# Agent Builder Tool ## Links - Product page URL: https://www.agentpmt.com/marketplace/agent-builder-tool - Product markdown URL: https://www.agentpmt.com/marketplace/agent-builder-tool?format=agent-md - Product JSON URL: https://www.agentpmt.com/marketplace/agent-builder-tool?format=agent-json ## Overview - Product ID: 69ed32a83ccc082ef9976212 - Type: model - Unit type: request - Price: Price unavailable - Categories: Developer Tools, AI & Machine Learning, Task Planning & Orchestration, Automation, Team Collaboration & Workspaces, Task & Workflow Automation, Agent Memory and Context - Generated at: 2026-08-01T17:24:44.187Z ### Page Description Build your own AI agent in a conversation. Describe the job you want done and this AI agent builder creates the agent, gives it the tools and workflows it needs, writes its operating instructions, and puts it live under its own name and link. Start from a blank agent or branch off one that already works, then keep shaping it in plain language: connect a CRM, an inbox, a calendar, a phone line, research and data tools, or an entire multi step workflow, and attach your own context documents so it answers with your pricing, your policies, and your voice instead of generic advice. Preview the agent in a live chat, publish it when it is ready, hand it to your team, and spin up new agents for other roles while the original keeps running untouched. No code, no framework, and no prompt engineering background required. If you can explain the job to a new hire, you can build the AI agent that does it. ### Agent Description Create, configure, publish, and manage custom AI agents end to end. create_new drafts a private agent, optionally as a remix of any agent you can view. update_existing edits name, description, status, model selection, and system prompt. fetch_existing lists your agents or fetches one by id or slug; search_public browses published public agents. publish moves a draft to active and finalizes its public slug; archive soft deletes with an optional redirect path. add_product and remove_product attach or detach tools; add_workflow and remove_workflow attach or detach multi step workflows; attach_context and detach_context manage up to 10 Agent Context documents (private context documents are rejected on public active agents). add_showcase_example and remove_showcase_example manage chat previews, with one featured example at a time. File Manager is attached to the agent automatically whenever an attached tool or workflow needs file storage. ## Details ### Details Build your own AI agent in a conversation. Describe the job you want done and this AI agent builder creates the agent, gives it the tools and workflows it needs, writes its operating instructions, and puts it live under its own name and link. Start from a blank agent or branch off one that already works, then keep shaping it in plain language: connect a CRM, an inbox, a calendar, a phone line, research and data tools, or an entire multi step workflow, and attach your own context documents so it answers with your pricing, your policies, and your voice instead of generic advice. Preview the agent in a live chat, publish it when it is ready, hand it to your team, and spin up new agents for other roles while the original keeps running untouched. No code, no framework, and no prompt engineering background required. If you can explain the job to a new hire, you can build the AI agent that does it. ### Actions - `create_new`: Create a private draft agent. - `update_existing`: Update editable fields on an agent you own. is_template is admin-only. - `fetch_existing`: List your agents (recently updated first), or fetch one by id/slug. - `search_public`: Search active public agents. - `publish`: Transition DRAFT to ACTIVE; stamps published_at the first time. - `archive`: Soft-delete the agent. If forward_to is supplied, issue 301 redirects from the agent's canonical paths to that internal destination. - `remix`: Create a private copy of a viewable agent. - `add_product`: Attach a product to the agent. Routes through file manager auto-attach. - `remove_product`: Detach a product from the agent. Routes through file manager auto-attach. - `add_workflow`: Attach a workflow to the agent. Routes through file manager auto-attach. - `remove_workflow`: Detach a workflow from the agent. Routes through file manager auto-attach. - `attach_context`: Attach an Agent Context document to the agent. - `detach_context`: Detach an Agent Context document from the agent. - `add_showcase_example`: Add a chat preview example to the agent. - `remove_showcase_example`: Remove a showcase example by id. ### Use Cases Build a custom AI agent without writing code, Turn a job description into a working AI agent, Equip an agent with CRM inbox calendar and messaging tools, Attach multi step workflows to an agent, Ground an agent in your own policies pricing and brand voice, Publish an AI agent and share it with your team, Remix an existing agent into a specialized version, Add showcase chat previews to an agent listing, Manage the agent lifecycle from draft to published to archived, Prototype and tune agent instructions in a live chat ### Workflows Using This Tool No public workflows currently reference this product. ### Related Content No related content is currently linked to this product. ## Documentation No platform documentation is currently linked to this product. ## Integration Details ### DynamicMCP - Setup page URL: https://www.agentpmt.com/dynamic-mcp - Claude setup guide: https://www.agentpmt.com/dynamic-mcp#platform=claude - ChatGPT setup guide: https://www.agentpmt.com/dynamic-mcp#platform=chatgpt - Cursor setup guide: https://www.agentpmt.com/dynamic-mcp#platform=cursor - Windsurf setup guide: https://www.agentpmt.com/dynamic-mcp#platform=windsurf Use the local router for command-based MCP clients. It forwards requests to `https://api.agentpmt.com/mcp` and does not execute tools locally. ```bash npm install -g @agentpmt/mcp-router agentpmt-setup ``` ### REST API The live page renders cURL, Python, JavaScript, and Node.js examples. Logged-in users see those examples prefilled with their own API and budget credentials. - Purchase endpoint: https://api.agentpmt.com/products/purchase - Authorization format: `Bearer ` ```bash curl -X POST "https://api.agentpmt.com/products/purchase" \ -H "Content-Type: application/json" \ -H "Authorization: Bearer eW91ci1hcGkta2V5LWhlcmU6eW91ci1idWRnZXQta2V5LWhlcmU=" \ -d '{ "product_id": "69ed32a83ccc082ef9976212", "parameters": { "action": "create_new" } }' ``` ### Autonomous Agents Autonomous agents can access this tool through AgentAddress credit balances or direct x402 payments. Use the Autonomous Agent API reference for endpoint shapes after choosing the access pattern below. - Autonomous Agent API reference URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents - Autonomous Agent API reference markdown URL: https://www.agentpmt.com/docs/api-reference/autonomous-agents?format=agent-md - Credit-Based Access Using AgentAddress: https://www.agentpmt.com/docs/autonomous-agents/credit-based-tool-usage-with-agentaddress - AgentAddress is preferred for persistent file access, stored platform state, and maximum tool use ability across repeated calls. - Direct x402 is for independent one-off tool calls that do not require shared files or stored platform state. - Direct x402 public payments: USDC on Base, Arbitrum, Optimism, Polygon, and Avalanche. #### Product Skill Package This product has a published Agent Skill package for product-specific operating instructions. - Skill slug: agent-builder-tool - Version: 1.0.0 - Download SKILL.md: https://raw.githubusercontent.com/AgentPMT/agent-skills/main/skills/agent-builder-tool/SKILL.md - Package source: https://github.com/AgentPMT/agent-skills/tree/main/skills/agent-builder-tool - OpenClaw listing: https://clawhub.ai/agentpmt/agent-builder-tool - OpenClaw install: `openclaw skills install agent-builder-tool` - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agent-builder-tool` - Last published: 2026-08-01T03:38:22.978Z ### Schema #### Parameters - Schema type: actions ```json { "actions": { "create_new": { "description": "Create a private draft agent.", "properties": { "name": { "type": "string", "description": "Agent display name. Required on create_new.", "required": false }, "description": { "type": "string", "description": "Free-text description shown in the marketplace.", "required": false }, "chat_model": { "type": "string", "description": "Override the agent's chat model identifier.", "required": false }, "slug": { "type": "string", "description": "Admin-only when slug_unlocked=true. Final URL slug for active agents.", "required": false }, "draft_slug": { "type": "string", "description": "Admin-only when slug_unlocked=true. Editable URL slug intent before activation.", "required": false }, "slug_unlocked": { "type": "boolean", "description": "Admin-only flag required before changing slug or draft_slug manually.", "required": false }, "context_document_ids": { "type": "array", "description": "Full set of Agent Context document ObjectIds to attach on create_new/update_existing (replaces the existing set). Use attach_context/detach_context to mutate a single id.", "required": false, "items": { "type": "string", "description": "" } }, "remixed_from_agent_id": { "type": "string", "description": "Source agent id to remix from. Used by create_new/remix.", "required": false }, "remixed_from_agent_name": { "type": "string", "description": "Override the remix source name attribution.", "required": false } } }, "update_existing": { "description": "Update editable fields on an agent you own. is_template is admin-only.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "name": { "type": "string", "description": "Agent display name. Required on create_new.", "required": false }, "description": { "type": "string", "description": "Free-text description shown in the marketplace.", "required": false }, "status": { "type": "string", "description": "Lifecycle status. Use the dedicated publish/archive actions where possible.", "required": false, "enum": [ "draft", "active", "archived" ] }, "chat_model": { "type": "string", "description": "Override the agent's chat model identifier.", "required": false }, "system_prompt": { "type": "string", "description": "System prompt persisted on the agent.", "required": false }, "slug": { "type": "string", "description": "Admin-only when slug_unlocked=true. Final URL slug for active agents.", "required": false }, "draft_slug": { "type": "string", "description": "Admin-only when slug_unlocked=true. Editable URL slug intent before activation.", "required": false }, "slug_unlocked": { "type": "boolean", "description": "Admin-only flag required before changing slug or draft_slug manually.", "required": false }, "context_document_ids": { "type": "array", "description": "Full set of Agent Context document ObjectIds to attach on create_new/update_existing (replaces the existing set). Use attach_context/detach_context to mutate a single id.", "required": false, "items": { "type": "string", "description": "" } }, "is_template": { "type": "boolean", "description": "Admin-only. Mark the agent as a public template; non-admin writes are silently dropped.", "required": false } } }, "fetch_existing": { "description": "List your agents (recently updated first), or fetch one by id/slug.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "query": { "type": "string", "description": "Substring search over name and description for fetch_existing/search_public.", "required": false }, "limit": { "type": "integer", "description": "Maximum results for list/search actions (1-100).", "required": false, "minimum": 1, "maximum": 100 }, "skip": { "type": "integer", "description": "Pagination offset for list/search actions.", "required": false, "minimum": 0 } } }, "search_public": { "description": "Search active public agents.", "properties": { "query": { "type": "string", "description": "Substring search over name and description for fetch_existing/search_public.", "required": false }, "limit": { "type": "integer", "description": "Maximum results for list/search actions (1-100).", "required": false, "minimum": 1, "maximum": 100 }, "skip": { "type": "integer", "description": "Pagination offset for list/search actions.", "required": false, "minimum": 0 } } }, "publish": { "description": "Transition DRAFT to ACTIVE; stamps published_at the first time.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false } } }, "archive": { "description": "Soft-delete the agent. If forward_to is supplied, issue 301 redirects from the agent's canonical paths to that internal destination.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "forward_to": { "type": "string", "description": "Internal path to redirect the archived agent's URLs to. Must start with /.", "required": false } } }, "remix": { "description": "Create a private copy of a viewable agent.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "name": { "type": "string", "description": "Agent display name. Required on create_new.", "required": false } } }, "add_product": { "description": "Attach a product to the agent. Routes through file manager auto-attach.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "product_id": { "type": "string", "description": "Product ObjectId for add_product/remove_product.", "required": false } } }, "remove_product": { "description": "Detach a product from the agent. Routes through file manager auto-attach.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "product_id": { "type": "string", "description": "Product ObjectId for add_product/remove_product.", "required": false } } }, "add_workflow": { "description": "Attach a workflow to the agent. Routes through file manager auto-attach.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "workflow_id": { "type": "string", "description": "Workflow (skill chain) ObjectId for add_workflow/remove_workflow.", "required": false } } }, "remove_workflow": { "description": "Detach a workflow from the agent. Routes through file manager auto-attach.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "workflow_id": { "type": "string", "description": "Workflow (skill chain) ObjectId for add_workflow/remove_workflow.", "required": false } } }, "attach_context": { "description": "Attach an Agent Context document to the agent.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "context_document_id": { "type": "string", "description": "Agent Context document ObjectId for attach_context/detach_context.", "required": false } } }, "detach_context": { "description": "Detach an Agent Context document from the agent.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "context_document_id": { "type": "string", "description": "Agent Context document ObjectId for attach_context/detach_context.", "required": false } } }, "add_showcase_example": { "description": "Add a chat preview example to the agent.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "showcase_example": { "type": "object", "description": "Showcase example object for add_showcase_example. See get_instructions for shape.", "required": false } } }, "remove_showcase_example": { "description": "Remove a showcase example by id.", "properties": { "agent_id": { "type": "string", "description": "Agent ObjectId hex string or slug. Required for update/publish/archive/composition/showcase actions.", "required": false }, "showcase_example_id": { "type": "string", "description": "Showcase example id for remove_showcase_example.", "required": false } } }, "get_instructions": { "description": "Return the handler reference guide." } } } ``` ### Usage Instructions Agent Builder Tool creates and manages custom AI agents: lifecycle, composition (tools and workflows), context documents, and showcase chat previews. ## Response field allowlist (read this first) Responses use a strict allowlist. `system_prompt` and `chat_model` are writable but are **never returned** by any action, including `fetch_existing`. Keep your own copy of a system prompt if you need to read it back or edit it incrementally. ## Actions ### create_new Create a private draft agent. - `name` (required; omitting it returns `AGENT_CREATE_NAME_REQUIRED`) - `description`, `chat_model`, `context_document_ids` - `remixed_from_agent_id`, `remixed_from_agent_name` to create the draft as a remix of a source you can view - When `remixed_from_agent_id` is supplied, the source composition is authoritative: accessible tools, workflows, Agent Context documents, a non-empty system prompt, and an available chat model are cloned. Caller-supplied `chat_model` and `context_document_ids` are ignored on that path. ### update_existing Update fields on an agent you own. - `agent_id` (required) - `name`, `description`, `status` (`draft` | `active` | `archived`), `chat_model`, `system_prompt`, `context_document_ids` - Prefer the dedicated `publish` and `archive` actions over setting `status` directly ### fetch_existing List your agents (most recently updated first) or fetch one by id or slug. - `agent_id` to fetch one; `query`, `limit` (1-100), `skip` to list - Unreadable or missing agents return `AGENT_FETCH_NOT_FOUND` (existence is masked) ### search_public Browse active public agents. `query`, `limit`, `skip`. Only agents that are active AND public AND unarchived appear here. ### publish `agent_id`. Moves a draft to active. The first publish stamps `published_at` and promotes `draft_slug` to the public `slug` (clearing `draft_slug`); later publishes keep both. Publishing does **not** make an agent public: `visibility` stays `private` and the agent will not appear in `search_public`. Public visibility is driven by the admin-only `is_template` flag. ### archive `agent_id`, optional `forward_to`. - `forward_to` must be an internal path starting with `/` and free of `..`. Anything else, including an absolute URL, is **silently ignored**: the agent is archived and no redirects are written (`redirects_written: 0`). - If a well-formed path fails deeper validation (pointing at the agent's own URL, or at a path that is already redirected) the call returns `AGENT_ARCHIVE_SEO_REDIRECT_FAILED` and the agent is left unarchived so it can be retried safely. - On success the response reports `redirects_written` (one per canonical path: the slug path and the id path). ### remix `agent_id`, optional `name`. Creates a **new private draft** from any agent you can view and leaves the source unchanged. - Copies every source item the new owner can access: products, workflows, Agent Context documents, a non-empty system prompt, and a still-available chat model. - Missing, inactive, inaccessible, or unavailable items are omitted without failing an otherwise usable clone and are reported in `skipped[]` with `kind`, `id`, and `reason`. - Showcase examples, template/publication/archive state, source URLs, and the source remix count are not copied. - Sets `remixed_from_*` and `original_creator_*` attribution and increments the source's `remix_count`. ### add_product / remove_product `agent_id`, `product_id`. Attaches or detaches a tool. File Manager is appended automatically when any attached tool, or any tool inside an attached workflow, needs file storage; the response reports `file_manager_added`. Auto-attach is add-only, so File Manager stays attached after you remove the product that pulled it in. Unknown, inactive, or inaccessible products return `AGENT_COMPOSITION_PRODUCT_NOT_FOUND`. ### add_workflow / remove_workflow `agent_id`, `workflow_id`. Same automatic file storage behavior applies. ### attach_context / detach_context `agent_id`, `context_document_id`. Maximum 10 documents per agent. A malformed id returns `AGENT_CONTEXT_INVALID_ID`. Private context documents are rejected on public active agents. ### add_showcase_example / remove_showcase_example `agent_id` plus `showcase_example` (object) or `showcase_example_id` (string). Only one example may be featured; adding a featured example unfeatures the previous one. Duplicate ids return `AGENT_SHOWCASE_DUPLICATE_ID`; malformed examples return `AGENT_SHOWCASE_INVALID_ASSET`. ### get_instructions Returns this reference. ## Showcase example shape 2 to 10 messages, at least one `user` and one `assistant`. Roles do not need to alternate. Each message needs `id`, `role`, `timestamp` (ISO 8601), and a non empty `parts` array. Use durable public URLs or a `file_id` for any media; unsigned private storage URLs are rejected. ## Examples ```json {"action":"create_new","name":"Deal Desk","description":"Sales follow-up agent for the Pipedrive pipeline."} ``` ```json {"action":"add_product","agent_id":"","product_id":""} ``` ```json {"action":"update_existing","agent_id":"","system_prompt":"Work only from records in the CRM. Never invent commitments. Every email is a draft for review."} ``` ```json {"action":"publish","agent_id":""} ``` ```json {"action":"archive","agent_id":"","forward_to":"/agents/replacement-agent"} ``` ## Response Actions return the affected agent payload (id, name, slug, draft_slug, status, visibility, products, workflows, context_document_ids, showcase_examples, plus computed categories and industry_tags derived from the attached products). Successful remix responses also include `skipped[]` (possibly empty). Errors return a stable `AGENT_*` error code with a usable message. ### Additional Product Content ## Build your own AI agent, in a conversation Agent Builder Tool is a no code AI agent builder. You describe the job you want done, and it creates the agent, connects the tools and workflows that job needs, writes the operating instructions, and publishes it under its own name and link. Everything happens in plain language, in chat, while you watch it take shape. Most AI agent platforms hand you a framework and a blank file. This one hands you a working agent. Tell it what the agent should know, what it should be able to do, and what it must never do, and it assembles a custom AI agent you can run, share, and keep improving. ### What you can build 1. **Sales agents** that read your CRM pipeline, draft follow ups in your voice, and log every touch. 2. **Support agents** that answer from your own policy and pricing documents instead of guessing. 3. **Research agents** that monitor news, competitors, filings, and public data on a schedule. 4. **Operations agents** that move work between your inbox, calendar, spreadsheets, storage, and messaging tools. 5. **Front desk agents** that answer the phone, qualify inbound leads, and book the appointment. 6. **Internal copilots** that know how your team actually works and follow your rules every time. ### How it works 1. **Describe the agent.** Say what it should do in the same words you would use to brief a new hire. A private draft agent is created immediately. 2. **Give it tools.** Attach any tools from the marketplace: CRM, email, calendar, SMS and voice, documents, spreadsheets, maps, payments, data, and more. Your agent can use every one of them. 3. **Attach workflows.** Add complete multi step workflows so your agent can run an entire process, not just a single call. 4. **Teach it your business.** Attach context documents with your pricing, policies, product details, and brand voice so answers come out right the first time. 5. **Write the rules.** The system prompt is set in plain language and can be rewritten any time, so behavior stays exactly where you want it. 6. **Test it live.** Chat with the agent, see what it does, and adjust on the spot. 7. **Publish and share.** Move the draft to active, give it a public link, and put it in front of your team or your customers. ### Real tools, not toy integrations An AI agent is only as useful as what it can reach. Agent Builder Tool connects your agent to live tools that read and write real systems, and it handles the plumbing for you. When a tool or workflow needs file storage, file handling is attached to the agent automatically, so uploads, exports, and attachments simply work. ### Workflows turn agents into operators Single tool calls answer questions. Workflows finish jobs. Attach a multi step workflow and your agent can run a full pipeline: pull the records, do the analysis, draft the output, check the quality, file it in the right place, and report back. One agent can carry several workflows and choose the right one for the request. ### Your knowledge, your voice Context documents give your agent the things a generic model cannot know: how you price, what you promise, which words you never use, who to escalate to. Attach up to ten per agent and swap them whenever the business changes. ### Publish, share, and branch Publishing turns a draft into a live agent with its own page and link. Remixing creates a new private draft from any agent you can see and credits the original as its source. The remix starts with every tool, workflow, context document, operating instruction, and available model that you can access already copied; anything unavailable to you is skipped and reported without changing the original. Build the sales version, remix it for renewals, remix that for onboarding, then tune each branch for its own job while the proven agent keeps running untouched. Showcase chat previews let visitors see exactly what your agent does before they run it. ### Who it is for Founders, operators, marketers, sales teams, consultants, agencies, and developers who want custom AI agents without a build cycle. If you have been searching for an AI agent builder, an AI agent creator, or a no code way to build AI agents that use real tools, this is the tool that does it, from first idea to published agent, in one conversation. ### Frequently Asked Questions #### How do I connect this tool to an external agent? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md You can install the local MCP server by opening a terminal and running: ``` npm install -g @agentpmt/mcp-router agentpmt-setup ``` This will connect you to local agents like Claude Code, Windsurf, Grok Build, Cursor, etc. Alternatively you can connect to the hosted version with this config block, no installation required: ``` { "mcpServers": { "agentpmt": { "type": "streamable-http", "url": "https://api.agentpmt.com/mcp", "headers": { "Authorization": "Bearer ", "x-instance-metadata": "{\"client\":\"generic-mcp\",\"platform\":\"remote\"}" } } } } ``` [View MCP Connection Instructions](/docs/mcp-reference/connection) for more details. #### How does an external agent use this tool? - Page URL: https://www.agentpmt.com/faq - Markdown URL: https://www.agentpmt.com/faq?format=agent-md After the external agent is connected to an Agent Group that can use this tool, paste this prompt into the agent: > Use the AgentPMT-Tool-Search-and-Execution tool. First call action 'get\_instructions' so you know how to use the tool search interface. Then call action 'get\_schema' with tool\_id 69ed32a83ccc082ef9976212 ("Agent Builder Tool"). After reading the schema and any returned instructions, tell me what this tool can do, we are going to be using it The agent should fetch the tool schema first, collect the required parameters for your request, and then call the tool through AgentPMT. #### Can I build an AI agent without coding? - Page URL: https://www.agentpmt.com/faq#faq-6a6b743835a694e90e703be5 - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b743835a694e90e703be5 - Tags: Product Specific Yes. The entire build happens in conversation. You describe the agent, review what gets attached, adjust the instructions in plain language, and publish when it behaves the way you want. There is no framework to install, no deployment step, and no prompt engineering background required. #### Can I change an agent after it is published? - Page URL: https://www.agentpmt.com/faq#faq-6a6b803b35a694e90e703cfc - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b803b35a694e90e703cfc - Tags: Product Specific Yes. Name, description, instructions, tools, workflows, and context documents can all be updated on a live agent, and changes take effect on the next conversation. If an agent has run its course you can archive it and point its old links at a replacement, so nothing sends visitors to a dead end. #### Can I share my AI agent with my team or publish it publicly? - Page URL: https://www.agentpmt.com/faq#faq-6a6b803a35a694e90e703cfa - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b803a35a694e90e703cfa - Tags: Product Specific Yes. Agents start as private drafts so you can experiment safely. Publishing makes the agent active with its own page and link, ready to hand to your team. You can also add showcase chat previews so anyone opening the agent can see exactly what it does before they run it. #### How do I give my AI agent tools like a CRM or email? - Page URL: https://www.agentpmt.com/faq#faq-6a6b743835a694e90e703be6 - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b743835a694e90e703be6 - Tags: Product Specific Ask for them by name. Tools from the marketplace can be attached to any agent you own, including CRM, email, calendar, SMS and voice, spreadsheets, documents, storage, maps, payments, and data services. Once attached, the agent can use those tools during a chat. If a tool needs file storage, file handling is attached to the agent automatically. #### How does my agent learn about my business? - Page URL: https://www.agentpmt.com/faq#faq-6a6b743935a694e90e703be8 - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b743935a694e90e703be8 - Tags: Product Specific Attach context documents. These hold your pricing, policies, product details, escalation rules, and brand voice, and the agent reads them before it answers. You can attach up to ten documents to an agent and swap them out whenever the business changes, so answers stay current without rebuilding anything. #### What does remixing an agent mean? - Page URL: https://www.agentpmt.com/faq#faq-6a6b803b35a694e90e703cfb - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b803b35a694e90e703cfb - Tags: Product Specific Remixing creates a new private draft from any agent you can view and credits the original as its source. The remix copies every tool, workflow, Agent Context document, operating instruction, and available model that you can access. Missing, inactive, inaccessible, or unavailable items are skipped and reported so the usable parts still copy successfully. The original agent is never modified, making remix the fastest way to branch a proven agent for renewals, onboarding, or another specialized role. #### What is an AI agent builder? - Page URL: https://www.agentpmt.com/faq#faq-6a6b743835a694e90e703be4 - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b743835a694e90e703be4 - Tags: Product Specific An AI agent builder is a tool that turns a description of a job into a working AI agent. Instead of writing code, you explain what the agent should do, what it should have access to, and how it should behave. Agent Builder Tool creates the agent, attaches the tools and workflows it needs, sets its operating instructions, and publishes it with its own name and link. #### What is the difference between a tool and a workflow? - Page URL: https://www.agentpmt.com/faq#faq-6a6b743935a694e90e703be7 - Markdown URL: https://www.agentpmt.com/faq?format=agent-md#faq-6a6b743935a694e90e703be7 - Tags: Product Specific A tool is a single capability, such as sending an email or updating a deal. A workflow is a complete multi step process that chains several tools together with logic and checks along the way. Attaching a workflow lets your agent finish an entire job in one request instead of improvising the steps. An agent can carry several workflows and pick the right one for the situation. ### Dependencies This product has no public dependency products.