# AI use cases for Intent Router (angel291592/Intent-Router)

Repo: [angel291592/Intent-Router](https://github.com/angel291592/Intent-Router) | Use cases: 3 | Page: https://dedupedai.com/use-cases/angel291592-intent-router/

Intent-Router is an installable skill that turns a vague request for an AI agent into a typed IntentSpec contract, and later checks the delivered work against that contract.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Turn a vague coding request into a checked spec: https://dedupedai.com/use-cases/angel291592-intent-router/compile-vague-request-into-intentspec/
- Delegate a task to an agent and check the result: https://dedupedai.com/use-cases/angel291592-intent-router/hand-off-delegated-task-with-contract-check/
- Stop an agent from guessing past an irreversible step: https://dedupedai.com/use-cases/angel291592-intent-router/stop-irreversible-guesses-before-routing/

## How to turn a vague coding request into a checked spec with Intent Router

Repo: [angel291592/Intent-Router](https://github.com/angel291592/Intent-Router) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Convert a one-line request into an IntentSpec that the repo partly answers and you answer once.

**Who it is for:** A developer who gets vague tasks like 'add caching to the user API' and wants a clear briefing before the agent writes code.

**The problem:** A vague request makes the agent guess. The guess can rest on an assumption you never made, and the work gets thrown away.

**The outcome:** A saved IntentSpec in .intent/ or .intent.yaml that records the probed facts, the one question you answered, and whether the intent is settled.

### Steps

1. Install the skill with `npx skills add angel291592/Intent-Router`, or follow the manual steps in Quick start. (inferred, check the README)
2. Give your agent the vague request in one sentence, in the same repo you want changed.
3. Let the skill probe the repo first, then answer only the question the repo cannot answer.
4. Open the saved file in .intent/ or .intent.yaml and check the probed fields and their evidence pointers.
5. Confirm the spec state reads settled before you let the agent carry out the work.

### Prompt to paste into your agent

```text
Using the Intent-Router skill in this repo, turn the request '<request>' into a typed IntentSpec. Probe the repo first and ask only the one question the repo cannot answer. Expected output: a saved IntentSpec file under .intent/ with evidence pointers and a state field. Verify that no probed field lacks an evidence pointer.
```

### Caveat

The README says the skill reads your repo, ticket system or docs before asking, so the number of questions depends on what those sources already answer.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/angel291592-intent-router/compile-vague-request-into-intentspec/

## How to delegate a task to an agent and check the result with Intent Router

Repo: [angel291592/Intent-Router](https://github.com/angel291592/Intent-Router) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Hand a settled spec to a coding agent, then compare the delivered work against each constraint.

**Who it is for:** A tech lead who delegates features to an AI agent and wants proof the output matches what was decided.

**The problem:** Delivered code often drifts from the original request, and a chat reply gives no record of what was decided.

**The outcome:** A spec file with each constraint marked met, with a code pointer, or not met, plus the check result written back into the same file.

### Steps

1. Install the skill with `npx skills add angel291592/Intent-Router`, or follow the manual steps in Quick start. (inferred, check the README)
2. Run the skill on the task in the same conversation as the coding work, so it can see the delivered result.
3. Let the agent carry out the settled spec as written.
4. Read the Intent check output, one line per constraint, marked met or not met.
5. Open the .intent/ file and confirm the check result was written back into it.

### Prompt to paste into your agent

```text
Using the Intent-Router skill in this repo, take the settled IntentSpec for '<task>' and carry it out as written. Then run the Intent check against the delivered code. Expected output: one line per constraint, each met with a code pointer or not met. Verify that the check result is saved in the same .intent/ file.
```

### Caveat

The README says the post-delivery check runs when the work happens in the same conversation, so a handoff to a separate session may not get this check.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/angel291592-intent-router/hand-off-delegated-task-with-contract-check/

## How to stop an agent from guessing past an irreversible step with Intent Router

Repo: [angel291592/Intent-Router](https://github.com/angel291592/Intent-Router) | Difficulty: Intermediate | Time: 15 minutes | Basis: From the README

Make the skill halt and name the field when an inferred value touches an irreversible boundary.

**Who it is for:** An engineer who runs agents on tasks with destructive or hard-to-undo actions and needs a stop before the agent commits.

**The problem:** Agents tend to pick a sensible default and keep going, so an irreversible action can happen on a value nobody confirmed.

**The outcome:** A HALT decision that names the unconfirmed field, so you can answer it before any routing happens.

### Steps

1. Install the skill with `npx skills add angel291592/Intent-Router`, or follow the manual steps in Quick start. (inferred, check the README)
2. Describe a task that includes a destructive or hard-to-undo action, leaving its target vague.
3. Watch for a HALT decision that names the field instead of a routed plan.
4. Answer the named field, then rerun the skill on the same request.
5. Confirm the saved spec records the decision state before the work proceeds.

### Prompt to paste into your agent

```text
Using the Intent-Router skill in this repo, process the request '<request>' and stop before routing if an inferred value touches an irreversible boundary. Expected output: a HALT decision that names the field to confirm. Verify that no routing or carrying out happened before you answered that field.
```

### Caveat

The README describes the HALT behavior but does not list which actions count as irreversible, so check the named field before trusting the stop.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/angel291592-intent-router/stop-irreversible-guesses-before-routing/