# Agentheya

## Docs

- [Agent-to-Agent (A2A)](https://agentheya.mintlify.app/a2a.md): Connect external AI agents to your AgentHeya agent using the Google A2A protocol.
- [Agent Dashboard](https://agentheya.mintlify.app/agent-dashboard.md): Feed the Agent Dashboard live values from built-in tools, sandboxed code, HTTPS APIs, per-agent JSON/XML data files your agent maintains, and read-only SQL databases.
- [Designer Chat](https://agentheya.mintlify.app/ai-helper.md): The Designer Chat configures your agent through conversation. Describe what you want and it handles the setup.
- [calculate](https://agentheya.mintlify.app/builtin-tools/calculate.md): Deterministic arithmetic, percentages, and unit conversions.
- [collect_form](https://agentheya.mintlify.app/builtin-tools/collect_form.md): Render a structured form in the chat and collect multiple fields at once.
- [commit_action](https://agentheya.mintlify.app/builtin-tools/commit_action.md): Gatekeeper — verifies the user actually approved a destructive action.
- [confirm_action](https://agentheya.mintlify.app/builtin-tools/confirm_action.md): Ask the user to approve a destructive action. Paired with commit_action.
- [send_email](https://agentheya.mintlify.app/builtin-tools/email_send.md): Send email.
- [check_email_status](https://agentheya.mintlify.app/builtin-tools/email_status.md): Look up the delivery status of an email sent earlier with send_email — timeline of events plus advice on what to do next.
- [handoff_release](https://agentheya.mintlify.app/builtin-tools/handoff_release.md): Return control of a received handoff back to the originating agent's visitor.
- [handoff_request](https://agentheya.mintlify.app/builtin-tools/handoff_request.md): Escalate the conversation to a human or sibling agent via a configured channel.
- [Built-in tools](https://agentheya.mintlify.app/builtin-tools/index.md): Capabilities Agentheya ships with — searchable from the agent loop and callable from your own custom code tools via the injected ctx.
- [present_public_file](https://agentheya.mintlify.app/builtin-tools/present_public_file.md): Present a public file as a download card in the chat.
- [render_ui](https://agentheya.mintlify.app/builtin-tools/render_ui.md): Emit a Generative UI component spec — cards, tables, stats, forms, and interactive elements — directly in the chat.
- [show_file_excerpt](https://agentheya.mintlify.app/builtin-tools/show_file_excerpt.md): Show the content of a public text file inline in the chat.
- [show_image](https://agentheya.mintlify.app/builtin-tools/show_image.md): Render a public image inline in the chat bubble.
- [surface_file](https://agentheya.mintlify.app/builtin-tools/surface_file.md): Save generated content and return a time-limited download URL.
- [web_fetch](https://agentheya.mintlify.app/builtin-tools/web_fetch.md): Fetch the content of a URL and return it as clean markdown.
- [web_search](https://agentheya.mintlify.app/builtin-tools/web_search.md): Search the web and return a list of results with title, URL, and snippet.
- [Configuring your agent](https://agentheya.mintlify.app/configuration.md): A guide to each configuration section in the agent editor.
- [Custom Dashboard Pages](https://agentheya.mintlify.app/custom-pages.md): Build extra dashboard pages with json-render — and wire them to live data, values your agent pushes, a private per-buyer scratchpad, and settings the agent reads.
- [Custom tool ctx](https://agentheya.mintlify.app/custom-tools-ctx.md): How sandboxed custom code tools call built-in tools via the injected ctx object.
- [Generative UI](https://agentheya.mintlify.app/generative-ui.md): Let your agent render cards, tables, metrics, alerts, and interactive forms directly in the chat — and collect structured input back from the user.
- [What is Agentheya?](https://agentheya.mintlify.app/introduction.md): Agentheya lets you create custom AI agents and share them with your users -- no coding required.
- [Management MCP](https://agentheya.mintlify.app/manage-mcp.md): Programmatically create, configure, and manage Agentheya agents using the Management MCP server.
- [Agent-to-agent patterns](https://agentheya.mintlify.app/peer-patterns.md): Three ways your agent can work with peer agents — delegate-as-call, bridge / relay, and transfer / drop-out. When each applies and how to configure it.
- [Preview](https://agentheya.mintlify.app/preview.md): Test your agent in the dashboard before sharing it with anyone.
- [Quickstart](https://agentheya.mintlify.app/quickstart.md): Create and share your first AI agent in under 10 minutes.
- [a2a_card](https://agentheya.mintlify.app/reference/a2a_card.md): The discovery card other agents see when this agent is exposed over the A2A protocol — its description, example prompts, tags, and documentation URL.…
- [builtin_tools](https://agentheya.mintlify.app/reference/builtin_tools.md): Switches and configuration for the platform built-in tools — disable specific ones, control outbound-message recipients, and pick the web-search engine.
- [connectors](https://agentheya.mintlify.app/reference/connectors.md): External MCP servers and OpenAPI integrations the agent can call (Notion, Stripe, Bitly, Google, …). Each connector contributes tools at chat time.
- [data_internal](https://agentheya.mintlify.app/reference/data_internal.md): Private knowledge the agent retrieves from but never exposes verbatim: uploaded files, indexed URLs, and optional external vector stores.
- [data_public](https://agentheya.mintlify.app/reference/data_public.md): Knowledge sources the agent may quote and surface to power-users — public files and URLs.
- [details](https://agentheya.mintlify.app/reference/details.md): The agent's core identity: its display name, a one-line description, and who can reach it. This is the lightweight identity record; the public-facing…
- [examples](https://agentheya.mintlify.app/reference/examples.md): Worked input→output examples that teach the agent your preferred style and reasoning. Few-shot guidance that ships in the system prompt.
- [feed_monitors](https://agentheya.mintlify.app/reference/feed_monitors.md): Recurring RSS and X (Twitter) watchers. Each monitor polls a source and can react to new items (off / all / classified), optionally delivering results to…
- [handoff_settings](https://agentheya.mintlify.app/reference/handoff_settings.md): Auto-escalation rules that hand a conversation to a human channel based on keywords or consecutive unresolved turns.
- [hooks](https://agentheya.mintlify.app/reference/hooks.md): Lifecycle webhooks fired at key moments (pre/post query, on tool call, on handoff). A Business-tier capability; for an all-plan equivalent use a callback…
- [im_channels](https://agentheya.mintlify.app/reference/im_channels.md): Inbound/outbound instant-messaging channels (Telegram, WhatsApp, Discord, …) the agent is connected to.
- [knowledge_graph](https://agentheya.mintlify.app/reference/knowledge_graph.md): Files used to build a structured knowledge graph for the agent.
- [langfuse](https://agentheya.mintlify.app/reference/langfuse.md): Per-agent tracing to our self-hosted Langfuse. Auto-provisioned: each agent gets its own Langfuse organization and project, so one agent's traces are…
- [memory_schema](https://agentheya.mintlify.app/reference/memory_schema.md): Defines the per-power-user memory the agent maintains: publicFields (a power-user-visible profile) and privateFields (the agent's working notes). Shapes…
- [monitoring](https://agentheya.mintlify.app/reference/monitoring.md): Quality criteria and alert rules used to score and watch the agent's behaviour over time.
- [Schema reference](https://agentheya.mintlify.app/reference/overview.md): Field-by-field reference for every agent configuration section, organised exactly like the canonical system schema, each linked to its dashboard page.
- [plugins](https://agentheya.mintlify.app/reference/plugins.md): Installed plugin bundles that package skills, commands, sub-agents, hooks, and MCP servers together. Largely managed by the install flow — most fields are…
- [policy_acceptable_use](https://agentheya.mintlify.app/reference/policy_acceptable_use.md): The agent's Acceptable Use Policy legal document. Auto-seeded on creation and editable on the Details page.
- [policy_privacy](https://agentheya.mintlify.app/reference/policy_privacy.md): The agent's Privacy Policy legal document. Auto-seeded on creation and editable on the Details page.
- [policy_refund](https://agentheya.mintlify.app/reference/policy_refund.md): The agent's Refund Policy legal document. Auto-seeded on creation and editable on the Details page.
- [policy_tos](https://agentheya.mintlify.app/reference/policy_tos.md): The agent's Terms of Service legal document. Auto-seeded from a template on agent creation and editable on the Details page.
- [pricing](https://agentheya.mintlify.app/reference/pricing.md): Per-agent power-user pricing tiers (what your power-users pay to use the agent), the Stripe currency, and free-evaluation settings.
- [public_details](https://agentheya.mintlify.app/reference/public_details.md): Everything shown on your agent's standalone public chat page — business name, support email, power-user instructions, theme, brand palette, and the page…
- [purpose](https://agentheya.mintlify.app/reference/purpose.md): The heart of the agent: what it does (overview), how it should behave (behaviour, used as the system prompt), output preferences, an optional structured…
- [rules](https://agentheya.mintlify.app/reference/rules.md): An ordered list of guardrails and behavioural constraints injected into the system prompt. Each rule has an enforcement level; a rule can also be a…
- [skills](https://agentheya.mintlify.app/reference/skills.md): Reusable instruction packs (with optional scripts, references, and assets) the agent can invoke for specialised procedures.
- [tool_guards](https://agentheya.mintlify.app/reference/tool_guards.md): Per-tool parameter guards: validation rules that reject a tool call and transforms that silently fix it, applied before every tool runs.
- [tools](https://agentheya.mintlify.app/reference/tools.md): Owner-defined tools the agent can call: api_endpoint (HTTP), code (sandboxed JS/Python), and derived (a preset wrapper over a built-in). Tools can return…
- [weaviate](https://agentheya.mintlify.app/reference/weaviate.md): Standalone connection details for an external Weaviate vector store.
- [widget](https://agentheya.mintlify.app/reference/widget.md): The embeddable chat widget design and behaviour — mode, branding, colours, launcher, sizing, pre-chat fields, conversation starters, and gating. Separate…
- [Durability and recovery](https://agentheya.mintlify.app/runtime/durability.md): What survives a restart or platform update — conversations, schedules, queued work, and pending approvals — and what happens to a reply that's mid-stream when an update lands.
- [Evaluation and quality](https://agentheya.mintlify.app/runtime/evaluation.md): How you measure and enforce quality — a judge that scores and regenerates answers, goal verification, runtime checks and alerts, test scenarios, and A/B model comparison.
- [Memory and context management](https://agentheya.mintlify.app/runtime/memory-and-context.md): What your agent remembers and works from each turn — conversation history, long-term memory per user, knowledge retrieval, and automatic handling of very long conversations.
- [Multi-agent orchestration](https://agentheya.mintlify.app/runtime/multi-agent.md): How your agent works with other agents and with humans — three peer patterns, an A2A endpoint, delegation, and human handoff.
- [Observability and debugging](https://agentheya.mintlify.app/runtime/observability.md): What's recorded for every turn — a cost row you can scan, a health snapshot you can watch, a full record you can open, and hard-failure capture — and how to debug one conversation.
- [Agent Harness](https://agentheya.mintlify.app/runtime/overview.md): What your agent does at runtime — how a turn behaves, the limits you can set, and the reliability, memory, orchestration, observability, safety, and evaluation features you get on every channel.
- [Safety and isolation](https://agentheya.mintlify.app/runtime/safety.md): The safety you get under every agent — the policy controls you own, sandboxed code, spend limits, platform protections, and isolation between agents, subscribers, and accounts.
- [State and sessions](https://agentheya.mintlify.app/runtime/state-and-sessions.md): How your agent stays stateful — separate conversations per channel, per-user workflow progress, and configuration history you can roll back.
- [Tool execution and reliability](https://agentheya.mintlify.app/runtime/tool-execution.md): The reliability you can count on for every tool call — what runs before a tool fires, protection against duplicate actions, time limits, retries, and the approval gates in front of destructive actions.
- [How a turn executes](https://agentheya.mintlify.app/runtime/turn-execution.md): What happens when your agent replies — how answers are delivered per channel, the limits you can set on time, tool use, tokens, and spend, and the model and effort controls you configure.
- [External vector stores](https://agentheya.mintlify.app/sections/data/external-stores.md): Connect your existing Pinecone or Weaviate cluster as a private RAG source — the agent queries it at chat time alongside built-in retrieval.
- [Pinecone (external store)](https://agentheya.mintlify.app/sections/data/external-stores/pinecone.md): Connect your existing Pinecone index — REST-based, works for serverless and pod-based indexes alike.
- [Weaviate (external store)](https://agentheya.mintlify.app/sections/data/external-stores/weaviate.md): Connect your Weaviate cluster — GraphQL queries, nearText or nearVector mode.
- [Page layout](https://agentheya.mintlify.app/sections/page-layout.md): Owner-defined UI blocks rendered around your agent's standalone chat page — pre-chat forms, hero banners, FAQ accordions, suggested-prompt chips, embedded widgets, and more.
- [divider block](https://agentheya.mintlify.app/sections/page-layout/divider.md): A simple horizontal rule between blocks.
- [embed block](https://agentheya.mintlify.app/sections/page-layout/embed.md): A sandboxed iframe — embed a third-party widget (Calendly, Typeform, status page, …) next to the chat.
- [faq block](https://agentheya.mintlify.app/sections/page-layout/faq.md): A collapsible Q&A accordion — deflects repetitive support questions without consuming a chat turn.
- [hero block](https://agentheya.mintlify.app/sections/page-layout/hero.md): Banner card with optional logo, headline, subtitle, and CTA — for first-impression brand framing.
- [input_capture block](https://agentheya.mintlify.app/sections/page-layout/input-capture.md): A pre-chat intake form whose submission either auto-sends as the first chat message or pre-fills the chat input box.
- [json_render block](https://agentheya.mintlify.app/sections/page-layout/json-render.md): Author custom UI as a static RenderSpec JSON object — the same format the agent emits at runtime.
- [links block](https://agentheya.mintlify.app/sections/page-layout/links.md): A flat list of outbound links, rendered as a row of pill links.
- [markdown block](https://agentheya.mintlify.app/sections/page-layout/markdown.md): A free-text markdown block rendered above, below, or beside the chat panel.
- [notice block](https://agentheya.mintlify.app/sections/page-layout/notice.md): A coloured info / success / warning / error banner with optional title, markdown body, and dismiss button.
- [suggested_prompts block](https://agentheya.mintlify.app/sections/page-layout/suggested-prompts.md): Clickable starter chips that seed the chat with a preset message when tapped.
- [Activity](https://agentheya.mintlify.app/sidebar-menu/activity.md): View recent queries handled by your agent.
- [API keys](https://agentheya.mintlify.app/sidebar-menu/api-keys.md): Generate and manage keys that authenticate your agent's programmatic interfaces.
- [Connectors](https://agentheya.mintlify.app/sidebar-menu/connectors.md): Connect your agent to external services and APIs via MCP servers, OpenAPI specs, and GraphQL endpoints.
- [Contacts](https://agentheya.mintlify.app/sidebar-menu/contacts.md): The per-touch contact registry — everyone who has ever reached your agent, across every channel, with whatever we could capture about them.
- [CRM Sync](https://agentheya.mintlify.app/sidebar-menu/crm-sync.md): Push new users into HubSpot, Salesforce, Pipedrive or Zoho as contacts, and log every conversation as an activity.
- [Internal Data](https://agentheya.mintlify.app/sidebar-menu/data-internal.md): Upload private files that your agent uses for retrieval-augmented generation.
- [Public Data](https://agentheya.mintlify.app/sidebar-menu/data-public.md): Upload redistributable files that your agent can share directly with users.
- [Agent Details](https://agentheya.mintlify.app/sidebar-menu/details.md): Configure your agent's public identity — name, description, instructions, visibility, legal policies, A2A discovery card, and the danger zone.
- [Email addresses](https://agentheya.mintlify.app/sidebar-menu/email-addresses.md): Give your agent its own inbound email address — emails arrive as conversations.
- [Sent](https://agentheya.mintlify.app/sidebar-menu/emails.md): Everything your agent has sent out — email replies and outbound messaging — in one timeline.
- [Interpreters](https://agentheya.mintlify.app/sidebar-menu/event-interpreters.md): Tell the agent what an incoming event is before it reads the body — a shared matching mechanism across email, messaging, webhooks, feeds, and connector events.
- [Event pre-processor](https://agentheya.mintlify.app/sidebar-menu/event-pre-processor.md): Run your own code in a sandbox before the agent (and before any LLM classifier) sees an incoming event, and decide what happens next.
- [Events](https://agentheya.mintlify.app/sidebar-menu/events.md): Run JavaScript or Python whenever a selected agent event fires.
- [Examples](https://agentheya.mintlify.app/sidebar-menu/examples.md): Provide sample situations and the responses you want, with optional reasoning. They act as few-shot training data for the agent.
- [Feeds](https://agentheya.mintlify.app/sidebar-menu/feeds.md): Watch RSS feeds and X/Twitter accounts, and have your agent react to new items automatically.
- [Goals & Goal Checks](https://agentheya.mintlify.app/sidebar-menu/goals.md): Track whether your agent's goals are actually met — with automatic per-turn evaluation and owner-written verification code that gates goal completion.
- [Hooks](https://agentheya.mintlify.app/sidebar-menu/hooks.md): Fire HTTP requests when conversation events occur — and fully control what happens next.
- [Human Handoff](https://agentheya.mintlify.app/sidebar-menu/human-handoff.md): Configure channels, routing, manual triggers, and delegates for escalating conversations to humans or peer agents.
- [IM Channels](https://agentheya.mintlify.app/sidebar-menu/im-channels.md): Connect your agent to messaging platforms — Telegram, WhatsApp, Discord, Slack, Facebook Messenger, Instagram, LINE, Viber.
- [Inbox](https://agentheya.mintlify.app/sidebar-menu/inbox.md): Cross-channel conversation viewer — read, take over, or release any conversation your agent is having.
- [Knowledge](https://agentheya.mintlify.app/sidebar-menu/knowledge.md): Control how your agent extracts, retrieves, and presents knowledge from the files and graphs you upload.
- [Memory](https://agentheya.mintlify.app/sidebar-menu/memory.md): Configure what your agent remembers about each subscriber — the schema, the engine that auto-extracts and compacts memories, AI schema generation, trust and contradiction resolution, and the controls subscribers have over their own memory.
- [Monitoring](https://agentheya.mintlify.app/sidebar-menu/monitoring.md): Live health snapshot for the published agent, plus optional Langfuse trace export.
- [Using Your Agent](https://agentheya.mintlify.app/sidebar-menu/overview.md): Four ways to put your Agentheya agent to work — chat link, REST API, MCP server, and scheduled runs.
- [Plugins](https://agentheya.mintlify.app/sidebar-menu/plugins.md): Bundle skills, commands, sub-agents, hooks, and MCP servers into reusable plugin packages.
- [Pricing](https://agentheya.mintlify.app/sidebar-menu/pricing.md): Set up subscription tiers to monetise your agent and manage Stripe Connect for payments.
- [Purpose](https://agentheya.mintlify.app/sidebar-menu/purpose.md): Define who your agent is, how it should behave, and when it has succeeded.
- [Retrieval Test](https://agentheya.mintlify.app/sidebar-menu/retrieval-test.md): See exactly what your agent would retrieve for a question — and what it costs — before spending a chat turn.
- [Rules](https://agentheya.mintlify.app/sidebar-menu/rules.md): Define constraints the agent must follow, with per-rule enforcement levels.
- [Schedules](https://agentheya.mintlify.app/sidebar-menu/schedules.md): Run your agent automatically on a timer — daily digests, weekly reports, one-off tasks, or any cron schedule.
- [Team & Roles](https://agentheya.mintlify.app/sidebar-menu/team.md): Give other people scoped access to an agent's dashboard — invite collaborators and control exactly which pages each one can view or edit with built-in or custom roles.
- [Tools](https://agentheya.mintlify.app/sidebar-menu/tools.md): Define callable tools your agent can invoke — API endpoints, code functions, or built-in operations.
- [Subscribers](https://agentheya.mintlify.app/sidebar-menu/users.md): Manage subscribers who use and build on your agent.
- [Web Page](https://agentheya.mintlify.app/sidebar-menu/web.md): Configure your agent's web chat page — layout blocks, free-floating page images, appearance (background, theme, typography), SEO, greeting, opening hours, custom dashboard pages, and response presentation.
- [Webhook Triggers](https://agentheya.mintlify.app/sidebar-menu/webhooks.md): Receive HTTP requests from any external service and have your agent process them automatically.
- [Chat widget](https://agentheya.mintlify.app/sidebar-menu/widgets.md): Embed your agent on any website — one script tag, no build step.
- [Tool parameters](https://agentheya.mintlify.app/tool-parameters.md): How the parameters you define on a tool reach the underlying Code function or HTTP endpoint.
- [User Memory](https://agentheya.mintlify.app/user-memory.md): How per-user memory works — the two memory stores, how each user gets their own memory, how the agent reads and writes it, and every control for managing it.