‑product agent chat
  • Start with prompts like “What can you help me with?” or “Today’s conversations.”
  • Ask targeted questions (“Find outage calls this week tagged ‘billing’, summarize top 3 themes.”).
  • The agent will call the allowed tools, then return a concise answer and recommended next step.

Chat History

Use the Chat History panel to revisit earlier threads and continue where you left off. Chat History

Explore Agents

Use the Explore Agents panel to switch between internal agents (e.g., Flow Building Agent, Conversation Analyst Agent) without leaving the page. Explore Agents

Example: Conversation Analyst Agent

Here’s a concise capability set that works well: Workflow & Capabilities
  • Search transcripts by keywords, tags (key–value pairs), agents, or date ranges.
  • Count transcripts that match filters.
  • Retrieve readable transcripts when specifically asked.
  • Analyze call metadata (duration, turns, messages).
  • Read and apply tags to transcripts where appropriate.
  • Reference internal documents or playbooks when provided.
Transcript Analysis Steps
  1. listTranscripts – Gather candidates.
  2. countTranscripts – Size the set.
  3. getTranscriptReport – Inspect stats.
  4. getReadableTranscript – Provide the transcript only if requested.
  5. getTagsForTranscript – Show tags or suggest additions.
You can duplicate this agent and swap the tools to create specialized back‑office agents (e.g., Campaign Reporting Agent, Billing Exceptions Agent).

FAQs

Why do agents show up on the Flows page? To keep management simple. Your team has one place to create, find, and launch automation—whether it’s customer‑facing (flows) or internal (agents). Can an agent be exposed to customers? No. Internal agents are not published to channels. If you need a customer experience, build a Flow. Do agents use states/events like flows? No. Agents are single‑chat assistants defined by a prompt and a set of tools.