Adds documents, files, and web pages to the knowledge base, asks bots sourced questions, and keeps folders and history in order.
21actions available
Every action runs live through MCP. Nothing to build, nothing to maintain.
Ayro submits questions to Cody AI and receives intelligent responses, enabling document-aware answers grounded in your knowledge base. This powers instant expert-level support.
Ayro uploads documents to Cody AI's knowledge library, expanding the AI's training data so it answers questions grounded in your content. This builds institutional knowledge.
Ayro removes old or irrelevant conversation threads from Cody AI, keeping your workspace clean and focused on active sessions. This prevents context pollution.
Each card is one request a support team gets, and the Cody actions Ayro runs to close it.
Ayro creates a document from text or HTML, uploads a policy PDF or deck as a file, or imports a public webpage, so a knowledge gap that surfaced in a conversation is closed the same day.
Ayro opens a conversation against the right bot, sends the question, and retrieves the reply along with the documents it drew on, so the answer can be checked rather than trusted.
Ayro creates folders to group related material, searches documents by keyword or folder to find what already exists, and removes a superseded document so it stops feeding answers.
Ayro lists the bots on the account, filters conversation history by bot or keyword, and pages through the messages inside one to show how a question was actually handled.
How it works
Connect once, then just ask. There is no workflow builder to learn and nothing to maintain — Ayro reads the Cody actions it has and picks the ones a request needs.
Authorize the Cody account your team already uses — one consent screen, no API keys, no mapping tables. Ayro can only do what you granted that account, and you can disconnect it at any time.
Describe the job the way you would hand it to a teammate. Ayro maps it to the Cody actions that close it and chains as many as the request needs.
The agent runs the actions inside the conversation the customer is already in, so nobody copies data between tabs and your team can take over at any point.
Get started freeCody · Ayro
What can you do in Cody without me setting anything up?
These, right away:
Great, let's start with the first one.
FAQ
Setup, permissions, and the limits of what Ayro can do inside Cody.
Create Document accepts up to 768 KB of text or HTML content. For anything bigger, Create Document From File takes files up to 100 MB across txt, md, rtf, pdf, ppt, pptx, pptm, doc, docx, and docm, and processes them asynchronously, so Ayro checks learning status with Get Document before treating the content as searchable.
All 21 actions your agent can call on Cody, straight from the live MCP connection.
Create a new conversation with a specified bot.
Create a new document with text or HTML content in Cody AI.
Create a document by uploading a file (up to 100 MB).
Create a document from a publicly accessible webpage URL.
Create a new folder in Cody AI for organizing content.
Delete a conversation by its ID.
Delete a document by id.
Fetch a conversation by its ID from Cody AI.
Retrieve a specific document by its identifier from Cody AI.
Retrieve a specific folder by its identifier.
Fetch a specific message by its ID from Cody AI.
Get an AWS S3 signed upload URL for file uploads.
Get all bots with optional keyword filtering.
Get all conversations with optional filtering by bot, keyword, or includes.
Retrieve all documents from Cody AI account with optional filtering.
Retrieve all folders with optional keyword filtering.
Retrieve a paginated list of messages from Cody, optionally filtered by conversation.
Send a message to Cody AI and receive an AI-generated response.
Send a message to Cody AI and receive a Server-Sent Events (SSE) stream URL for the AI response.
Update a conversation by its ID including name, bot_id, and document_ids.
Update a folder by its ID.
Same connection, same setup. Pick the next one your team already uses.
Reads the available voice catalogue, returning each voice_id, name, gender, and language, and narrows it to one language code on request.
Answers off-catalog questions with live web, news, retail, travel, and maps results, then fetches the source page behind the answer.
Estimates the gender most often associated with a first name, optionally scoped to a country code, from the name a workflow already holds.
Synthesizes speech in preset or custom voices, returns word-level timings for captions, and keeps the voice library and usage in check.
Retrieves the passages that answer a query, ingests documents from files, URLs or raw text, and keeps the indexed material current.
Drafts product titles, social posts, emails, and video descriptions, then summarizes or translates them across 72+ languages.

Authorize the account and your agent has all 21 actions from the first conversation.
