canonical: https://jentic.com/apis/mitchellapi.com/mitchellapi

# Mitchellapi Task Integration API

The Task Integration API keeps a partner system in step with Mitchell's claim workflow by updating assignment tasks and posting their status. It patches an appraisal assignment or a repair and rework assignment identified by a claim number and partner key, and records a status update against either assignment. It is a narrow integration surface for assignment handoff, not a full claims system.

## For AI agents

Update appraisal and repair assignment tasks on a Mitchell claim and post status updates for each, keyed by claim number and partner key. A narrow assignment-handoff integration surface.

## Scope

Does not create claims, estimate repair costs, or process payments. Use for updating appraisal and repair assignment tasks and their status only.

## Capabilities

- Update an appraisal assignment task on a claim
- Post a status update for an appraisal assignment
- Update a repair or rework assignment task on a claim
- Post a status update for a repair or rework assignment

## Use cases

### Agent-driven assignment sync

An AI agent in a partner shop keeps Mitchell's claim workflow current as work progresses. The Task Integration API patches the appraisal or repair assignment for a claim and posts a status update, so the agent can reflect each real-world step back into the claim. Through Jentic the operations are discovered by intent and the token is injected at call time.

Example prompt: Patch the appraisal assignment for a claim and post a status update reflecting the current stage

### Appraisal assignment updates

When an appraisal task changes, the partner records it against the claim. The Task Integration API updates the appraisal assignment identified by claim number and partner key and accepts a status update for it, so an agent can revise the assignment and mark its progress in two calls.

Example prompt: Update the appraisal assignment for a claim and partner key, then post its new status

### Repair assignment updates

Repair and rework assignments move through their own stages. The Task Integration API updates the repair or rework assignment for a claim and posts a status update against it, so an agent can keep the repair side of a claim synchronised as the shop works through it.

Example prompt: Update the repair assignment for a claim and post a status update when the repair stage advances

## Key endpoints

| Method | Path | Description |
| --- | --- | --- |
| PATCH | `/v1/claims/{claimNumber}/appraisalassignments/{partnerKey}` | Update an appraisal assignment task |
| POST | `/v1/claims/{claimNumber}/appraisalassignments/{partnerKey}/appraisalassignmentstatusupdate` | Post an appraisal assignment status update |
| PATCH | `/v1/claims/{claimNumber}/repairassignments/{partnerKey}` | Update a repair or rework assignment task |
| POST | `/v1/claims/{claimNumber}/repairassignments/{partnerKey}/repairassignmentstatusupdate` | Post a repair assignment status update |

## Key resources

- **Appraisal Assignments** — Update an appraisal assignment on a claim and post a status update for it
- **Repair Assignments** — Update a repair or rework assignment on a claim and post a status update for it

## AI readiness

This API is usable in Jentic One now. Its AI-readiness score against Jentic's framework shows where it stands today and where improvements would make it even easier for agents to use.

- **Score:** 51 / 100
- **Maturity:** Foundational
- **Dimensions:**
  - Foundational Compliance: 85 / 100
  - Developer Experience & Jentic Compatibility: 72 / 100
  - AI-Readiness & Agent Experience: 36 / 100
  - Agent Usability: 94 / 100
  - Security: 50 / 100
  - AI Discoverability: 25 / 100
- **View full report:** https://jentic.com/apis/mitchellapi.com/mitchellapi/scorecard
- **How the score is calculated:** https://docs.jentic.com/reference/api-readiness-framework/overview/
- **More about the dimensions:** https://docs.jentic.com/reference/api-readiness-framework/specification/#dimensional-model-overview

### Score it yourself

Every API in the directory is allowlisted, so you can re-score it with no key required.

- **Score your own API:** https://jentic.com/scorecard.md
- **Scoring CLI agent skill:** https://github.com/jentic/jentic-api-scorecard/blob/main/skills/jentic-api-scorecard/SKILL.md

```sh
npx @jentic/api-scorecard-cli score <openapi-url>
```

## Why Jentic

- **Setup:** Wiring the Task Integration API by hand means passing the Authorization token, building the claim-number and partner-key paths, and distinguishing the appraisal and repair assignment operations yourself. Through Jentic you install once, import it from the API Directory, store the token once, and your agent calls it.
- **Permission scoping:** Mitchell puts the claim number and partner key in the URL path, so a rule can pin your agent to the appraisal or repair assignment operations you pick for the claims it handles. You choose the operation set, so the repair-assignment operations are not included unless you add them.
- **Credential handling:** Your Mitchell token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
- **Discovery method:** Agents search Jentic by intent such as 'update a claim appraisal assignment' or 'post an assignment status update', and Jentic returns the matching Mitchell operation with its input schema so the agent calls the right endpoint without browsing the reference docs.

## Related APIs

- **Asana** — Asana assigns and tracks generic tasks, where Mitchell models insurance claim assignments.
- **ClickUp** — ClickUp tracks tasks, statuses, and workloads across a workspace.
- **Trello** — Trello boards can mirror assignment stages for a human view alongside Mitchell.

## FAQ

### What authentication does the Task Integration API use?

The Task Integration API expects a token in the Authorization header, declared as an api key in its OpenAPI spec. Through Jentic the token is stored once and injected at call time, so it never enters the agent's prompt, logs, or context.

### Can I update both appraisal and repair assignments with the Task Integration API?

Yes. There is a patch operation and a status-update operation for appraisal assignments and the same pair for repair and rework assignments, each keyed by claim number and partner key. An agent can update either assignment type and post its status.

### What are the rate limits for the Task Integration API?

The OpenAPI spec does not define numeric rate limits; the API is fronted by an Apigee gateway that governs them. Have your agent back off when it receives an HTTP 429 response and check with Mitchell for the limits on your partner key.

### Is there a Mitchell MCP server?

You don't need an MCP server to give your agent the Task Integration API. Jentic connects it directly from the API Directory: import it, store your token once, and your agent updates assignments through it. Operations are discovered on demand, so no extra tool definitions sit in the agent's context.

### Can I limit what my agent is allowed to do with the Task Integration API?

Yes. Mitchell puts the claim number and partner key in the URL path, so a rule can pin your agent to the appraisal or repair assignment operations you pick for the claims it handles. The repair-assignment operations are not included unless you add them, and every call it makes is logged.

### How do I update an assignment through Jentic?

Search Jentic for an intent such as 'update a claim appraisal assignment' and it returns the matching patch operation with its input schema, so your agent sends the claim number, partner key, and the changed fields. To run it on your own infrastructure, install Jentic One from its GitHub repo.