Install Jentic One Beta

Connect the Task Integration API to your agent

Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the Task Integration API, or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.

Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.

Step 1: Jentic One Host machine

# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmitchellapi.com%2Fmitchellapi" | sh

Step 2: Agent machine

# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fmitchellapi.com%2Fmitchellapi" | sh
jentic register       # connects your agent to your Jentic One instance

Jentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.

Capabilities

What an agent can do with Task Integration API.

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

Patterns agents use Task Integration API for, with concrete tasks.

GET STARTED

Start building with Task Integration API

Explore with Jentic One

View OpenAPI Document

★ 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.

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.

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.

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

Key Endpoints

4 endpoints — the task integration api keeps a partner system in step with mitchell's claim workflow by updating assignment tasks and posting their status.

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

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

Why Jentic?

What agents get from Jentic-routed access to this vendor.

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 isolation

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.

Intent-based discovery

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.

FAQs

Specific to using Task Integration API through Jentic.

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.

Mitchellapi Task Integration API

AI ReadinessFoundational (C-)51/100

See full scorecard

Community OpenAPI document · agent-readyProductivityTask ManagementapiKey4 EndpointsREST

Know of an official OpenAPI document? Contribute it →

For 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.

Use for: Update an appraisal assignment on a claim, Post a status update for an appraisal assignment, Update a repair assignment task, Record a repair assignment status change

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

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.

Jentic One on Github View OpenAPI Document

Show dimension breakdown

Foundational Compliance

Base layer of spec validity and structural soundness.

Grade: ASignals: 4

99%

Lint Results

Aggregated quality score from linter diagnostics, weighted by severity.

100%

Resolution Completeness

Percentage of `$ref` references that resolve successfully.

100%

Specification Validity

Checks whether the API description parses successfully and conforms to its declared specification (e.g., OpenAPI).

42%

Structural Integrity

Structural correctness score based on schema issues using logarithmic dampening.

Developer Experience & Jentic Compatibility

Clarity, completeness, and ingestion readiness for developers and tooling.

Grade: A-Signals: 4

15%

Example Density

How richly the API is illustrated with examples.

100%

Example Validity

Percentage of examples that conform to their schemas.

75%

Response Coverage

Percentage of operations with complete response definitions (success, client error, server error).

100%

Tooling Readiness

Health of API ingestion, bundling, and resolution within Jentic pipelines.

AI-Readiness & Agent Experience

Semantic breadth, depth, and agent comprehension for AI systems.

Grade: FSignals: 4

35%

Description Coverage

Coverage of descriptions across API elements.

Error Standardization

Coverage of RFC 9457 Problem Details for error responses.

100%

OperationId Quality

Coverage, uniqueness, and casing consistency of operationIds for AI inference.

Summary Coverage

Coverage of summaries across operations/tags/info.

Agent Usability

Functional utility, complexity comfort, and AI orchestration readiness.

Grade: A+Signals: 1

94%

Complexity Comfort

Agent comfort level based on API operational and structural complexity.

Security

Trust, risk posture, and security compliance.

Grade: C-Signals: 1

50%

Authentication Strength

Average quality of security schemes based on authentication method strength (weakest link for OAuth2).

AI Discoverability

Findability, semantic richness, and reasoning readiness.

Grade: FSignals: 1

25%

Descriptive Richness

Clarity and depth of descriptions across API elements.

Connect the Task Integration API to your agent

Capabilities

Use Cases

Start building with Task Integration API

Key Endpoints

Why Jentic?

Related APIs

FAQs

Mitchellapi Task Integration API

Jentic AI Readiness Score

Task Integration API

Foundational Compliance

Lint Results

Resolution Completeness

Specification Validity

Structural Integrity

Developer Experience & Jentic Compatibility

Example Density

Example Validity

Response Coverage

Tooling Readiness

AI-Readiness & Agent Experience

Description Coverage

Error Standardization

OperationId Quality

Summary Coverage

Agent Usability

Complexity Comfort

Security

Authentication Strength

AI Discoverability

Descriptive Richness