[Home](/) / Use cases

Use cases

# What you can send to a human.

hitl.ph accepts five core task types — the moments an AI agent hits a wall only a person can get over. Each maps to a literal `task.type` you send on the wire, and each is owned end to end by a named, accountable specialist.

## 01 — Review a document

`task.type = "document.review"`

Something a model shouldn’t sign off on alone — a contract clause, a medical note, a flagged edge case. A trained person reads it, applies judgement, and returns a decision with reasoning.

### Typical uses

-   Contract clause review
-   Medical or clinical note check
-   Flagged edge-case adjudication
-   Quality assurance on model output

## 02 — Make a phone call

`task.type = "voice.call"`

Confirm a booking, chase a supplier, verify a detail. The jobs that still need a human voice on the line. The specialist makes the call and returns the outcome and any notes.

### Typical uses

-   Booking confirmation
-   Supplier or vendor follow-up
-   Detail or identity verification by phone
-   Appointment chasing

## 03 — Validate ambiguous data

`task.type = "data.validate"`

Two records that might be the same person. A field that doesn’t parse. The judgement calls models guess at and get wrong. A person resolves the ambiguity and returns a clean, confident answer.

### Typical uses

-   Entity / duplicate resolution
-   Data deduplication and matching
-   Unparseable field interpretation
-   Edge-case classification

## 04 — Take a photo, check the world

`task.type = "world.capture"`

Confirm something physically exists, capture proof, or eyeball a real-world state your agent can’t see from a server, then send back what was found.

### Typical uses

-   Proof-of-existence capture
-   Physical state verification
-   On-the-ground photo capture
-   Real-world status check

## 05 — Make the call you can’t automate

`task.type = "decision.own"`

The decision that needs real accountability — a person who owns the outcome, signs their name to it, and stands behind it. Not a confidence score. A named specialist makes the call and returns it with their reasoning.

### Typical uses

-   Accountable approval / sign-off
-   Ambiguous escalation handling
-   High-stakes judgement call
-   Human-owned exception

## AI agent human handoff

The five task types share one moment: the point where your agent stops guessing and hands the work to a person. A low-confidence answer, a task it cannot resolve, a customer who has had enough of talking to a bot — that is when the agent needs human escalation, not another retry. hitl.ph is built to be that escalation point: the agent posts the task, keeps working on everything else, and picks the person’s answer up on a webhook.

`# the agent hits a step it cannot resolve and hands off curl https://api.hitl.ph/v1/tasks \ -H "Authorization: Bearer $HITL_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "type": "decision.own", "brief": "Refund request falls outside policy — approve or decline, with the reason.", "context": { "url": "https://your-app.com/tickets/4821" }, "return": { "mode": "webhook", "url": "https://your-app.com/hooks/hitl" } }'`

Request · the agent carries on; the human's decision returns on the webhook

## Not sure which fits?

If a step in your agent needs real-world judgement, a human voice, physical confirmation, or someone accountable for the outcome, it belongs in the loop. Read [what human in the loop means](/human-in-the-loop/), see the [integration shape](/docs/), or just send us the moment your agent gets stuck and we will map it to a task type.

## Wire a human into your stack.

hitl.ph is onboarding its first agencies now. Request access and the team will send you a key.

Need someone in the seat? We help you [find full-time staff](/pricing/), too.

***

Source: https://www.hitl.ph/use-cases/
This is the markdown representation of that page, served to clients that send `Accept: text/markdown`.
Machine-readable index: https://www.hitl.ph/llms.txt · Knowledge bundle: https://www.hitl.ph/okf/index.md