> ## Documentation Index
> Fetch the complete documentation index at: https://docs.teamfollowup.ai/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Use the public API base URL: https://api.teamfollowup.ai/api.
> Authenticate public API requests with Authorization: Bearer YOUR_API_KEY.
> Use product-owned terms: agents, calls, campaigns, contacts, phone numbers, billing, and configuration.

# Skills and tools

> Your voice agent can carry skills now, the same idea you already use in Claude Code and Codex. It makes calls more reliable, more deterministic, and easy to keep improving.

You already know skills from Claude Code and Codex: focused capabilities the model
reaches for at the right moment, instead of one giant prompt holding everything at
once.

Your voice agent can carry them too now. That's newer than it sounds, and it's the
difference between an agent that gets shakier the more you teach it and one that
gets sharper.

## A new way to think about a voice agent

For years a voice agent was one long script. Every rule and objection packed into a
single wall of text, with the agent trying to hold all of it at once. It works
until it doesn't. The more you add, the more each instruction gets buried, and the
more the agent drifts.

Skills flip that. The agent carries a set of small, focused plays and reaches for
the right one exactly when the moment comes up. It's closer to how a good rep
actually works: they don't recite everything they know on every call, they pull
the right move when the call calls for it. Most teams building voice AI haven't
structured it this way yet.

## Why it makes calls more reliable

* **Progressive disclosure.** The agent sees the triggers, not the full text. It
  pulls one skill's instructions the instant that moment lands and ignores the
  rest. More skills makes it sharper, not foggier.
* **Fewer hallucinations.** Each moment gets its own tight brief instead of being
  lost in a mega prompt, so there's far less room to improvise.
* **More deterministic.** For the things that must be exactly right, do we cover
  this ZIP, transfer here, tag this lead, a tool runs real code and returns a fact
  instead of a guess.
* **Always improvable.** Every skill is a small thing you can watch, edit, and
  sharpen on its own. Your agent keeps getting more reliable because you tune
  specific plays, not a wall of text.

## Two kinds of ability

<CardGroup cols={2}>
  <Card title="Skills you write" icon="sparkles">
    Rules in plain English: when this comes up, do that. No code. Your judgment,
    taught to the agent.
  </Card>

  <Card title="Tools we ship" icon="wrench">
    Built abilities you add and configure, deterministic where it counts. A tool
    checks a ZIP, transfers a call, tags a lead. You don't build tools; we maintain
    them so they work every call.
  </Card>
</CardGroup>

In the dashboard both live in one panel, **Skills & Tools**: everything this agent
can do during a call. It's all per agent, and nothing here makes the agent dial.
That's still the [campaign](/campaigns/overview).

<CardGroup cols={2}>
  <Card title="The tool library" icon="wrench" href="/skills/tool-library">
    The abilities we ship and how to set each one up.
  </Card>

  <Card title="Writing a skill" icon="sparkles" href="/skills/writing-a-skill">
    Teach the agent a play in plain English.
  </Card>
</CardGroup>