miso.ai

Miso (Miso Technologies, askmiso.com) is an AI personalization, search, and answers platform for publishers, media companies, and retailers. Miso trains machine-learning "Engines" on three data sets a site already has — its log of historical and real-time user interactions, its catalog of products/content, and its users — and exposes the output as REST APIs for personalized semantic search, typo-tolerant autocomplete, product and user recommendations, and an LLM-grounded Q&A / "Answers" experience that answers questions using only the customer's own content (reducing hallucination). The platform ships JavaScript (client + server), Python, and PHP SDKs, a WordPress plugin, embeddable Ask / Explore / Hybrid Search web modules, and the Dojo console for training engines and managing API keys and environments.

miso.ai publishes 10 APIs on the APIs.io network, including Ask APIs API, Bulk API API, Experiment APIs API, and 7 more. Tagged areas include Company, Artificial Intelligence, Machine Learning, Search, and Recommendations.

miso.ai’s developer surface includes documentation, API reference, getting-started guide, quickstart, authentication, pricing, signup flow, and 21 more developer resources.

49.2/100 developing ▬ flat Agent 51/100 agent ready Full breakdown ↓
scored 2026-07-27 · rubric v0.5
AccessSelf serve
10 APIs 1 MCP Servers
CompanyArtificial IntelligenceMachine LearningSearchRecommendationsPersonalizationSemantic SearchLLMQuestion AnsweringPublishingMediaRetailEcommerceDevelopers

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-27 · rubric v0.5
Composite quality — 49.2/100 · developing
Contract Quality 13.9 / 25
Developer Ergonomics 15.7 / 20
Commercial Clarity 8.9 / 20
Operational Transparency 0.7 / 13
Governance 0.0 / 12
Discoverability 10.0 / 10
Agent readiness — 51/100 · agent ready
Machine-Readable Contract 18 / 18
Agentic Access Contract 0 / 15
MCP Server 12 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 8 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 0 / 7
Typed Event Surface 0 / 6
Agent Skills 5 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/misoai: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 10

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

miso.ai Ask APIs API

Miso's new Ask API is the next generation of question answering APIs. It is designed to provide accurate and concise answers to your questions based on your existing product doc...

miso.ai Bulk API API

The Bulk API provides an efficient interface for making multiple Search / Recommendations / Q&A requests in one API call. These requests will be executed concurrently at the Mis...

miso.ai Experiment APIs API

Miso's experiment APIs let you do the A/B testing of your current result with Miso. ### Start an experiment in Dojo. Login to the [dojo](https://dojo.askmiso.com) platform. Crea...

miso.ai Interaction APIs API

Miso’s Interaction APIs let you manage your Interaction records stored with Miso. ### Interaction records Your Interaction records tell Miso about user interactions with product...

miso.ai Product / Content APIs API

Miso's Product / Content APIs let you upload, read, and delete Product / Content records that represent your site's catalog. ### Product / Content records Miso analyzes your Pro...

miso.ai Product Recommendations API

APIs for recommending related products based on a given product.

miso.ai Q&A APIs API

The Q&A APIs API from miso.ai — 3 operation(s) for q&a apis.

miso.ai Search APIs API

The Search APIs API from miso.ai — 3 operation(s) for search apis.

miso.ai User APIs API

Miso’s User APIs let you upload, read, and delete User records that tell Miso about your site’s unique users and visitors. ### User records User records specify relatively stati...

miso.ai User Recommendations API

APIs for recommending products and content to users based on their interests.

Scroll for all 10

MCP Servers 1

Model Context Protocol servers that expose these APIs to AI agents.

misoai-mcp.yml

MCP SERVER

Security Posture 2

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

Misoai Authentication

apiKey · 1 scheme

SECURITY

Misoai Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Resources

Get Started 6

Portal, sign-up, and the first successful call

Documentation 2

Reference material describing how the API behaves

Agent Surfaces 3

MCP servers, agent skills, and machine-readable catalogs

Design & Contract 6

Pagination, idempotency, versioning, errors, and events

Build 3

SDKs, sample code, and the tooling you integrate with

Access & Security 2

Authentication, authorization, and security posture

Operate 2

Status, limits, changes, and where to get help

Commercial 3

Pricing, plans, and the legal terms of use

Company 1

The organization behind the API

Source (apis.yml)

apis.yml Raw ↑
x-enrichment:
  date: '2026-07-20'
  status: enriched
  artifacts_added: 20
  pass: local-v1
aid: misoai
name: miso.ai
description: Miso (Miso Technologies, askmiso.com) is an AI personalization, search, and answers platform for publishers,
  media companies, and retailers. Miso trains machine-learning "Engines" on three data sets a site already has — its log of
  historical and real-time user interactions, its catalog of products/content, and its users — and exposes the output as REST
  APIs for personalized semantic search, typo-tolerant autocomplete, product and user recommendations, and an LLM-grounded
  Q&A / "Answers" experience that answers questions using only the customer's own content (reducing hallucination). The platform
  ships JavaScript (client + server), Python, and PHP SDKs, a WordPress plugin, embeddable Ask / Explore / Hybrid Search web
  modules, and the Dojo console for training engines and managing API keys and environments.
url: https://raw.githubusercontent.com/api-evangelist/misoai/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- 500-global
x-tier: stub
x-tier-reason: portfolio-lead
accessModel:
  pricing: unknown
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Self-serve signup
  confidence: medium
  source:
  - authentication
  generated: '2026-07-22'
  method: derived
specificationVersion: '0.20'
created: '2026-07-17'
modified: '2026-07-20'
tags:
- Company
- Artificial Intelligence
- Machine Learning
- Search
- Recommendations
- Personalization
- Semantic Search
- LLM
- Question Answering
- Publishing
- Media
- Retail
- Ecommerce
- Developers
image: https://miso.ai/favicon.ico
apis:
- aid: misoai:misoai-ask-apis-api
  name: miso.ai Ask APIs API
  description: "Miso's new Ask API is the next generation of question answering APIs.\nIt is designed to provide accurate\
    \ and concise answers to your questions\nbased on your existing product documents.\n\nAsk API offers a seamless and effective\
    \ way to address complex queries in\na near-realtime fasion.\n\nMiso preprocesses your product documents, breaking them\
    \ into segments.\nWhen a question is received, Miso finds the most related product and segments, then\nsummarize to a\
    \ concise and informative answer based on the identified segments,\nincluding products related to the question.\n\nPossible\
    \ use case includes: knowledge base, documentation search, customer support, and more.\n\nTo use the Ask API, you first\
    \ submit a \"question\" you want to ask.\nQuestion can be any human-readable text. Then a question ID will returned,\n\
    and the question will be processed in the background.\n\nAfter receving question ID, you can then use the question ID\
    \ to get latest answer\nto the question as it is being compiled.\n\n----\n\nFor example:\n\nIf you want to know about\
    \ the inner workings of nginx:\n\n```json\n{\n    \"question\":\"How nginx works internally?\"\n}\n```\n\nThe API would\
    \ response with a question id.\n```json\n{\n    \"data\": {\n        \"question_id\": \"ff4775fa-345e-4d28-91b0-8fb8bf095e6a\"\
    \n    },\n    \"message\": \"success\"\n}\n```\n\nThen you can send a GET request to `/v1/ask/questions/{question_id}/answer`\n\
    to get the latest answer as it is being compiled and summerized.\nYou can use `answer_stage` and `finished` to check current\
    \ answer status.\n\nHere's the response of answer API when data is fetched and being verified, before answer is summerized:\n\
    ```json\n{\n    \"message\": \"success\",\n    \"data\": {\n        \"question\": \"How nginx works internally?\",\n \
    \       \"question_id\": \"ff4775fa-345e-4d28-91b0-8fb8bf095e6a\",\n        \"parent_question_id\": null,\n        \"\
    answer_stage\": \"Verifying possible answers\",\n        \"finished\": false,\n        \"answer\": \"Verifying possible\
    \ answers ...\",\n        \"sources\": [],\n        \"related_resources\": [],\n        \"followup_questions\": []\n \
    \   }\n}\n```\n\nHere's the response when answer is fullly summerized:\n\n```json\n{\n    \"message\": \"success\",\n\
    \    \"data\": {\n        \"question\": \"How nginx works internally?\",\n        \"question_id\": \"ff4775fa-345e-4d28-91b0-8fb8bf095e6a\"\
    ,\n        \"parent_question_id\": null,\n        \"answer_stage\": \"Generating summary\",\n        \"finished\": true,\n\
    \        \"answer\": \"# How does Nginx work internally?\\n\\n## Internal requests [1]\\n\\nNginx differentiates\nbetween\
    \ external and internal requests. External requests...[omitted for simplicity]\",\n        \"sources\": [\n          \
    \  {\n                \"title\": \"Internal requests\",\n                \"product_id\": \"9781788623551\",\n        \
    \        \"child_title\": \"Internal requests\",\n                \"child_id\": \"203\",\n                \"snippet\"\
    : \"<mark>Internal requests\\nNginx differentiates external and internal\nrequests.</mark>\"\n           \
    \ },\n            {\n                \"title\": \"5. Nginx Core Architecture\",\n                \"product_id\": \"9781484216569\"\
    ,\n                \"child_title\": \"5. Nginx Core Architecture\",\n                \"child_id\": \"5\",\n          \
    \      \"snippet\": \"Checks if the client can access of the requested the resource.\\n<mark>It\nis at this step\
    \ that Nginx...[omitted]</mark>\"\n            },\n            {\n                \"title\": \"2. Managing Nginx\"\
    ,\n                \"product_id\": \"9781785289538\",\n                \"child_title\": \"2. Managing Nginx\",\n     \
    \           \"child_id\": \"14\",\n                \"snippet\": \"<mark>The Nginx connection processing architecture\\\
    nBefore you study...[omitted]</mark>\"\n            },\n            {\n                \"title\": \"3. Nginx Core\
    \ Directives\",\n                \"product_id\": \"9781484216569\",\n                \"child_title\": \"3. Nginx Core\
    \ Directives\",\n                \"child_id\": \"3\",\n                \"snippet\": \"<mark>Understanding the Default\
    \ Configuration\\nThe default configuration...[omitted]</mark>\"\n            },\n            {\n              \
    \  \"title\": \"4. Nginx Modules\",\n                \"product_id\": \"9781484216569\",\n                \"child_title\"\
    : \"4. Nginx Modules\",\n                \"child_id\": \"4\",\n                \"snippet\": \"<mark>Based on the\
    \ context like HTTP, MAIL, and STREAM, it creates\na ...[omitted]</mark>\"\n            }\n        ],\n        \"\
    related_resources\": [],\n        \"followup_questions\": [\n            \"What are the steps involved in processing a\
    \ request and generating a response in Nginx?\",\n            \"How do Nginx modules contribute to the internal workings\
    \ of Nginx?\"\n        ]\n    }\n}\n```\n\nRelated product IDs will be returned along with human-readable answer. Related\
    \ text section in the product will also be quoted.\n\nIf a product has any children, they will also be matched, `child_id`\
    \ and `child_title` will be included for sources belonging to the product's children.\n\nYou can use `fq` to limit the\
    \ search scope, for example, to a specific product type or other condition.\n\nIf you only want to search for books (no\
    \ articles of videos), you can use `fq=type:book` like this:\n```json\n{\n    \"question\":\"How nginx works internally?\"\
    \n    \"fq\": \"type:book\"\n}\n```\n\nIf you want the answer to contain any other fields, set `source_fl` when submitting\
    \ the question."
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Ask APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-ask-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-bulk-api-api
  name: miso.ai Bulk API API
  description: "The Bulk API provides an efficient interface for making multiple Search / Recommendations / Q&A requests in\
    \ one API\ncall. These requests will be executed concurrently at the Miso side, and returned at once when all of them\
    \ are finished.\nThis API is particularly useful when you need to invoke multiple Miso APIs to respond to a user request.\n\
    Using this API, you can batch multiple API calls into one, and significantly save the network round-trip times.\n\n###\
    \ Request schema\nThe request schema for this API call is as follow:\n```\nPOST /v1/bulk\n{\n  \"requests\": [\n    {\n\
    \      \"api_name\": \"search/search\",\n      \"body\": { ... }\n    },\n    {\n      \"api_name\": \"recommendation/product_to_product\"\
    ,\n      \"body\": { ... }\n    },\n    ...\n  ]\n}\n```\nEach request object should contain:\n* **api_name**: name of\
    \ the API you want to access. The name should contain a slash `/`.\nFor example, search/search for search requests, search/autocomplete\
    \ for autocomplete requests, etc.\n* **body**: the complete request body as if you are making the API request individually.\n\
    \nAny errors in one of the requests will be returned, and will not prevent other requests from being\nexecuted.\n\n###\
    \ Response Schema\nBulk API endpoint will return the API responses in the same order as they appear in the request.\n\
    For example, if the Bulk API request is like the following:\n```\nPOST /v1/bulk\n{\n  \"requests\": [\n    {... request\
    \ 1 ...},\n    {... request 2 ...}\n  ]\n}\n``` \n\nThe response will be like:\n```\n{\n  \"data\": [\n    // response\
    \ for request 1\n    {\n      \"error\": false,\n      \"status_code\": 200,\n      \"body\": { ... }\n    },\n    //\
    \ response for request 2\n    {\n      \"error\": false,\n      \"status_code\": 200,\n      \"body\": { ... }\n    }\n\
    \  ]\n}\n```\n\nEach response object will contain the following fields:\n* **error**: whether there was an error with\
    \ the request. You should check this field to determine whether to\nperform error handling.\n* **status_code**: status\
    \ code of the request.\n* **body**: the response body of the request (as if the request was sent individually).\n\nLet's\
    \ see a complete example with MovieLens data. The following requests will issue two requests in one API call that \nreturn\
    \ the `Sci-Fi` movies directed by\n*Ridley Scott*, and *James Cameron* respectively in the first and second responses:\n\
    ```\nPOST /v1/bulk\n{\n  \"requests\": [\n    {\n      \"api_name\": \"search/search\",\n      \"body\": {\n        \"\
    user_id\": \"test_user\",\n        \"q\": \"sci-fi\",\n        \"fq\": \"custom_attributes.director:\\\"Ridley Scott\\\
    \"\"\n      }\n    },\n    {\n      \"api_name\": \"search/search\",\n      \"body\": {\n        \"user_id\": \"test_user\"\
    ,\n        \"q\": \"sci-fi\",\n        \"fq\": \"custom_attributes.director:\\\"James Cameron\\\"\"\n      }\n    }\n\
    \  ]\n}\n```\nThe response will be like:\n```\n{\n  \"data\": [\n    {\n      \"error\": false,\n      \"status_code\"\
    : 200,\n      \"body\": {\n        \"data\": {\n          \"took\": 136,\n          \"miso_id\": \"19ab254c-5fb8-11ec-bd48-b20169940af9\"\
    ,\n          \"products\": [\n            {\n              \"product_id\": \"blade-runner\",\n              \"title\"\
    : \"Blade Runner (1982)\"\n            }\n          ],\n          \"total\": 6,\n          \"start\": 0\n        }\n \
    \     }\n    },\n    {\n      \"error\": false,\n      \"status_code\": 200,\n      \"body\": {\n        \"data\": {\n\
    \          \"took\": 116,\n          \"miso_id\": \"19ab254c-5fb8-11ec-bd48-b20169940af9\",\n          \"products\": [\n\
    \            {\n              \"product_id\": \"avatar\",\n              \"title\": \"Avatar (2009)\"\n            }\n\
    \          ],\n          \"total\": 10,\n          \"start\": 0\n        }\n      }\n    }\n  ]\n}\n```"
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Bulk API
  properties:
  - type: OpenAPI
    url: openapi/misoai-bulk-api-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-experiment-apis-api
  name: miso.ai Experiment APIs API
  description: "Miso's experiment APIs let you do the A/B testing of your current result with Miso.\n\n### Start an experiment\
    \ in Dojo.\n\nLogin to the [dojo](https://dojo.askmiso.com) platform.\nCreate an experiment event for you.\n\n### Start\
    \ running A/B testing in your environment.\n\n#### Implement A/B testing code.\n\nHere's an example in NodeJS. You can\
    \ also use any programming language of you choice.\n```nodejs\nconst axios = require('axios');\n\nasync function get_user_experiment_info(api_key,\
    \ experiment_id, user_id) {\n    data = {\"user_id\": user_id}\n    endpoint = `https://api.askmiso.com/v1/experiments/${experiment_id}/events?api_key=${api_key}`\n\
    \    return await axios.post(endpoint, data)\n}\n\nconst api_key = '<YOUR_SECRET_API_KEY>'\nconst experiment_id = \"<EXPERIMENT_ID\
    \ | EXPERIMENT_SLUG_NAME>\"\nlet user_id = 'user_1234'  // use to evaluate a treatment for\n\nconst user_experiment_info\
    \ = get_user_experiment_info(api_key, experiment_id, user_id)\nuser_experiment_info.then((response) => {\n    let variant\
    \ = response.data['variant']\n    if (variant['name'] == \"treatment\") {\n        // insert code here to show \"treatment\"\
    \ variant\n    } else if (variant['name'] == \"control\") {\n        // insert code here to show \"control\" variant\n\
    \    } else {\n        // unexpected variant name. raise error\n        throw new Error(`Unexpected variant name ${variant[\"\
    name\"]}`)\n    }\n})\n```\n\nIf you implement A/B testing code in FrontEnd, like JavaScript, and are also worried about\
    \ exploding the secret api_key. You can choose to use anonymous_id with the public_api_key for this API. Here's an example.\n\
    \n```javascript\nconst apiKey = '<YOUR_PUBLIC_API_KEY>';\nconst experimentId = '<EXPERIMENT_ID | EXPERIMENT_SLUG_NAME>';\n\
    const anonymous_id = 'user_1234';  // use to evaluate a treatment for\n\nfunction getUserExperimentInfo(apiKey, experimentId,\
    \ anonymous_id) {\n  const data = {\n    user_id: anonymous_id\n  };\n  const url = `https://api.askmiso.com/v1/experiments/${experimentId}/events?api_key=${apiKey}`;\n\
    \  const options = {\n    method: 'POST',\n    headers: {\n      'Content-Type': 'application/json',\n    },\n    body:\
    \ JSON.stringify(data),\n  };\n\n  return window.fetch(url, options)\n    .then((response) => response.json())\n    .then((data)\
    \ => {\n      const variantName = data.variant.name;\n      if (variantName === `${this.treatmentName}`) {\n        //\
    \ insert code here to show 'treatment' variant\n      } else if (variantName === `${this.controlName}`) {\n        //\
    \ insert code here to show 'control' variant\n      } else {\n        // unexpected variant name, throw error\n      \
    \  throw new Error(`Unexpected variant name: ${variantName}`);\n      }\n    })\n    .catch((error) => console.error(error));\n\
    }\n\ngetUserExperimentInfo(apiKey, experimentId, anonymous_id);\n```"
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Experiment APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-experiment-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-interaction-apis-api
  name: miso.ai Interaction APIs API
  description: "Miso’s Interaction APIs let you manage your Interaction records stored with Miso.\n\n### Interaction records\n\
    Your Interaction records tell Miso about user interactions with products and content on your site or application.\nFrom\
    \ these interactions, Miso understands how users move through your conversion funnels: which products or content\nassets\
    \ attract the attention of each individual user, and which products or content ultimately will be purchased or\nconsumed\
    \ by each of them. With these insights, Miso makes real-time tailored recommendations for each user, and\nresponds to\
    \ each of their clicks and views on the site (even for anonymous users).\n\nInteraction records share some common attributes,\
    \ but are distinguished by their type.\nMiso captures 23 different interaction types, divided into the following 6 groups:\n\
    \n#### Core click-streams\n* `product_detail_page_view`: a user viewed the detail page for a product\n* `search`: a user\
    \ made a search request with keywords and (optionally) filters\n\nThe above interactions are the core fuel for Miso's\
    \ personalization Engines, because they happen in a much higher\nfrequency than other interactions and provide an unbiased\
    \ and high-fidelity view of users' interests on the site.\nThe collection of these interactions is highly important for\
    \ Miso's personalization performance. At the minimum,\nyou should implement the `product_detail_page_view` interaction\
    \ to start with.\n\n#### Conversion (eCommerce)\n* `add_to_cart`: a user added a product to the shopping cart\n* `remove_from_cart`:\
    \ a user removed a product from the shopping cart\n* `checkout`: a user checked out and started the payment process\n\
    * `refund`: a user refunded the product\n* `subscribe`: a user subscribed to a product\n\nThe above interactions are the\
    \ main revenue drivers for eCommerce sites. It’s important to collect them so that\nMiso can not only drive click-through\
    \ rates, but actually improve the revenue in a targeted way. To start with,\nyou should at least implement the `add_to_cart`\
    \ interaction.\n\n#### Consumption (content media)\n* `read`, `watch`, and `listen` interactions capture how and for how\
    \ long a user consumed a piece of content.\n* `add_to_collection`: a user added an product to their personal collection\n\
    * `remove_from_collection`: a user removed an product from their personal collection\n\nIf you are a content site, the\
    \ above interactions are the main drivers to users' satisfaction on the site.\nCollecting these interactions allows Miso\
    \ to drive consumption rates and consumption durations for the content on\nyour site. If you run a content site, you should\
    \ implement at least one of these interactions.\n\n#### Feedback signals\n* `like`, `dislike`, `share`, `rate`,  and `bookmark`\
    \ are common ways  users express their interests.\n\nThese are strong signals for Miso to understand each user's preferences\
    \ regarding your products or content. You\nshould send these signals to Miso if you have any of these UI patterns on your\
    \ site.\n\n#### Performance Checking\n* `impression`: a user saw or was presented with a product or content asset (but\
    \ didn't yet interact with it)\n* `viewable_impression`: the product or content presented is actually viewed by the user\n\
    \  (for example, minimum of 50% of the pixels were in viewable space for at least one continuous second.)\n* `click`:\
    \ a user clicked on something (for example, a product item)\n\n#### Additional click-streams\n* `home_page_view`: user\
    \ viewed your home page\n* `category_page_view`: a user viewed the page for a specific “group” or “family” or products\
    \ or content in your catalog\n* `promo_page_view`: user viewed the promotion pages about certain products\n* `product_image_view`:\
    \ user clicked on or otherwise interacted with  the product image (e.g. enlarged the image)\n\nThe above interactions\
    \ are additional signals for Miso to understand users' behavior on the site.\n\n#### Custom\n* `custom` interaction types\
    \ are reserved for you to define your own business-specific interaction types.\n\nMiso will analyze any custom interactions\
    \ you define to infer users' interests and preferences."
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Interaction APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-interaction-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-product-content-apis-api
  name: miso.ai Product / Content APIs API
  description: 'Miso''s Product / Content APIs let you upload, read, and delete Product / Content records that represent your
    site''s

    catalog.


    ### Product / Content records

    Miso analyzes your Product / Content records to provide personalized search and recommendations that connect users

    with products or content on your site or application.


    Much of Miso''s search and personalization capability relies on understanding your catalog in-depth and drawing

    correlations between your catalog and your users'' consumption or purchasing behaviors. In other words, Miso

    discovers that, with high correlation, users who are interested in certain product attributes would also be

    interested in other products with similar or related attributes. (For simplicity, we will often overload the word

    "products" to mean items for purchase if you are an eCommerce business, and content to consume if you are a content

    marketplace.)


    To fully optimize your search and recommendations, it is important to provide Miso with Product / Content records

    that are complete and accurate. We define a set of common attributes that capture the basics of most eCommerce and

    content media products, such as `title`, `description`, `categories`, `tags`, `material`, `authors`, etc.


    If your products'' characteristics cannot be fully captured by these fields, we recommend that you specify

    `custom_attributes`. For Miso, the more complete the product information is, the better its personalized search

    and recommendations become.'
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Product / Content APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-product-content-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-product-recommendations-api
  name: miso.ai Product Recommendations API
  description: APIs for recommending related products based on a given product.
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Product Recommendations
  properties:
  - type: OpenAPI
    url: openapi/misoai-product-recommendations-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-q-a-apis-api
  name: miso.ai Q&A APIs API
  description: The Q&A APIs API from miso.ai — 3 operation(s) for q&a apis.
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Q&A APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-q-a-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-search-apis-api
  name: miso.ai Search APIs API
  description: The Search APIs API from miso.ai — 3 operation(s) for search apis.
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - Search APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-search-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-user-apis-api
  name: miso.ai User APIs API
  description: 'Miso’s User APIs let you upload, read, and delete User records that tell Miso about your site’s unique users
    and

    visitors.


    ### User records

    User records specify relatively static attributes for a given user, such as their `age`, `gender`, `city`, etc. As a

    rule of thumb, you should put information here that is not already captured in your

    [Interaction records](#tag/Interaction-APIs). For example, *last_bought_product* is probably not needed here because

    Miso already can tell that from the [Interaction records](#tag/Interaction-APIs).


    Miso will discover the correlations between a user''s attributes and their behaviors on your site. For example, Miso

    might determine that users of a certain age group tend to be interested in certain products or a certain price

    range. These insights will be taken into account when predicting users'' interests, in particular for new users who

    have not yet generated many interaction records.


    We define a set of common user attributes for e-Commerce and content media sites. Some of them, such as `name` are

    for display in the Dojo dashboard only. The rest are for model quality. Most attributes are optional and you don''t

    need to specify them if you don''t collect such data. On the other hand, you can specify your custom user attributes

    in the `custom_attributes` field. Miso will analyze custom user attributes to improve the model quality as well.'
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - User APIs
  properties:
  - type: OpenAPI
    url: openapi/misoai-user-apis-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
- aid: misoai:misoai-user-recommendations-api
  name: miso.ai User Recommendations API
  description: APIs for recommending products and content to users based on their interests.
  humanURL: https://docs.miso.ai/api-reference/introduction
  baseURL: https://api.askmiso.com
  tags:
  - User Recommendations
  properties:
  - type: OpenAPI
    url: openapi/misoai-user-recommendations-api-openapi.yml
  - type: Documentation
    url: https://docs.miso.ai/api-reference/introduction
  - type: Authentication
    url: authentication/misoai-authentication.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: Website
  url: https://miso.ai/
- type: DeveloperPortal
  url: https://docs.miso.ai/
- type: Documentation
  url: https://docs.miso.ai/api-reference/introduction
- type: APIReference
  url: https://docs.miso.ai/api-reference/introduction
- type: GettingStarted
  url: https://docs.miso.ai/introduction/getting-started
- type: Quickstart
  url: https://docs.miso.ai/introduction/quickstart-ask
- type: Authentication
  url: authentication/misoai-authentication.yml
- type: Pricing
  url: https://docs.miso.ai/introduction/pricing
- type: SignUp
  url: https://miso.ai/get-answers
- type: Login
  url: https://dojo.miso.ai
- type: TermsOfService
  url: https://miso.ai/terms-of-service
- type: PrivacyPolicy
  url: https://miso.ai/privacy-policy
- type: Support
  url: https://docs.miso.ai/support/faqs
- type: HelpCenter
  url: https://docs.miso.ai/support/answers-faqs
- type: GitHubOrganization
  url: https://github.com/MisoAI
- type: Sandbox
  url: https://dojo.miso.ai
- type: SDKs
  url: packages/misoai-packages.yml
- type: Packages
  url: packages/misoai-packages.yml
- type: LLMsTxt
  url: llms/misoai-llms.txt
- type: MCPServer
  url: mcp/misoai-mcp.yml
- type: Conventions
  url: conventions/misoai-conventions.yml
- type: ErrorCatalog
  url: errors/misoai-problem-types.yml
- type: Lifecycle
  url: lifecycle/misoai-lifecycle.yml
- type: Conformance
  url: conformance/misoai-conformance.yml
- type: DomainSecurity
  url: security/misoai-domain-security.yml
- type: DataModel
  url: data-model/misoai-data-model.yml
- type: Components
  url: components/misoai-components.yml
- type: AgentSkill
  url: skills/_index.yml