---
title: "Campaigns & Agents — Who Does What — Campaigns & Strategy"
description: "A campaign is a plan; an agent is a worker. What happens where the two meet — which agent runs your campaign, why a campaign has no autonomy setting, and why campaign drafts always wait for you."
canonical_url: "https://bolta.ai/university/courses/campaigns-and-strategy/campaigns-and-agents"
markdown_url: "https://bolta.ai/university/courses/campaigns-and-strategy/campaigns-and-agents.md"
last_updated: "2026-09-10"
content_type: "feature"
publisher: "Bolta"
---

# Campaigns & Agents — Who Does What — Campaigns & Strategy

Source: https://bolta.ai/university/courses/campaigns-and-strategy/campaigns-and-agents
Last updated: 2026-09-10

A campaign is a plan; an agent is a worker. What happens where the two meet — which agent runs your campaign, why a campaign has no autonomy setting, and why campaign drafts always wait for you.

## Summary

Lesson from the Bolta University course "Campaigns & Strategy". The full lesson text follows.

## Who this is for

- Founders
- Creators
- Marketing teams
- Agencies

## Limitations and boundaries

- Course material describes the product and the platforms at the time of writing; verify current behaviour in the app.
- Social network features, limits, and algorithms change independently of Bolta.
- Current prices and plan limits must be verified on the Bolta pricing page.

## Lesson 1: Plan and Worker

The cleanest way to hold the difference:

> **An agent is a worker you hire. A campaign is a brief you hand it.**

An agent has a name, a personality, a role, jobs, a schedule and an autonomy
level. It exists indefinitely. It is *who* does the work.

A campaign has a subject, an angle, a window and a plan. It has no
personality, no schedule of its own, and no autonomy. It is *what* the work is
about.

They are not alternatives. A campaign **runs through** an agent — every
campaign week is executed by a content-creator agent in your workspace. If you
have never hired one, the campaign hires one for you.

| | Agent | Campaign |
|-|-|-|
| What it is | A worker | A brief |
| Lifespan | Indefinite | 1–4 weeks |
| Has a personality | Yes | No |
| Has an autonomy level | Yes | No — always review |
| Has a subject | No | Yes, a theme |
| Has an editorial angle | Implied by its persona | Explicit, one of six |
| Can publish without you | Yes, if set to auto | **Never** |
| Judged by | Ongoing output | A single readable outcome |

## Lesson 2: Which Agent Runs Your Campaign

You do not assign a campaign to an agent, and there is no picker for it. The
run resolves the right agent itself, in this order:

1. **An active content-creator agent in your workspace.** If you have one, it
   is used — preferring the preset the work calls for.
2. **An agent in an error state.** It is reactivated and used. A fresh attempt
   is what clears a system flag, and hiring a duplicate around a flagged agent
   is how workspaces end up with three near-identical Hype Men.
3. **A paused agent stops the run.** If your only content-creator agent is
   paused, the campaign refuses to start and tells you which agent and why.
   Your pause is respected — Bolta will not hire a second agent behind your
   back to get around it.
4. **No agent at all?** One is hired from the preferred preset.

Two consequences worth knowing:

**If your campaign will not start and the message names a paused agent, resume
that agent.** This is a common and completely silent-looking failure otherwise
— the campaign is fine, the plan is fine, and nothing will happen.

**Hiring an agent for a campaign does not switch on recurring posting.** When
an agent is auto-hired this way, the recurring job that normally comes with a
new hire is removed immediately. Starting a campaign must never quietly turn on
a standing schedule you did not ask for.

### The hidden job

Each workflow the platform runs has a hidden system job behind it, shared by
every run of that kind. It carries none of your campaign's per-run
configuration — no accounts, no plan. That is deliberate: the row is shared, so
writing your campaign's targeting onto it would put two concurrently running
campaigns in a race over the same field.

Your campaign's own settings ride on the run itself. This is why two campaigns
with different accounts, different voices and different tones can run in the
same week without interfering.

## Lesson 3: Why a Campaign Has No Autonomy Setting

Agents have four autonomy levels:

| Level | Behaviour |
|-|-|
| **Manual** | Never acts on its own |
| **Assisted** | Drafts, then waits for approval |
| **Auto** | Approves and acts by itself |
| **Aggressive** | Like auto, and proposes new work |

Campaigns have none of these, and the reason is a single design decision:

> **A campaign always requests review. Its drafts land in the Approve queue,
> every time, regardless of your workspace autonomy or the agent's level.**

You pressed "activate a plan", not "post these". A plan that published itself
the moment you saved it would make the activation button the most dangerous
control in the product.

So a workspace set to fully autonomous will still have its campaign drafts wait
for a person. If you want content that publishes without review, that is an
agent with a job on a schedule — not a campaign.

A few related mechanics, since they interact:

- **Autonomy can be tightened but never loosened** as it flows down. A job can
  demand more oversight than the agent; it can never grant less.
- **Safe mode** on the workspace forces approval everywhere, overriding
  everything below it.
- **Per-agent autonomy is honoured only once you have confirmed it.** An agent
  showing a level you never explicitly saved runs on the workspace default
  instead, so nothing escalates by surprise.

## Lesson 4: What Each One Is Better At

Use an **agent** when:

- You want a permanent capability — someone who replies to comments, someone
  who watches for prospects, someone who reports on performance.
- The work is ongoing and has no ending.
- You genuinely want things to happen without you.
- The job is not writing scheduled content at all — hunting, engaging,
  analysing, relationship management.

Use a **campaign** when:

- The content is about a specific thing.
- There is a start and an end you can name.
- You want to read a result and decide whether the angle worked.
- You want a countable plan rather than an open-ended stream.

Use **both**, which is the normal case:

A content-creator agent gives you baseline presence. Campaigns sit on top for
launches, promotions and pushes. An Engager agent handles the comments those
campaigns generate. An Analyst tells you which angle earned attention, which is
the input to your next campaign's angle.

### A common mistake

*"I'll make my agent do the campaign."*

You can tell an agent to write about your launch, and it will. What you lose is
everything a campaign gives you: the countable plan, the window, the single
angle applied consistently across every piece, the derived result at the end,
and the ability to duplicate the whole shape when it works. An agent given a
subject produces posts. A campaign produces an answer to "did this angle
work?"

## What to take away

- Agent = worker, campaign = brief. A campaign runs *through* an agent.
- The agent is resolved for you; a **paused** content-creator agent stops the
  campaign, by design.
- Campaigns always request review. They cannot auto-publish, on any autonomy
  setting.
- The pairing to aim for: agents for standing capability, campaigns for pushes.

## Relevant links

- [Bolta University](https://bolta.ai/university)
- [Campaigns & Strategy](https://bolta.ai/university/courses/campaigns-and-strategy)
- [Bolta pricing](https://bolta.ai/pricing)