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

# Define your solution set

> Choose the mix of changes that closes the gap — process redesign, automation and enterprise transformation — and who owns each one.

Start with the work: a maze of handoffs, detours and decisions that people carry information through. Your solution set is the mix of changes that turns that maze into a simpler route. Agents are usually one part of it, not all of it.

Press **Play story** to watch the changes build on each other, or pick a solution type to see what it changes.

## Three families, six solution types

| Family | Solution type | What changes | Where Within helps | Who delivers it |
| - | - | - | - | - |
| **Process Redesign** | Remove waste | The work that adds no value comes out. A smaller maze still has complexity. | Diagnosis from your Work Brain, future-state design and measurement | The process owner approves the policy, controls and operating change |
| **Process Redesign** | Reengineer | What's left is rearranged into a simpler sequence: one left turn, one right turn, mostly straight through. Controls stay in place. | Diagnosis from your Work Brain, future-state design and measurement | The process owner approves the policy, controls and operating change |
| **Automation** | Deterministic | Fixed rules take over the repeatable steps: macros, APIs and scripts. | Context, design, builder enablement, evaluation and value review | The builder, release authority, system owners and operator own deployment and operation |
| **Automation** | Probabilistic / agentic | Agents handle the variation. They interpret the work, choose tools and escalate, and people handle the exceptions. | Context, agent design with the Within ADK, builder enablement, evaluation and value review | The builder, release authority, system owners and operator own deployment and operation |
| **Enterprise Transformation** | Systems & data | Same route, new foundation: the systems and data underneath change. An ERP migration is the typical example. | Exposes dependencies and provides the process and agent requirements | IT and data owners deliver the remediation, migration and platform change |
| **Enterprise Transformation** | Organization | Where the work sits, and how people support it: people, ownership and capacity are aligned around the work. | Makes the operating-model implications visible and supports capability planning | The sponsor and functional leadership authorize and carry out the change |

## Order matters

The changes build on each other. Remove waste, then reengineer what's left, then automate the simpler route — fixed rules first, then agents for the variation that rules can't handle — and then change the foundation and the organization around it. Automating a step you could have removed just makes the waste faster.

Then zoom out. Order to Cash alone is several connected processes in one value stream, and a real company runs hundreds of processes with hundreds or thousands of people. Read the solution set across the value stream, not one process at a time.

## How to choose the mix

**1. Start from the root causes**

Use Advisor to find the largest causes of the gap in your Work Brain (Process Index), not a favourite solution. Size the causes together: fixing one usually exposes the next. See [Strategic analysis with Advisor](/user-docs/define/strategic-analysis-with-advisor).

**2. Remove and reengineer first**

For each cause, ask what work can come out and what can be rearranged before anything is automated. These changes are often the fastest and the cheapest to run.

**3. Pick the smallest automation that works**

Choose the smallest shape that produces the outcome and passes its controls. Use rule-based automation when the process is stable and every step must be explainable. Use an agent when the inputs vary too much for a fixed path. Every agent option names its non-agent alternative, so you can compare the two.

**4. Name the enterprise changes**

Note the system, data and organizational changes the outcome depends on, and who owns them. Your teams deliver these; Within makes the dependencies visible.

**5. Agree the future state, owners and investment**

The solution set is done when the future state, the mix of changes and the investment are approved, with an owner for each change.

## Is an agent ready to build?

Grade each agent candidate before it goes on the roadmap, and check system access here rather than after a build.

| Criterion | What to check |
| - | - |
| **System access** | Can the agent reach the systems the work runs in, with the permissions it needs? |
| **Business context** | Are the rules, policies and exceptions written down, or captured in your Work Brain? |
| **Evidence quality** | Is the process captured from observed work, with enough real cases to test against? |
| **Agent identity** | How the agent is set up to act in your systems: the account it uses and the approvals it works under. |

Then pick how much the agent may do on its own:

* **Process redesign only.** No agent yet: the change is to the process.
* **Draft-only.** The agent prepares the work and a person approves it.
* **Full autonomy.** The agent acts on its own. Keep a person's approval for anything irreversible, regulated or expensive to correct, and reduce review only when testing and production evidence support it.

## Who decides what

| Role | Their part in choosing the change |
| - | - |
| **Executive Sponsor** | Funds the full solution, including the non-agent dependencies |
| **Functional Champion** | Owns the process design, the handoffs and the adoption plan |
| **AI Builder & Deployer** | Designs the agent's boundaries, controls and recovery |
| **Process Performers** | Test the future workflow on real examples |
| **Within** | Simplifies before automating, and supports the agent brief |

## Doing it in Within

Advisor does the analysis across your Work Brain. Two prompts to start from:

```text Solution mix for each root cause theme={null}
For the top three root causes of [the gap] in [value stream], recommend a mix of changes across process redesign, automation and enterprise transformation. For each change, say what it changes, who would own it, and what it depends on.
```

```text The non-agent alternative theme={null}
For each agent opportunity you found in [value stream], name the non-agent alternative (a removed step, a reengineered handoff or a rule-based automation) and compare the two on effort, risk and expected effect.
```

More in the [Advisor prompt library](/user-docs/define/advisor-prompt-library). For a template-based view of where automation pays off, see [Automation assessment](/custom-use-cases/automation-assessment).

## Where to go next

> **[Build your AI roadmap](/user-docs/define/build-your-ai-roadmap)**
>
> Set the objective and sequence the changes.

> **[Execute your improvements](/user-docs/deliver/execute-your-improvements)**
>
> How each solution type runs through delivery.

> **[Redesign the process](/user-docs/deliver/redesign-the-process)**
>
> Remove waste and reengineer before you automate.

> **[Build an agent with the Within ADK](/user-docs/deliver/build-an-agent-with-the-adk)**
>
> Specify, build and validate an agent from observed work.

> [!NOTE]
>
> **Need help?** Use the in-app chat — click the chat bubble in the bottom-right corner of Within (staffed 24×5) — or email [support@within.ai](mailto:support@within.ai).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.