How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC
Assembled website screenshot

Assembled

Assembled is a San Francisco-headquartered support operations platform that unifies workforce management (WFM), AI agents, and AI Copilot for modern customer support teams. Founded in 2020 by former Stripe operations engineers, Assembled lets support leaders plan, schedule, and orchestrate a hybrid workforce of in-house agents, BPO vendors, and AI agents from a single system. The platform delivers ML-based volume forecasting, automated schedule generation, real-time adherence, time-off and shift-swap automation, vendor capacity planning, multichannel routing, and structured reporting across phone, email, chat, SMS, social, and back-office channels. Its AI surface includes autonomous AI Agents that resolve customer conversations end-to-end across chat, email, SMS, and voice, plus AI Copilot, which drafts replies, translates in real time, and surfaces knowledge for human agents. The Assembled REST API (api.assembledhq.com/v0) exposes people, queues, sites, teams, skills, activities, agent states, forecasts, time-off requests, requirements, working hours, QA scores, structured reports, and the Assist endpoints for AI chat responses and knowledge articles. Assembled is used by Stripe, Etsy, Robinhood, Webflow, Canva, Duolingo, Autodesk, HubSpot, Intercom, and Ramp, and integrates with Zendesk, Salesforce Service Cloud, Intercom, Kustomer, Gladly, Gorgias, Dixa, ServiceNow, Five9, Genesys Cloud, Talkdesk, Amazon Connect, NiCE, UJET, Zoom Contact Center, Slack, Okta, Workday, HiBob, Google Calendar, Shopify, Notion, Confluence, Guru, SharePoint, Fivetran, and quality tools like Klaus, Rippit (MaestroQA), evaluagent, and Observe.AI.

agent aware

Solid contracts, transparent operations, and an easy start — typically complete on four or five facets with one clear soft spot.

Kin Score

API Evangelist profiles Assembled the way a machine reads it — 126 machine-readable artifacts across 4 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.

Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Assembled scores 59.2/100 (strong), with a separate agent-readiness read of 24/100 (agent aware). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.

Kin Score

This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance. Every facet and dimension name is a link: it opens that measurement's page on APIs.io, where the rating runs across the whole catalog — the exact checks that feed it, how every profiled provider distributes on it, and who is at the top of it.

Kin Score Kin Score How this is scored →
scored 2026-09-10 · rubric v0.20.0
Assembled Kin Score — API readiness rating by API Evangelist

Put this on your own site. The badge is drawn live from Assembled's current Kin Score — paste it once and it updates itself every time the score is recomputed. It follows your visitor's light or dark setting, and it links back here so anyone who sees it can read the full breakdown.

<!-- Kin Score · API Evangelist -->
<a href="https://providers.apievangelist.com/providers/assembled/"
   title="Assembled on API Evangelist — API profile and Kin Score">
  <img src="https://apis.io/badge/assembled.svg"
       alt="Assembled Kin Score — API readiness rating by API Evangelist" width="150" height="150" loading="lazy">
</a>

More shapes, themes and sizes → · Score as JSON · How badges work

How we profile Assembled

Each block below is one kind of artifact we hold for Assembled. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.

APIs 27

Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.

Individual APIs this provider publishes, each with its own machine-readable definition.

Assembled People API

Manage agents (people) in the Assembled workforce. List, retrieve, create, and update agents along with their roles, channels, skills, and team assignments. The People API is th...

Assembled Agent State API

Read and write real-time agent state used to drive adherence reporting, live dashboards, and dynamic routing. Supports bulk state ingestion from upstream telephony and CRM platf...

Assembled Activities API

Create, list, and delete activities — the scheduled shifts, breaks, time off, training, and meetings that make up an agent's calendar. Includes bulk creation, soft-delete semant...

Assembled Forecasts API

Retrieve Assembled's ML-generated forecasts, forecast totals, manual adjustments, and detected outliers. The forecasted-vs-actuals endpoint compares predicted to realised volume...

Assembled Time Off API

Programmatically create, list, and cancel time-off requests, and pull a stream of time-off updates for downstream HRIS or payroll synchronisation. The endpoint underpins the aut...

Assembled Requirements API

Create and list staffing requirements that express how many agents are needed by queue, site, team, or skill across time intervals. Requirement types describe the family of need...

Assembled Conversations API

Bulk-ingest and bulk-update customer conversation records — phone, email, chat, SMS, social, and back-office — so they can be associated with agents, queues, and channels for re...

Assembled Reports API

Asynchronously generate and retrieve structured reports including adherence, ticket statistics, and handle times. Reports are kicked off with a POST /v0/reports/:reportType call...

Assembled Activity Types API

Types/categories of activity

Assembled Agent Associations API

Map platform IDs to Assembled people

Assembled Assist Articles API

The Assist Articles API from Assembled — 2 operation(s) for assist articles.

Assembled Assist Conversations API

The Assist Conversations API from Assembled — 2 operation(s) for assist conversations.

Assembled Assist Replies API

The Assist Replies API from Assembled — 1 operation(s) for assist replies.

Assembled Assist Responses API

The Assist Responses API from Assembled — 2 operation(s) for assist responses.

Assembled Event Changes API

Audit trail of schedule modifications

Assembled Forecast Adjustments API

The Forecast Adjustments API from Assembled — 3 operation(s) for forecast adjustments.

Assembled Forecast Outliers API

The Forecast Outliers API from Assembled — 3 operation(s) for forecast outliers.

Assembled Forecast Totals API

The Forecast Totals API from Assembled — 2 operation(s) for forecast totals.

Assembled Forecasts Vs Actuals API

The Forecasts Vs Actuals API from Assembled — 1 operation(s) for forecasts vs actuals.

Assembled Quality Assurance API

The Quality Assurance API from Assembled — 1 operation(s) for quality assurance.

Assembled Queues API

The Queues API from Assembled — 2 operation(s) for queues.

Assembled Requirement Types API

The Requirement Types API from Assembled — 1 operation(s) for requirement types.

Assembled Roles API

Available roles that can be assigned to people

Assembled Sites API

The Sites API from Assembled — 2 operation(s) for sites.

Assembled Skills API

The Skills API from Assembled — 2 operation(s) for skills.

Assembled Teams API

The Teams API from Assembled — 2 operation(s) for teams.

Assembled Working Hours API

The Working Hours API from Assembled — 2 operation(s) for working hours.

Scroll within the panel for all 27 ·

Postman Collections 12

A runnable collection turns the contract into something a developer can execute in seconds. We profile them because the fastest way to trust an API is to make a real call against it.

Ready-to-run Postman collections for exercising this provider's APIs.

Scroll within the panel for all 12 ·

Open Collections 32

Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Assembled Activities API

OPEN COLLECTION

Assembled Assist API

OPEN COLLECTION

Assembled Filters API

OPEN COLLECTION

Assembled QA API

OPEN COLLECTION

Scroll within the panel for all 32 ·

Arazzo Workflows 15

Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.

Multi-step API workflows described with the Arazzo specification.

Assembled Update an Agent Profile

Find an agent in the workforce, read their full profile, then patch their attributes.

ARAZZO

Assembled Associate Platform IDs to an Agent

Confirm an agent exists, map upstream platform identifiers to them, then read back the linked record.

ARAZZO

Assembled Audit Schedule Changes

List the activities scheduled in a window, then pull the audit trail of changes to them.

ARAZZO

Assembled Review and Cancel a Time Off Request

List pending time-off requests and cancel the first one, branching on whether any exist.

ARAZZO

Assembled Turn a Forecast into a Staffing Requirement

Read the volume forecast for a window, resolve a requirement type, then create a staffing requirement.

ARAZZO

Assembled Generate and Retrieve a Report

Start an async report job, then fetch the result, branching on completion status.

ARAZZO

Assembled Ingest and Enrich Conversations

Bulk-upsert customer conversation records, then bulk-update them with enriched fields.

ARAZZO

Assembled Create and Read a Forecast Total

Create a forecast total for a queue window, list totals to find it, then fetch it in full.

ARAZZO

Assembled Provision a New Agent

Resolve an available role, create a new agent, then read back the created record.

ARAZZO

Assembled Provision a Queue and Staff It

Create a routing queue, pick an active agent, then schedule an activity routed to that queue.

ARAZZO

Assembled Request Time Off for an Agent

Confirm the agent exists, create a time-off request, then verify it in the request list.

ARAZZO

Assembled Review an Agent's Working Hours

List the working-hours rules for an agent, then fetch the first rule in full.

ARAZZO

Assembled Schedule an Agent Shift

Resolve an activity type, create a scheduled activity, then list it back on the calendar.

ARAZZO

Assembled Staff a Shift for a Workforce Agent

Pick an active agent from the workforce, then schedule a shift activity for them.

ARAZZO

Assembled Stream and Verify Agent State

Confirm an agent exists, push a batch of state records, then read back the condensed timeline.

ARAZZO

Scroll within the panel for all 15 ·

Pricing Plans 1

Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the things the Kin Score reads for access clarity — renamed from commercial clarity in rubric 0.12, because a free statutory interface has access terms and no commercial ones.

Published pricing tiers and plan structures.

Rate Limits 1

Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.

Documented rate limits and quota policies.

Assembled Rate Limits

2 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.

Cost, billing, and metering signals for API financial operations.

Features 20

The notable capabilities this provider advertises, captured as structured features so they can be searched and compared instead of read one landing page at a time.

Notable capabilities this provider offers.

ML-based forecasting with >90% accuracy across phone, email, chat, SMS, social, and back-office channels
AI-powered schedule generation that accounts for both human and AI agent coverage
Real-time adherence and live performance dashboards with intelligent case routing
Unified workforce management for in-house agents, BPO vendors, and AI agents
Automated time-off and shift-swap workflows (Pro and Enterprise)
Custom API integrations and white-glove onboarding (Enterprise)
AI Agents — autonomous multichannel resolution across chat, email, SMS, and voice with smart handoffs
AI Copilot — reply drafting, real-time translation, summarisation, agent guidance, and tone modifiers
Agentic workflows, escalation rules, custom style guides, and built-in QA tools for AI Agents
Vendor Management add-on with capacity planning, scheduling integration, coverage heatmaps, and billing reports
Structured reports for adherence, ticket statistics, and handle times via async report jobs
Quality assurance score ingestion from Klaus, Rippit (MaestroQA), evaluagent, Observe.AI
REST API at https://api.assembledhq.com/v0/ with HTTP Basic Auth (sk_live_ API keys)
Date-based API versioning via the API-Version request header
Default rate limit of 300 requests per minute (5 req/s) with bursts up to 20
Bulk operations supported across most write endpoints, plus soft-delete semantics
Native integrations across CCaaS (Five9, Genesys Cloud, Talkdesk, Amazon Connect, NiCE, UJET, Zoom), CRM/helpdesk (Zendesk, Salesforce, Intercom, Kustomer, Gladly, Gorgias, Dixa, ServiceNow), HRIS (Workday, HiBob), knowledge bases (Notion, Confluence, Guru, SharePoint, Google Drive), Fivetran data pipeline, Slack, Okta, Google Calendar, and Shopify
Official iOS and Android SDKs for embedding the Assembled chat widget into mobile applications
SOC 2, GDPR, and HIPAA compliance with enterprise-grade security and policy guardrails
Scheduling 4.5+ billion events per year for ~100,000 agents across 50+ countries (2025)

Scroll within the panel for all 20 ·

Semantic Vocabularies 1

JSON-LD contexts give the data shared meaning across APIs. We profile them because semantics are what let a machine reconcile 'customer' here with 'customer' somewhere else.

JSON-LD contexts and semantic vocabularies used across these APIs.

Assembled Context

0 classes · 6 properties

JSON-LD

Spectral Rules 2

Governance rulesets we run against this provider's specs — the automated checks behind parts of the score. Profiling them makes the quality bar explicit and re-runnable, not a matter of opinion.

Assembled API Rules

5 rules · 4 warnings

SPECTRAL

Assembled API Rules

8 rules · 3 errors · 4 warnings

SPECTRAL

JSON Schema 4

Standalone JSON Schema definitions describe the data models behind the API. We profile them so the shapes are validatable on their own — useful long after a single request is forgotten.

Standalone JSON Schema definitions for this provider's data models.

AssembledActivity

11 properties

JSON SCHEMA

AssembledAssistResponse

9 properties

JSON SCHEMA

AssembledConversation

16 properties

JSON SCHEMA

AssembledPerson

15 properties

JSON SCHEMA

Examples 5

Real request and response payloads are what turn a spec from abstract into obvious — and they're one of the twelve things an agent needs to call an API correctly on the first try.

Example request and response payloads for these APIs.

Security Posture 4

Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Assembled Authentication

http · 1 scheme

SECURITY

Assembled Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Assembled Vulnerability Disclosure

disclosure policy published

SECURITY

Assembled Trust Center

SOC 2, GDPR

SECURITY

Agentic Access 1

An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.

Recommended x-agentic-access execution contracts for AI agents.

Assembled Agentic Access

70 operations · 41 acting · 3 human-in-the-loop

70 operations · 41 acting

AGENTIC

Resources

Every other property we hold for Assembled — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.

Get Started 4

Portal, sign-up, and the first successful call

Documentation 1

Reference material describing how the API behaves

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

Learn 1

Tutorials, courses, talks, and written guidance

Operate 4

Status, limits, changes, and where to get help

← All providers · Data indexed from github.com/api-evangelist/assembled · machine-readable index on apis.io

Where this information came from

This is an independent, third-party profile of Assembled, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.