# AgentPMT Audit Logs ## Links - Product page URL: https://www.agentpmt.com/marketplace/agentpmt-audit-logs - Product markdown URL: https://www.agentpmt.com/marketplace/agentpmt-audit-logs?format=agent-md - Product JSON URL: https://www.agentpmt.com/marketplace/agentpmt-audit-logs?format=agent-json ## Overview - Product ID: 6a3c7e39dd9737171d93cb19 - Type: memory - Unit type: request - Price: Price unavailable - Categories: Quality Assurance, Developer Tools, Compliance & Audit, Project Management, Task & Workflow Automation, Agent Memory and Context - Generated at: 2026-08-24T22:25:56.620Z ### Page Description Give your agents a memory of everything they have done. Pull up past chat conversations, review every tool your agents have run, and look back over finished and scheduled workflow runs, all on demand and in plain language. Ask "what did my agents work on this weekend?" or "why did that workflow fail?" and get a clear, sourced answer drawn straight from your own activity history. It is the easiest way to keep oversight of autonomous agents, debug a run that went sideways, put together an end-of-week summary, and keep a trustworthy record of what was done and when. ### Agent Description Look back over this account's own activity, read-only. Search and read past chat sessions, pull a full chat transcript together with the tool calls that happened inside it, list tool-call history filtered by tool, action, response status, and date range, and review prior workflow runs and scheduled workflows. Access is scoped to the agent groups the user is authorized for. Use it to answer questions about what was done and when, investigate why a run failed, trace a specific tool's usage, or summarize recent activity. ## Details ### Details Give your agents a memory of everything they have done. Pull up past chat conversations, review every tool your agents have run, and look back over finished and scheduled workflow runs, all on demand and in plain language. Ask "what did my agents work on this weekend?" or "why did that workflow fail?" and get a clear, sourced answer drawn straight from your own activity history. It is the easiest way to keep oversight of autonomous agents, debug a run that went sideways, put together an end-of-week summary, and keep a trustworthy record of what was done and when. ### Actions - `list_agent_groups`: List the agent groups this user can read. - `list_chat_sessions`: List chat sessions for the current or selected agent group. - `get_chat_review`: Fetch a bounded chat transcript page and correlated tool calls. - `list_tool_calls`: List safe, read-only tool call activity for authorized agent groups. - `list_workflow_runs`: List prior workflow run results for authorized agent groups. - `get_workflow_run`: Fetch one prior workflow run result by ID. - `list_workflow_schedules`: List scheduled workflows for authorized agent groups. - `get_workflow_schedule`: Fetch one scheduled workflow by ID. ### Use Cases Summarize what your agents did this week, Review a past chat conversation and the tool calls inside it, Audit tool-call history by tool, status, and date, Investigate why a workflow run failed, Check recent and upcoming scheduled workflow runs, Build an activity report for oversight, Trace a single tool's usage history, Keep a read-only audit trail of agent actions ### Workflows Using This Tool #### Workflow Builder Agent Design, build, test, and publish custom automation workflows on AgentPMT. Walk through the complete workflow creation process from idea to published skill: define what you want to automate, discover available tools from a catalog of 170+, design multi-step DAG graphs with tool nodes, prompt nodes, branching, loops, and human notifications, then test and iterate until the workflow runs correctly. Uses the AgentPMT Workflow Creator tool directly for tool discovery, workflow creation, verification, and publishing. Covers workflow architecture, node types, edge connections, industry tagging, versioning, and publishing. Ideal for no-code automation, business process automation, task chaining, AI agent orchestration, and building reusable skill chains. - Page URL: https://www.agentpmt.com/agent-workflow-skills/workflow-builder-agent - Markdown URL: https://www.agentpmt.com/agent-workflow-skills/workflow-builder-agent?format=agent-md - Published: 2026-07-28T03:12:56.407Z ### Related Content #### Consumer AI Shopping's Real Test Starts at the Checkout - Type: article - Page URL: https://www.agentpmt.com/articles/consumer-ai-shopping-s-real-test-starts-at-the-checkout - Markdown URL: https://www.agentpmt.com/articles/consumer-ai-shopping-s-real-test-starts-at-the-checkout?format=agent-md As of mid-July 2026, using AI to shop has become normal for consumers and standard for retailers, yet shoppers still balk at letting an agent pay. The retailers pulling ahead are the ones building assistants they can be accountable for at checkout, with approval steps, audit records, spend controls, and first-party data, rather than answer-only chatbots that hand the customer to third-party AI. #### Artificial Intelligence Business Oversight, on AgentPMT - Type: article - Page URL: https://www.agentpmt.com/articles/artificial-intelligence-business-oversight-on-agentpmt - Markdown URL: https://www.agentpmt.com/articles/artificial-intelligence-business-oversight-on-agentpmt?format=agent-md AgentPMT Audit Logs is now live on the marketplace: a read-only connector that gives your agents a searchable memory of everything they have done, past chat sessions and their tool calls, filtered tool-call history, and finished or scheduled workflow runs, so you can answer what your agents did, trace why a run failed, and keep an auditable record on demand. #### Artificial Intelligence in Churches Carries a Secular Tilt - Type: article - Page URL: https://www.agentpmt.com/articles/artificial-intelligence-in-churches-carries-a-secular-tilt - Markdown URL: https://www.agentpmt.com/articles/artificial-intelligence-in-churches-carries-a-secular-tilt?format=agent-md Three research efforts published in one week measured the moral defaults inside large language models and found that a model's values shift with its version, the language of the conversation, and the culture behind its training data. The same week, UK church leaders published the first practical AI guidance for ministry. Together they turn model selection for faith organizations from an IT purchase into a governance decision. #### Artificial Intelligence Technology Fabricates Missing Data - Type: article - Page URL: https://www.agentpmt.com/articles/artificial-intelligence-technology-fabricates-missing-data - Markdown URL: https://www.agentpmt.com/articles/artificial-intelligence-technology-fabricates-missing-data?format=agent-md New research posted to arXiv this month finds that when an AI agent's tools fail silently, returning an empty payload instead of an error, the agent's most common response is to treat that emptiness as data and fabricate a result. That mechanism explains why most enterprises have moved agents past pilots while only a third trust what those agents do, and it points at the specific instrumentation, recorded tool responses, approval gates, and scoped credentials, that separates the teams already seeing gains from the ones still waiting. #### Artificial Intelligence for Agriculture Needs Readable Data - Type: article - Page URL: https://www.agentpmt.com/articles/artificial-intelligence-for-agriculture-needs-readable-data - Markdown URL: https://www.agentpmt.com/articles/artificial-intelligence-for-agriculture-needs-readable-data?format=agent-md USDA has asked universities and outside partners to build AI tools that can translate the germplasm data it already collects, and the House introduction of the FARM AI Act plus four preprints posted the same week all point at the same bottleneck. The limiting factor in agricultural AI right now is whether existing records can be read by a machine, and that is work an operator can start without waiting on federal funding. #### Professional Services AI Now Has to Show Its Work - Type: article - Page URL: https://www.agentpmt.com/articles/professional-services-ai-now-has-to-show-its-work - Markdown URL: https://www.agentpmt.com/articles/professional-services-ai-now-has-to-show-its-work?format=agent-md Three studies published this week converge on one measurable finding: handing an AI agent the correct source material does not mean the agent applies it, and compliance slips further under time pressure. In professional services, where the deliverable carries a signature and the firm carries the liability, that turns agent accountability into a question of reproducibility and evidence. Here is what firms are already building in response, from insured autonomous work to per-run audit records and deliberate human review gates. ## 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": "6a3c7e39dd9737171d93cb19", "parameters": { "action": "get_instructions" } }' ``` ### 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: agentpmt-audit-logs - Version: 1.0.0 - Download SKILL.md: https://raw.githubusercontent.com/AgentPMT/agent-skills/main/skills/agentpmt-audit-logs/SKILL.md - Package source: https://github.com/AgentPMT/agent-skills/tree/main/skills/agentpmt-audit-logs - OpenClaw listing: https://clawhub.ai/agentpmt/agentpmt-audit-logs - OpenClaw install: `openclaw skills install agentpmt-audit-logs` - skills.sh install: `npx skills add AgentPMT/agent-skills --skill agentpmt-audit-logs` - Last published: 2026-07-10T17:37:33.425Z ### Schema #### Parameters - Schema type: actions ```json { "actions": { "get_instructions": { "description": "Explain how to read chat history, tool calls, workflow runs, and scheduled workflows." }, "list_agent_groups": { "description": "List the agent groups this user can read.", "properties": { "limit": { "type": "integer", "description": "Maximum list items to return (1-100).", "required": false, "default": 20, "minimum": 1, "maximum": 100 }, "offset": { "type": "integer", "description": "Number of list items to skip.", "required": false, "minimum": 0, "maximum": 10000 } } }, "list_chat_sessions": { "description": "List chat sessions for the current or selected agent group.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "query": { "type": "string", "description": "Optional search text for supported list actions.", "required": false }, "status": { "type": "string", "description": "Optional status filter. Use all for workflow run and schedule list actions.", "required": false }, "limit": { "type": "integer", "description": "Maximum list items to return (1-100).", "required": false, "default": 20, "minimum": 1, "maximum": 100 }, "offset": { "type": "integer", "description": "Number of list items to skip.", "required": false, "minimum": 0, "maximum": 10000 }, "from_date": { "type": "string", "description": "Optional inclusive ISO date/datetime lower bound.", "required": false }, "to_date": { "type": "string", "description": "Optional inclusive ISO date/datetime upper bound.", "required": false } } }, "get_chat_review": { "description": "Fetch a bounded chat transcript page and correlated tool calls.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "session_id": { "type": "string", "description": "Chat session ID for review or session-scoped tool call listing.", "required": true }, "message_limit": { "type": "integer", "description": "Maximum chat messages to return for get_chat_review (1-200).", "required": false, "default": 100, "minimum": 1, "maximum": 200 }, "message_offset_from_end": { "type": "integer", "description": "Offset from the end of the transcript for get_chat_review.", "required": false, "minimum": 0, "maximum": 10000 }, "activity_limit": { "type": "integer", "description": "Maximum correlated tool activity rows for get_chat_review (1-200).", "required": false, "default": 100, "minimum": 1, "maximum": 200 }, "activity_offset": { "type": "integer", "description": "Tool activity row offset for get_chat_review.", "required": false, "minimum": 0, "maximum": 10000 } } }, "list_tool_calls": { "description": "List safe, read-only tool call activity for authorized agent groups.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "session_id": { "type": "string", "description": "Chat session ID for review or session-scoped tool call listing.", "required": false }, "product_id": { "type": "string", "description": "Optional product/tool ID filter for list_tool_calls.", "required": false }, "action_name": { "type": "string", "description": "Optional nested tool action name filter for list_tool_calls.", "required": false }, "response_status": { "type": "string", "description": "Optional tool call response status filter.", "required": false }, "limit": { "type": "integer", "description": "Maximum list items to return (1-100).", "required": false, "default": 20, "minimum": 1, "maximum": 100 }, "offset": { "type": "integer", "description": "Number of list items to skip.", "required": false, "minimum": 0, "maximum": 10000 }, "from_date": { "type": "string", "description": "Optional inclusive ISO date/datetime lower bound.", "required": false }, "to_date": { "type": "string", "description": "Optional inclusive ISO date/datetime upper bound.", "required": false } } }, "list_workflow_runs": { "description": "List prior workflow run results for authorized agent groups.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "workflow_id": { "type": "string", "description": "Optional workflow ID filter.", "required": false }, "schedule_id": { "type": "string", "description": "Workflow schedule ID for schedule detail or run filtering.", "required": false }, "trigger_source": { "type": "string", "description": "Workflow run trigger source filter.", "required": false, "default": "all", "enum": [ "all", "agent_webhook", "dashboard_schedule_test", "workflow_schedule" ] }, "status": { "type": "string", "description": "Optional status filter. Use all for workflow run and schedule list actions.", "required": false }, "limit": { "type": "integer", "description": "Maximum list items to return (1-100).", "required": false, "default": 20, "minimum": 1, "maximum": 100 }, "offset": { "type": "integer", "description": "Number of list items to skip.", "required": false, "minimum": 0, "maximum": 10000 }, "from_date": { "type": "string", "description": "Optional inclusive ISO date/datetime lower bound.", "required": false }, "to_date": { "type": "string", "description": "Optional inclusive ISO date/datetime upper bound.", "required": false } } }, "get_workflow_run": { "description": "Fetch one prior workflow run result by ID.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "run_id": { "type": "string", "description": "Workflow run ID for get_workflow_run.", "required": true } } }, "list_workflow_schedules": { "description": "List scheduled workflows for authorized agent groups.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "workflow_id": { "type": "string", "description": "Optional workflow ID filter.", "required": false }, "status": { "type": "string", "description": "Optional status filter. Use all for workflow run and schedule list actions.", "required": false }, "execution_mode": { "type": "string", "description": "Workflow schedule execution mode filter.", "required": false, "default": "all", "enum": [ "all", "external_due", "managed_cron" ] }, "query": { "type": "string", "description": "Optional search text for supported list actions.", "required": false }, "limit": { "type": "integer", "description": "Maximum list items to return (1-100).", "required": false, "default": 20, "minimum": 1, "maximum": 100 }, "offset": { "type": "integer", "description": "Number of list items to skip.", "required": false, "minimum": 0, "maximum": 10000 }, "due_from": { "type": "string", "description": "Optional inclusive next_due_at lower bound for schedules.", "required": false }, "due_to": { "type": "string", "description": "Optional inclusive next_due_at upper bound for schedules.", "required": false } } }, "get_workflow_schedule": { "description": "Fetch one scheduled workflow by ID.", "properties": { "agent_group_id": { "type": "string", "description": "Optional agent group ID. This is stored internally as budget_id but shown to users as an agent group.", "required": false }, "scope": { "type": "string", "description": "Read scope. current_agent_group reads only the calling workflow's agent group unless agent_group_id is provided. all_authorized_agent_groups reads every agent group the user can access.", "required": false, "default": "current_agent_group", "enum": [ "current_agent_group", "all_authorized_agent_groups" ] }, "schedule_id": { "type": "string", "description": "Workflow schedule ID for schedule detail or run filtering.", "required": true } } } } } ``` ### 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 6a3c7e39dd9737171d93cb19 ("AgentPMT Audit Logs"). 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. ### Dependencies This product has no public dependency products.