# Abundly - [Welcome](https://docs.abundly.ai/introduction/welcome.md): Learn about the Abundly agent platform - [What is an AI Agent?](https://docs.abundly.ai/introduction/what-is-an-agent.md): Understanding autonomous AI agents and how they work - [Getting Started](https://docs.abundly.ai/introduction/getting-started.md): Create your first AI agent in minutes - [Platform Overview](https://docs.abundly.ai/introduction/platform-overview.md): A quick tour of the Abundly interface - [Pricing](https://docs.abundly.ai/introduction/pricing.md): Understanding Abundly pricing and credit usage - [Agent Instructions](https://docs.abundly.ai/features/instructions.md): Configure the behavior of your agent - [Configurable Capabilities](https://docs.abundly.ai/features/capabilities.md): Give your agent the tools it needs to do its job - [Skills](https://docs.abundly.ai/features/skills.md): Step-by-step guides your agent loads on demand, built in or added by you - [Multi-channel Communication](https://docs.abundly.ai/features/communication.md): Agents communicate through chat, email, SMS, voice calls, and more - [Advanced Chat](https://docs.abundly.ai/features/chat.md): A feature-rich chat interface for interacting with your agent - [Email & SMS](https://docs.abundly.ai/features/messaging.md): Send and receive emails and text messages - [Voice Communication](https://docs.abundly.ai/features/voice.md): Talk to your agent and receive audio responses - [Live Voice](https://docs.abundly.ai/features/live-voice.md): Talk with your agent in a real-time voice conversation - [Agent Documents](https://docs.abundly.ai/features/documents.md): Agents can read, edit, and create documents, apps, databases, and executable scripts - [Agent Databases](https://docs.abundly.ai/features/agent-databases.md): Instant structured data stores your agent can create, query, and update—no setup required - [Interactive Apps](https://docs.abundly.ai/features/apps.md): Agents build web applications on demand—dashboards, forms, calculators, and custom tools - [Code Execution](https://docs.abundly.ai/features/scripts.md): Agents can write and run code for faster, cheaper, and more reliable automation - [Virtual Machine](https://docs.abundly.ai/features/virtual-machine.md): Give your agent a Linux VM for code, scripts, and file processing - [Scheduled Tasks](https://docs.abundly.ai/features/scheduling.md): Let your agent work proactively by scheduling recurring and one-off tasks - [Context and Memory](https://docs.abundly.ai/features/memory.md): How agents know what they know, and remember across conversations - [Web Search, Scraping, Deep Research, and Docs](https://docs.abundly.ai/features/search.md): Search the web, read pages, and conduct deep research to find current information - [Multi-Agent Collaboration and Task Delegation](https://docs.abundly.ai/features/multi-agent.md): Agents can delegate to temporary sub-agents or communicate with other persistent agents - [Model Selection](https://docs.abundly.ai/features/model-selection.md): Choose the right LLM for your agent's needs—or let the platform pick for you - [Agent Personalization](https://docs.abundly.ai/features/personalization.md): Give your agent a distinct appearance and personality - [Agent Evals](https://docs.abundly.ai/features/evals.md): Test and evaluate your agents with automated test cases - [Activity Monitoring](https://docs.abundly.ai/features/monitoring.md): Real-time monitoring and audit trails for agent activities - [Usage & Limits](https://docs.abundly.ai/features/usage.md): Track credit consumption, agent activity, and set daily and monthly limits for your agents - [Value tracking](https://docs.abundly.ai/features/value-tracking.md): Say what each agent is worth to you, rate how critical it is, and count the outcomes it produces — all next to its usage and cost - [Workspace Members](https://docs.abundly.ai/features/workspace-members.md): Invite colleagues and manage who has access to your workspace - [Teams](https://docs.abundly.ai/features/teams.md): Organize agents and users into logical teams for better access control and delegation - [Agent management](https://docs.abundly.ai/features/agent-management.md): Centralized administration for managing agents, filters, and limits across your workspace - [Agent lifecycle phases](https://docs.abundly.ai/features/agent-lifecycle.md): Keep experimental agents in a sandbox and promote them to production when they are ready, with phase-specific credentials and a credit reserve - [Agent Sharing and Cloning](https://docs.abundly.ai/features/sharing.md): Clone agents within your workspace or share them publicly for others to use - [HTTP Requests: Connect to Any API](https://docs.abundly.ai/features/http.md): Connect your agent to any online service with a REST API - [Incoming Endpoints](https://docs.abundly.ai/features/agent-api-endpoint.md): Let external systems reach your agent via webhooks, an HTTP API, MCP, or an embeddable chat widget - [Workspace API](https://docs.abundly.ai/features/workspace-api.md): API access to read workspace data and administer agents using workspace API keys - [Chat Widget](https://docs.abundly.ai/features/chat-widget.md): Embed an AI-powered chat bubble on any website with a secure backend proxy - [List agent promotion requests](https://docs.abundly.ai/api-reference/list-agent-promotion-requests.md): Promotion requests across the workspace, newest first, each with its review steps and the decisions taken so far. Unlike the portal's review page this is not filtered by reviewer — a workspace key sees every request, including those for restricted and personal agents. `reviewersByStepId` is only res… - [Read the user action log](https://docs.abundly.ai/api-reference/read-the-user-action-log.md): Who changed which agent, team or workspace setting, who invited or added whom, and when, newest first — the same rows as Usage › User action log in the portal, restricted, personal and deleted agents included. `kind` tells setting changes ("resource") from invitations and workspace and team membersh… - [Get workspace configuration](https://docs.abundly.ai/api-reference/get-workspace-configuration.md): Workspace-level settings: feature flags, credit defaults, account rules, DPA and subprocessor settings, login settings, tags, the configured LLMs, and the retired value capture configuration (deprecated, removed in a later release). - [Get credit balances and current usage](https://docs.abundly.ai/api-reference/get-credit-balances-and-current-usage.md): A live snapshot: workspace balances, credits used today per agent (all agents, including disabled, restricted and personal ones), credits used this month per team, and per owner of personal agents. Accepts no date filters and keeps no history — snapshot the response yourself if you need a time serie… - [List workspace members](https://docs.abundly.ai/api-reference/list-workspace-members.md): Every member with their workspace role, team memberships, and basic profile info. Abundly staff on a support grant are included with the role `support`. - [List workspace invitations](https://docs.abundly.ai/api-reference/list-workspace-invitations.md): Pending and expired invitations, which doubles as a record of who was invited but never joined. - [Invite someone to the workspace](https://docs.abundly.ai/api-reference/invite-someone-to-the-workspace.md): Email an invitation to join the workspace as a Creator (`member`) or Collaborator, optionally into teams. Admins and guests can't be invited through the API. Requires the Invite members scope. Returns 400 when the person is already a member or already has a pending invitation (so a retried call neve… - [List teams](https://docs.abundly.ai/api-reference/list-teams.md): All teams in the workspace, each with its tags, monthly credit limit and settings. Payload fields use the internal name for teams, so a team id appears as `groupId`. - [Create a team](https://docs.abundly.ai/api-reference/create-a-team.md): Create a team, optionally with tags so it is never left untagged. Team names don't have to be unique, so a create retried after a timeout can leave a duplicate — look the team up with `/workspaceapi/teams?tag=…` or `?name=…` before retrying. Returns 400 when team settings are not enabled for the wor… - [Get a team](https://docs.abundly.ai/api-reference/get-a-team.md): A single team with its full member list. - [Rename a team](https://docs.abundly.ai/api-reference/rename-a-team.md): Rename a team. Returns 400 when team settings are not enabled for the workspace. - [List workspace secrets](https://docs.abundly.ai/api-reference/list-workspace-secrets.md): Secret names and metadata, including which agents, admins and teams can use each one. Values are masked server-side and never leave the platform. - [List shared HTTP API configurations](https://docs.abundly.ai/api-reference/list-shared-http-api-configurations.md): Workspace-level Outbound API configurations, including each endpoint's URL pattern. Resolve an agent's `httpApis[].configId` against this list to see which external systems it can reach. Redaction covers the whole `secrets[]` block, so its string values all read `[redacted]`. - [Get capability settings](https://docs.abundly.ai/api-reference/get-capability-settings.md): Which capabilities are available in the workspace and their admin-configured defaults. - [Get security settings](https://docs.abundly.ai/api-reference/get-security-settings.md): Security alert configuration for the workspace. - [List agents](https://docs.abundly.ai/api-reference/list-agents.md): Every agent in the workspace, restricted and personal ones included (marked with `isPrivate`). `capabilities` is a mixed array of plain strings and `{ name, settings }` objects, so normalise to the name before counting. With `includeOverview=true` the response also carries `overview.reducedAgents` —… - [Per-agent usage for a period](https://docs.abundly.ai/api-reference/per-agent-usage-for-a-period.md): One row per agent, restricted and personal ones included (marked with `isPrivate`), with what it delivered (key metric counts, and the average or total for measured metrics), how much it was used (triggers & chats, with a daily series) and what it cost (credits), each alongside the same figure for t… - [List the workspace tag vocabulary](https://docs.abundly.ai/api-reference/list-the-workspace-tag-vocabulary.md): Every tag in use across agents, teams, and members, with usage counts per entity type. Check it before tagging via the write endpoints, so near-duplicate tags don't creep in. Untagged entities are not listed — use the list endpoints to enumerate entities. - [Get an agent's configuration](https://docs.abundly.ai/api-reference/get-an-agents-configuration.md): The agent's full configuration, including handle, scheduled triggers with their cron expressions, LLM preferences, and tool credentials as metadata with `isSet` flags rather than values. Returns 403 for a restricted or personal agent. - [List an agent's chats](https://docs.abundly.ai/api-reference/list-an-agents-chats.md): Chat conversations for the agent, without message bodies. - [Get a chat](https://docs.abundly.ai/api-reference/get-a-chat.md): A single conversation with its full message history. - [List an agent's documents](https://docs.abundly.ai/api-reference/list-an-agents-documents.md): Documents and folders belonging to the agent. Each entry inlines the document's complete `textContent`, which makes one call enough for an audit but produces large responses on document-heavy agents. Pass `excludeContent=true` for metadata only. - [Get a document](https://docs.abundly.ai/api-reference/get-a-document.md): A single document with its content. - [List diary entries](https://docs.abundly.ai/api-reference/list-diary-entries.md): The agent's diary. Filter to one day with `date`, to one conversation with `conversationId`, or pass `year` and `month` together for a month summary. - [Read the activity log](https://docs.abundly.ai/api-reference/read-the-activity-log.md): Trigger runs with their per-stage credit cost. Pass `entryId` for a single entry with its full `steps[]` trace — the most detailed audit surface in the API. Passing `page` or `pageSize` returns a paginated response that echoes both; without either you get the most recent entries capped by `limit`. - [List email and SMS messages](https://docs.abundly.ai/api-reference/list-email-and-sms-messages.md): External messages sent to or by the agent. `totalCount` reflects the active filter, so it changes as you narrow by direction, channel or date. - [List evals](https://docs.abundly.ai/api-reference/list-evals.md): Eval definitions and settings for the agent, optionally with the most recent results. - [List instruction versions](https://docs.abundly.ai/api-reference/list-instruction-versions.md): The agent's instruction history, newest first, with who made each change, when, and the length of each version's text; the first entry is the live instructions. Pass `since` for the version in effect at that time plus every later one — enough to diff what changed after a given date, such as a promot… - [List connected agents](https://docs.abundly.ai/api-reference/list-connected-agents.md): Outbound connections, inbound connections, and other agents available to connect to. - [List MCP servers](https://docs.abundly.ai/api-reference/list-mcp-servers.md): MCP servers connected to the agent. - [Get usage for one tool](https://docs.abundly.ai/api-reference/get-usage-for-one-tool.md): How often the agent called one specific tool, across chats and trigger runs, plus the most recent call inputs. `:toolName` is a tool name (lowercase with underscores, e.g. `send_email`), not a capability name — an unknown name returns 404 rather than a zero count. - [Get an agent's key metrics](https://docs.abundly.ai/api-reference/get-an-agents-key-metrics.md): The agent's key metrics — the outcomes its owner chose to count — with the count for the period, the average or total for measured metrics, the same figures for the period of equal length before, and optionally the most recent records. Definitions live on the agent (`keyMetrics` on GET /agents/:agen… - [List one agent's promotion requests](https://docs.abundly.ai/api-reference/list-one-agents-promotion-requests.md): The agent's promotion review history, newest first — the same records as /workspaceapi/promotion-requests, narrowed to this agent. This is the one per-agent endpoint that does not reject restricted and personal agents: the workspace-level list already returns their requests, so refusing here would o… - [Enable or pause agents](https://docs.abundly.ai/api-reference/enable-or-pause-agents.md): Enable or pause the listed agents. A paused agent cannot run and its scheduled triggers stop firing; its chats and configuration are kept. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Set agents' default model](https://docs.abundly.ai/api-reference/set-agents-default-model.md): Set the agents' default model, leaving per-chat and per-trigger overrides alone. With null, each agent gets the model a new agent would get: the workspace default, else the platform default. Models the workspace cannot currently select are rejected with 400. Batch write: each id gets its own result… - [Set agents' daily and monthly credit limits](https://docs.abundly.ai/api-reference/set-agents-daily-and-monthly-credit-limits.md): Set (or clear, with null) the daily and/or monthly credit limit on the listed agents; an omitted limit is left unchanged. An agent that hits its daily limit stops running until the next day, and one that hits its monthly limit until the next month. Only admins can change the monthly limit, and reset… - [Set agents' credit limits (deprecated path)](https://docs.abundly.ai/api-reference/set-agents-credit-limits-deprecated-path.md): Deprecated: use `POST /agents/credit-limits` instead, which takes the same request, including `monthlyCreditLimit`. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Set agents' criticality rating](https://docs.abundly.ai/api-reference/set-agents-criticality-rating.md): Set (or clear, with null) the agents' criticality rating — how much it would hurt to lose the agent. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Show or hide per-message credit details](https://docs.abundly.ai/api-reference/show-or-hide-per-message-credit-details.md): Show or hide the per-message credit details in the listed agents' chats. Display only — it does not change what an agent may spend. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Tag agents](https://docs.abundly.ai/api-reference/tag-agents.md): Add, remove, or replace tags on the listed agents. Use /workspaceapi/agents to find agent ids and current tags, and /workspaceapi/tags for the existing tag vocabulary. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Move agents to a team](https://docs.abundly.ai/api-reference/move-agents-to-a-team.md): Move the listed agents to another team, or to the workspace-global space with targetTeamId=null. Moving an agent changes who can reach it and can flip team-scoped capabilities on or off, so call with dryRun=true first: each result carries an `impact` naming the members who gain or lose access and th… - [Promote or demote agents between lifecycle phases](https://docs.abundly.ai/api-reference/promote-or-demote-agents-between-lifecycle-phases.md): Set the listed agents' lifecycle phase: `production` to promote, `sandbox` to demote. Production unlocks the capabilities, secrets and outbound APIs marked production-only plus the reserved credits; demotion pauses that access but keeps the agent's configuration. Agents already in the requested phas… - [Tag teams](https://docs.abundly.ai/api-reference/tag-teams.md): Add, remove, or replace tags on the listed teams. Use /workspaceapi/teams to find team ids and current tags. Returns 400 when team settings are not enabled for the workspace. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Tag workspace members](https://docs.abundly.ai/api-reference/tag-workspace-members.md): Add, remove, or replace tags on the listed workspace members (ids are user ids). Use /workspaceapi/members to find user ids and current tags. Batch write: each id gets its own result and per-id failures still return HTTP 200 — check `results[].success` and `summary`. - [Set a team's monthly credit limit](https://docs.abundly.ai/api-reference/set-a-teams-monthly-credit-limit.md): Set, or remove with null, the credits all of the team's agents may use together per calendar month. When the limit is reached, every agent in the team pauses until it is raised or the month rolls over; it applies on top of each agent's own limits. Read the current limit and this month's usage from `… - [Add a team member or set their role](https://docs.abundly.ai/api-reference/add-a-team-member-or-set-their-role.md): Add a workspace member to the team with the given role, or change the role of someone already in it. Idempotent: repeating the call changes nothing and answers 200. Returns 404 when the user is not a member of the workspace. Returns 400 when team settings are not enabled for the workspace. - [Remove a team member](https://docs.abundly.ai/api-reference/remove-a-team-member.md): Remove the user from the team. Returns 404 when the user is not in the team, so a retried removal reads as already done. Returns 400 when team settings are not enabled for the workspace. - [Revoke an invitation](https://docs.abundly.ai/api-reference/revoke-an-invitation.md): Revoke an invitation so it can no longer be accepted, as a workspace admin can from the Members page; to change an invitation, revoke it and send a new one. Requires the Invite members scope. Returns 404 for an unknown invitation or one from another workspace. - [Integrations Overview](https://docs.abundly.ai/integrations/overview.md): Give your agent access to external services and data - [MCP Servers](https://docs.abundly.ai/integrations/mcp.md): Connect external tools via the Model Context Protocol - [Integration pricing](https://docs.abundly.ai/integrations/pricing.md): How integrations are billed - [Anthropic](https://docs.abundly.ai/integrations/anthropic.md): Claude family of language models - [Atlassian](https://docs.abundly.ai/integrations/atlassian.md): Work with Jira, Confluence, and other Atlassian products - [Autodesk](https://docs.abundly.ai/integrations/autodesk.md): Upload, convert, and view CAD files — and browse ACC projects — from your agent - [BigQuery](https://docs.abundly.ai/integrations/bigquery.md): Ask questions about your data in plain English and get answers from Google BigQuery - [Cloud Storage](https://docs.abundly.ai/integrations/cloud-storage.md): Read and write files in S3-compatible object storage — AWS S3, Cloudflare R2, Google Cloud Storage, and more - [ElevenLabs](https://docs.abundly.ai/integrations/elevenlabs.md): Speech to text transcription and text to speech with natural-sounding voices - [Figma](https://docs.abundly.ai/integrations/figma.md): Read Figma files, render frames as images, browse projects, and post comments - [Firecrawl](https://docs.abundly.ai/integrations/firecrawl.md): Extract content from web pages - [Giphy](https://docs.abundly.ai/integrations/giphy.md): Search and share GIFs - [GitHub](https://docs.abundly.ai/integrations/github.md): Manage repositories, pull requests, and issues - [Google Calendar](https://docs.abundly.ai/integrations/google-calendar.md): View events, create meetings, and manage schedules - [Google Chat](https://docs.abundly.ai/integrations/google-chat.md): Connect your agent to Google Chat as its own named app, in a simple or advanced mode - [Google Drive](https://docs.abundly.ai/integrations/google-drive.md): Access files, create documents, and work with spreadsheets - [Google Gemini](https://docs.abundly.ai/integrations/google-gemini.md): Gemini family of language models and image generation - [HubSpot](https://docs.abundly.ai/integrations/hubspot.md): Manage contacts, companies, deals, and more - [Meta Ads](https://docs.abundly.ai/integrations/meta-ads.md): Read campaign, ad set, and ad performance data from Facebook and Instagram ads - [Microsoft 365 Assistant](https://docs.abundly.ai/integrations/microsoft-365.md): One personal connection for Outlook mail, calendar, OneDrive, SharePoint, Teams chats and Planner tasks - [Microsoft Outlook](https://docs.abundly.ai/integrations/outlook.md): Email management for Microsoft 365 - [Microsoft Outlook Calendar](https://docs.abundly.ai/integrations/outlook-calendar.md): View events, create meetings, and manage Outlook calendars - [Microsoft SharePoint](https://docs.abundly.ai/integrations/sharepoint.md): Access documents and work with team sites - [Microsoft Teams](https://docs.abundly.ai/integrations/msteams.md): Connect your agent to Microsoft Teams so it appears as its own named bot - [Microsoft Admin](https://docs.abundly.ai/integrations/microsoft-admin.md): Let an agent do Microsoft 365 and Entra administration for you — granting SharePoint access, registering Entra apps, setting up Teams bots — with a temporary token that lasts an hour and is never renewed - [MongoDB](https://docs.abundly.ai/integrations/mongodb.md): Let your agent read and write your MongoDB data using your own database connection - [NetSuite](https://docs.abundly.ai/integrations/netsuite.md): Manage customers, vendors, invoices, purchase orders, and more in NetSuite ERP - [Notion](https://docs.abundly.ai/integrations/notion.md): Read and write pages, manage databases, and search content - [OpenAI](https://docs.abundly.ai/integrations/openai.md): GPT models, image generation, voice, and vision capabilities - [Perplexity](https://docs.abundly.ai/integrations/perplexity.md): AI-powered web search and deep research - [Salesforce](https://docs.abundly.ai/integrations/salesforce.md): Manage contacts, accounts, opportunities, leads, and more - [Slack](https://docs.abundly.ai/integrations/slack.md): Chat with your agent in Slack, or drive it from Slack events - [Snowflake](https://docs.abundly.ai/integrations/snowflake.md): Turn your Snowflake data into answers — query and explore your warehouse in plain English - [Steep](https://docs.abundly.ai/integrations/steep.md): Query your Steep metrics in plain English — same definitions your team already uses - [Telnyx](https://docs.abundly.ai/integrations/telnyx.md): SMS and phone call infrastructure - [Trello](https://docs.abundly.ai/integrations/trello.md): Manage boards, lists, and cards - [Twitter / X](https://docs.abundly.ai/integrations/twitter.md): Search, analyze, and post on social media - [WhatsApp](https://docs.abundly.ai/integrations/whatsapp.md): Connect your agent to WhatsApp so it can send and receive messages - [Find Your Use Case](https://docs.abundly.ai/guides/find-use-case.md): Identify which tasks are best suited for AI agents - [Agent Design](https://docs.abundly.ai/guides/agent-design.md): A structured approach to designing AI agents that actually work - [Agent Optimization](https://docs.abundly.ai/guides/agent-optimization.md): Reduce costs and improve agent performance - [Troubleshooting](https://docs.abundly.ai/guides/troubleshooting.md): Solutions for common issues - [Use Cases](https://docs.abundly.ai/use-cases/index.md): Examples of AI agents in action across different business functions - [Security Overview](https://docs.abundly.ai/security/overview.md): Multi-layer security architecture for enterprise AI agents - [Risk & Autonomy](https://docs.abundly.ai/security/risk-autonomy.md): Understanding and managing risk based on your agent's role - [Attack Detection](https://docs.abundly.ai/security/attack-detection.md): Automated screening of untrusted trigger content before agent execution - [Guardrails](https://docs.abundly.ai/security/guardrails.md): Technical constraints enforced by code, not LLM reasoning - [User Approval](https://docs.abundly.ai/security/user-approval.md): Require human approval before agents execute sensitive actions - [Access Control](https://docs.abundly.ai/security/access-control.md): Role-based permissions for users and agents - [Personal and Restricted Agents](https://docs.abundly.ai/security/personal-and-restricted-agents.md): What workspace admins can see and do about agents they can't open - [Credentials](https://docs.abundly.ai/security/credentials.md): Secure storage of secrets and API keys - [Workload identity](https://docs.abundly.ai/security/workload-identity.md): Give agents keyless access to your Google Cloud, Microsoft Entra and your own APIs - [Infrastructure & Compliance](https://docs.abundly.ai/security/infrastructure.md): Data residency, encryption, audit trails, and regulatory compliance - [Agent web requests](https://docs.abundly.ai/security/web-requests.md): How to recognize requests that Abundly agents make to websites and APIs - [Subprocessors](https://docs.abundly.ai/security/subprocessors.md): Third parties that may process customer data when using Abundly agents and integrations. - [Platform summary](https://docs.abundly.ai/summary/index.md): A comprehensive single-page summary of all Abundly documentation — ideal for LLM context - [Changelog](https://docs.abundly.ai/changelog/index.md): New features, improvements, and fixes in Abundly ## OpenAPI Specs - [workspace-api](/api-reference/workspace-api.json) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.