# Archetype AI Documentation

> ## Agent Instructions
> Start with /introduction/getting-started. Use the Direct Query API (POST /query) with the Newton Fusion model (text, image, and video reasoning) or the Newton Omega encoder (time-series embeddings). ATAI_API_ENDPOINT must include the version path: /v0.5 for most APIs, /v0.6 for the Fine-Tuning Service. Pages whose descriptions are marked (Archived) document the legacy Lens runtime — do not use them for new projects.

- [Overview](https://docs.archetypeai.app/introduction/overview.md): What the Archetype platform is: the Newton foundation model for physical AI, platform capabilities, and where to start.
- [Developer Quickstart](https://docs.archetypeai.app/introduction/getting-started.md): Run your first Direct Query calls against the Newton Fusion and Newton Omega models — analyze a video and detect a machine fault from real sensor data, in a few lines of Python.
- [Overview](https://docs.archetypeai.app/core-concepts/introduction/introduction.md): The platform's core concepts: Newton models, Files, Batch Processing, Direct Query, and Customization, and how they fit together.
- [Overview](https://docs.archetypeai.app/core-concepts/agents/overview.md): Overview of the available agent blueprints and how they're used to create new agents.
- [Managing Agents Using the Agents API](https://docs.archetypeai.app/core-concepts/agents/api.md): An introduction to using the Agents API to create, run, and manage agents.
- [Anomaly Discovery Agent](https://docs.archetypeai.app/core-concepts/agents/anomaly-discovery.md): Discovers novel anomalies and failure modes by distinguishing meaningful issues from normal variation, with no labeled failures required. Every sensor data time window comes back with an anomaly score, flagging behavior that falls outside the norm.
- [Manual Generation Agent](https://docs.archetypeai.app/core-concepts/agents/manual-generation.md): Analyzes video recordings of a procedure and generates step-by-step work instructions, with a relevant image pulled for every step. Every step comes back as editable structured text, ready to refine and publish.
- [Operational State Monitoring Agent](https://docs.archetypeai.app/core-concepts/agents/osm.md): Continuously monitors machines and industrial processes by identifying changing operating states from multimodal sensor data. Every window comes back with a predicted state and a confidence score.
- [Rare Event Detection Agent](https://docs.archetypeai.app/core-concepts/agents/rare-event-detection.md): Detects known faults and failures by matching new data against a handful of labeled examples. Each sensor data window is classified as normal or abnormal, with a confidence score.
- [Task Verification Agent](https://docs.archetypeai.app/core-concepts/agents/task-verification.md): Verifies work is performed according to standard operating procedures by observing video data. Returns a pass/fail verdict with a short description and the timestamp it came from, plus a summary across the run.
- [Introduction to the Files API](https://docs.archetypeai.app/core-concepts/files/files.md): Upload and manage data on the Archetype platform: organization-scoped access, file IDs, upload paths, and supported formats.
- [Direct-to-Cloud Uploads](https://docs.archetypeai.app/core-concepts/files/cloud-upload.md): Upload files up to 250GB with the direct-to-cloud workflow: presigned part URLs, checkpointing, and upload completion.
- [Overview](https://docs.archetypeai.app/core-concepts/batch-processing/overview.md): How the Batch Processing API runs jobs against many files via the Jobs Orchestration Service: jobs, indexes, tasks, pipelines, and the job lifecycle.
- [YAML Parameter Reference](https://docs.archetypeai.app/core-concepts/batch-processing/yaml-parameters.md): A reference for the parameters available when configuring batch jobs.
- [Improving Model Performance](https://docs.archetypeai.app/core-concepts/models/model-performance.md): Recommendations to help improve the performance of Newton models for your use cases.
- [Overview](https://docs.archetypeai.app/core-concepts/customization/overview.md): Three ways to customize Newton — prompting, n-shot examples, and fine-tuning — and how to choose based on your model family and labeled data.
- [N-Shot Examples](https://docs.archetypeai.app/core-concepts/customization/n-shot-examples.md): Classify time-series sensor data with the Newton Omega model by comparing new windows against a small labeled reference library — no training required.
- [Fine-Tuning](https://docs.archetypeai.app/core-concepts/customization/fine-tuning.md): Train a forked instance of Newton on your own data set: the most powerful customization option, producing an org-private model adapted to your use case.
- [Overview](https://docs.archetypeai.app/developer-console/overview.md): What you can do in the Developer Console: create API keys, manage files, run batch jobs, fine-tune models, and access documentation.
- [Profile & API Keys](https://docs.archetypeai.app/developer-console/profile.md): View your account information and create and manage your API keys.
- [Using Agents in the Developer Console](https://docs.archetypeai.app/developer-console/agents/overview.md): A guide to running, monitoring, and deleting agents using the Developer Console.
- [Agent Gallery](https://docs.archetypeai.app/developer-console/agents/agent-gallery.md): Browse the available agent blueprints, view details about them, and access code examples and live demos.
- [Agent Manager](https://docs.archetypeai.app/developer-console/agents/agent-manager.md): View and run agents available to your organization.
- [Batch Manager](https://docs.archetypeai.app/developer-console/batch-manager.md): Create, manage, and monitor batch processing jobs from the Batch Manager dashboard in the Developer Console.
- [Fine-Tuning](https://docs.archetypeai.app/developer-console/fine-tuning/fine-tuning.md): Create and monitor fine-tuning jobs from the Developer Console: training data, job configuration, progress, logs, and checkpoints.
- [Overview](https://docs.archetypeai.app/libraries/libraries.md): Set up your development environment to use the Archetype API with a client library in your preferred language
- [Python](https://docs.archetypeai.app/libraries/python.md): Install the official Python client on macOS, Linux, or Windows, verify the installation, and keep it up to date.
- [Environment Variables](https://docs.archetypeai.app/libraries/environment-variables.md): Configure environment variables for the Archetype AI platform.
- [Example Projects](https://docs.archetypeai.app/code-examples/example-projects.md): Open-source demo projects built on the Direct Query API — clone them as starting templates for vision, text reasoning, and time-series applications.
- [Request Access](https://docs.archetypeai.app/support/request-access.md): Request a free trial API key for the Archetype platform.
- [Support](https://docs.archetypeai.app/support/support.md): This page covers common issues you might encounter when working with the Archetype API and provides step-by-step solutions.
- [Troubleshooting](https://docs.archetypeai.app/support/troubleshooting.md): Common issues and solutions when working with Archetype's APIs
- [Error Codes](https://docs.archetypeai.app/support/error-codes.md): Canonical list of platform error codes with meanings, causes, and which API surface emits them.
- [v1.1.x](https://docs.archetypeai.app/release-notes/1.1.x.md): These notes detail the new features, enhancements, and fixes included in each release of our platform.
- [What is a Lens?](https://docs.archetypeai.app/core-concepts/lenses/overview.md): (Archived) Legacy Lens runtime: what Lenses are and how they interpret sensor data.
- [Activity Monitor](https://docs.archetypeai.app/core-concepts/lenses/lens-templates/activity-monitor.md): (Archived) Legacy Lens runtime: the Activity Monitor starter lens template.
- [Machine State Lens](https://docs.archetypeai.app/core-concepts/lenses/lens-templates/machine-state.md): (Archived) Legacy Lens runtime: the Machine State starter lens template.
- [Test Lens](https://docs.archetypeai.app/core-concepts/lenses/lens-templates/test-lens.md): (Archived) Legacy Lens runtime: the Test Lens starter template.
- [Lens Parameters](https://docs.archetypeai.app/core-concepts/lenses/lens-parameter.md): (Archived) Legacy Lens runtime: reference for configuring lens parameters across lens types.
- [Lens Processors](https://docs.archetypeai.app/core-concepts/lenses/lens-processors.md): (Archived) Legacy Lens runtime: Lens processors reference.
- [Lens Customization](https://docs.archetypeai.app/core-concepts/customization/lens-customization.md): (Archived) Legacy Lens runtime: customizing lens behavior through configuration.
- [Data Streams](https://docs.archetypeai.app/core-concepts/streams/data-streams.md): (Archived) Legacy Lens runtime: input, output, and control streams for moving data in and out of a lens.
- [CSV File Reader](https://docs.archetypeai.app/core-concepts/streams/data-connectors/readers/csv-reader.md): (Archived) Legacy Lens runtime: stream CSV timeseries data into a lens with the CSV File Reader connector.
- [Video File Reader](https://docs.archetypeai.app/core-concepts/streams/data-connectors/readers/video-reader.md): (Archived) Legacy Lens runtime: stream pre-recorded video into a lens with the Video File Reader connector.
- [RTSP Video Reader](https://docs.archetypeai.app/core-concepts/streams/data-connectors/readers/rtsp-video-reader.md): (Archived) Legacy Lens runtime: stream live RTSP camera video into a lens.
- [JSONL File Reader](https://docs.archetypeai.app/core-concepts/streams/data-connectors/readers/jsonl-file-reader.md): (Archived) Legacy Lens runtime: stream JSONL data into a lens with the JSONL File Reader connector.
- [SSE Writer](https://docs.archetypeai.app/core-concepts/streams/data-connectors/writers/sse-writer.md): (Archived) Legacy Lens runtime: stream lens output over Server-Sent Events with the SSE Writer connector.
- [Events](https://docs.archetypeai.app/core-concepts/streams/events/overview.md): (Archived) Legacy Lens runtime: the events protocol for sending data and control messages in and out of a lens.
- [Session Events](https://docs.archetypeai.app/core-concepts/streams/events/session-events.md): (Archived) Legacy Lens runtime: session events for querying, validating, and controlling active lens sessions.
- [Stream Events](https://docs.archetypeai.app/core-concepts/streams/events/stream-events.md): (Archived) Legacy Lens runtime: input/output stream configuration events for lens sessions.
- [Data Events](https://docs.archetypeai.app/core-concepts/streams/events/data-events.md): (Archived) Data event formats for packaging sensor data (text, JSON, base64 image, numeric array); the payload shapes are also used by the Direct Query API's events parameter.
- [SSE Streaming](https://docs.archetypeai.app/core-concepts/streams/events/sse-streaming.md): (Archived) Legacy Lens runtime: real-time SSE streaming of lens session output.
- [Getting Started](https://docs.archetypeai.app/developer-console/introduction.md): (Archived) Legacy Lens-era Developer Console guide: the Workbench, lens monitoring, and file management.
- [Activity Monitor Lens](https://docs.archetypeai.app/developer-console/workbench/activity.md): (Archived) Legacy Lens-era Workbench tutorial: the Activity Monitor lens with video files.
- [Machine State Lens](https://docs.archetypeai.app/developer-console/workbench/machine-state.md): (Archived) Legacy Lens-era Workbench tutorial: the Machine State Lens with CSV files.
- [Activity Monitor](https://docs.archetypeai.app/code-examples/command-line-demos/activity-monitor/activity-monitor.md): (Archived) Legacy Lens-based CLI example: monitor video files or RTSP streams from the terminal.
- [Machine State Lens](https://docs.archetypeai.app/code-examples/command-line-demos/machine-state/machine-state.md): (Archived) Legacy Lens-based CLI example: classify machine states from time-series CSV data.
- [Real-time Camera Alerts](https://docs.archetypeai.app/code-examples/telegram-alerts/telegram-alerts.md): (Archived) Legacy Lens-based example: smart video monitoring with alerts delivered to Telegram.
- [RTSP Configuration](https://docs.archetypeai.app/code-examples/telegram-alerts/setup/rtsp-setup.md): (Archived) Setup guide for the legacy Telegram alerts example: RTSP on a Tapo C100 camera.
- [Telegram Bot Setup](https://docs.archetypeai.app/code-examples/telegram-alerts/setup/bot-setup.md): (Archived) Setup guide for the legacy Telegram alerts example: creating and configuring the Telegram bot.
- [Google Sheets Integration](https://docs.archetypeai.app/code-examples/machine-state/sensor-analysis-with-sheets.md): (Archived) Legacy Lens-based example: sensor analysis logged to Google Sheets.
- [Google Sheets API Credentials](https://docs.archetypeai.app/code-examples/machine-state/setup/credentials-setup.md): (Archived) Setup guide for the legacy Google Sheets example: OAuth 2.0 credentials.
- [Overview](https://docs.archetypeai.app/api-reference/introduction.md): Complete reference for APIs
- [Quick Reference](https://docs.archetypeai.app/api-reference/quick-reference.md): Essential API commands and patterns for quick reference.
- [Error Handling](https://docs.archetypeai.app/api-reference/errors.md): Understanding and handling API errors
- [Direct Query](https://docs.archetypeai.app/api-reference/query.md): Run a natural-language query against a model, optionally grounded in uploaded files or inline data events
- [Cancel Agent](https://docs.archetypeai.app/api-reference/agents/cancel-agent.md): Cancel a running or paused agent run
- [Create Blueprint](https://docs.archetypeai.app/api-reference/agents/create-blueprint.md): Register a new blueprint, or a new version of an existing key
- [Create Bundle](https://docs.archetypeai.app/api-reference/agents/create-bundle.md): Create a deployable bundle that pins a blueprint
- [Delete Agent](https://docs.archetypeai.app/api-reference/agents/delete-agent.md): Delete a terminal agent run
- [Delete Blueprint](https://docs.archetypeai.app/api-reference/agents/delete-blueprint.md): Delete a blueprint by id or key
- [Delete Bundle](https://docs.archetypeai.app/api-reference/agents/delete-bundle.md): Delete a bundle by id
- [Get Agent Logs](https://docs.archetypeai.app/api-reference/agents/get-agent-logs.md): Page through an agent run's executor-sourced log lines
- [Get Agent Results](https://docs.archetypeai.app/api-reference/agents/get-agent-results.md): Page through the output artifacts an agent run produced
- [Get Agent](https://docs.archetypeai.app/api-reference/agents/get-agent.md): Retrieve a single agent run and its current status
- [Get Blueprint](https://docs.archetypeai.app/api-reference/agents/get-blueprint.md): Retrieve a single blueprint, including its full document
- [Get Bundle](https://docs.archetypeai.app/api-reference/agents/get-bundle.md): Retrieve a single bundle, optionally with its recent runs
- [List Agent Events](https://docs.archetypeai.app/api-reference/agents/list-agent-events.md): Page through an agent run's event log
- [List Agents](https://docs.archetypeai.app/api-reference/agents/list-agents.md): Page through agent runs, filtered by status, bundle, or blueprint
- [List Blueprints](https://docs.archetypeai.app/api-reference/agents/list-blueprints.md): Page through the blueprint catalog
- [List Bundles](https://docs.archetypeai.app/api-reference/agents/list-bundles.md): Page through the bundles available to your organization
- [List Node Registry](https://docs.archetypeai.app/api-reference/agents/list-node-registry.md): List the nodes available for building blueprints
- [Pause Agent](https://docs.archetypeai.app/api-reference/agents/pause-agent.md): Pause a running agent
- [Resume Agent](https://docs.archetypeai.app/api-reference/agents/resume-agent.md): Resume a paused agent
- [Run Bundle](https://docs.archetypeai.app/api-reference/agents/run-bundle.md): Start a run of a bundle by binding its inputs and outputs
- [Register Lens](https://docs.archetypeai.app/api-reference/lens/lens-register.md): Register a new lens configuration that can be used to create sessions
- [Clone Lens](https://docs.archetypeai.app/api-reference/lens/lens-clone.md): Creates a copy of a lens template
- [Modify Lens](https://docs.archetypeai.app/api-reference/lens/lens-modify.md): Modifies an existing lens template
- [Delete Lens](https://docs.archetypeai.app/api-reference/lens/lens-delete.md): Deletes a lens template
- [Get Lens Info](https://docs.archetypeai.app/api-reference/lens/get-info.md): Retrieve high-level information about all lenses in your organization
- [Get Lens Metadata](https://docs.archetypeai.app/api-reference/lens/get-metadata.md): Retrieve detailed metadata for all lenses available to your organization
- [Create Lens Session](https://docs.archetypeai.app/api-reference/lens/create-session.md): Create a new lens session for processing sensor data
- [Destroy Lens Session](https://docs.archetypeai.app/api-reference/lens/destroy-session.md): Destroy an active lens session and free up resources
- [Get Sessions Info](https://docs.archetypeai.app/api-reference/lens/get-sessions-info.md): Get summary information about all lens sessions in your organization
- [Get Sessions Metadata](https://docs.archetypeai.app/api-reference/lens/get-sessions-metadata.md): Get detailed metadata for all active lens sessions
- [Session Events Process](https://docs.archetypeai.app/api-reference/lens/sessions-events-process.md): Sends an event to an active session to process
- [Lens Events API (WebSocket)](https://docs.archetypeai.app/api-reference/lens/websocket-events.md): Real-time control and data streaming for lens sessions via WebSocket
- [Consume Session Events (SSE)](https://docs.archetypeai.app/api-reference/lens/consumer.md): Subscribe to a lens session’s Server-Sent Events stream to receive asynchronous inference results
- [Lens API Examples](https://docs.archetypeai.app/api-reference/lens/examples.md): Complete examples for CSV streaming and RTSP camera integration
- [Upload File](https://docs.archetypeai.app/api-reference/files/upload.md): Upload a file via streaming multipart/form-data
- [Upload Base64 File](https://docs.archetypeai.app/api-reference/files/upload-base64.md): Upload a file with base64-encoded contents via streaming multipart/form-data
- [Delete File](https://docs.archetypeai.app/api-reference/files/delete-file.md): Delete a file from the authenticated organization
- [Download File](https://docs.archetypeai.app/api-reference/files/download-file.md): Download the raw bytes of a previously uploaded file
- [Get Files Info](https://docs.archetypeai.app/api-reference/files/get-info.md): Retrieve aggregated file statistics for the authenticated organization
- [Get File Metadata](https://docs.archetypeai.app/api-reference/files/get-metadata.md): Retrieve metadata for a specific file
- [List Files Metadata](https://docs.archetypeai.app/api-reference/files/get-all-metadata.md): List metadata for all files in the authenticated organization
- [Initiate Upload](https://docs.archetypeai.app/api-reference/files/initiate-upload.md): Begin a direct-to-cloud upload and receive presigned URLs for the file parts
- [Generate Upload Part URLs](https://docs.archetypeai.app/api-reference/files/generate-part-urls.md): Request fresh presigned URLs for specific parts of an in-progress upload
- [Checkpoint Upload Parts](https://docs.archetypeai.app/api-reference/files/checkpoint-parts.md): Persist part_tokens for completed parts so they can be skipped on resume
- [Complete Upload](https://docs.archetypeai.app/api-reference/files/complete-upload.md): Finalize a direct-to-cloud upload after all parts have been uploaded
- [Abort Upload](https://docs.archetypeai.app/api-reference/files/abort-upload.md): Abort an in-progress direct-to-cloud upload and clean up its resources
- [Create Fine-tuning Job](https://docs.archetypeai.app/api-reference/fine-tuning/create-job.md): Create a fine-tuning job
- [Get Fine-tuning Job Details](https://docs.archetypeai.app/api-reference/fine-tuning/get-job.md): Get a fine-tuning job by ID
- [List Fine-tuning Jobs](https://docs.archetypeai.app/api-reference/fine-tuning/list-jobs.md): List fine-tuning jobs (cursor-paginated, newest first)
- [Pause Fine-tuning Job](https://docs.archetypeai.app/api-reference/fine-tuning/pause-job.md): Pause a fine-tuning job
- [Resume Fine-tuning Job](https://docs.archetypeai.app/api-reference/fine-tuning/resume-job.md): Resume a paused or failed fine-tuning job
- [Cancel Fine-tuning Job](https://docs.archetypeai.app/api-reference/fine-tuning/cancel-job.md): Cancel a fine-tuning job
- [List Job Checkpoints](https://docs.archetypeai.app/api-reference/fine-tuning/list-job-checkpoints.md): Get a cursor-paginated list of checkpoints produced by the job
- [List Job Events](https://docs.archetypeai.app/api-reference/fine-tuning/list-job-events.md): List job-level events for the specified job, cursor-paginated, in chronological order
- [List Job Logs](https://docs.archetypeai.app/api-reference/fine-tuning/list-job-logs.md): Returns all events for the job, cursor-paginated, newest first
- [List Job Metrics](https://docs.archetypeai.app/api-reference/fine-tuning/list-job-metrics.md): Get per-step training and evaluation metrics for the job
- [List Checkpoint Options](https://docs.archetypeai.app/api-reference/fine-tuning/list-checkpoint-options.md): List checkpoints available to warm-start a new fine-tuning job
- [Create Job](https://docs.archetypeai.app/api-reference/batch/jobs/create-job.md): Create a new batch or training job
- [List Jobs](https://docs.archetypeai.app/api-reference/batch/jobs/list-jobs.md): Retrieve a paginated list of jobs with optional filters
- [Get Job](https://docs.archetypeai.app/api-reference/batch/jobs/get-job.md): Retrieve details of a specific job by ID
- [Retry Job](https://docs.archetypeai.app/api-reference/batch/jobs/retry-job.md): Retry a failed or cancelled job
- [Pause job](https://docs.archetypeai.app/api-reference/batch/jobs/pause-job.md): Pause an ongoing batch job
- [Resume Job](https://docs.archetypeai.app/api-reference/batch/jobs/resume-job.md): Resume a paused or interrupted job
- [Delete Job](https://docs.archetypeai.app/api-reference/batch/jobs/delete-job.md): Permanently delete a job and its associated data
- [Cancel Job](https://docs.archetypeai.app/api-reference/batch/jobs/cancel-job.md): Cancel a running or pending job
- [Get Queue Depths](https://docs.archetypeai.app/api-reference/batch/jobs/get-queue-depths.md): Retrieve global queue depths grouped by pipeline type
- [List Job Events](https://docs.archetypeai.app/api-reference/batch/events/list-job-events.md): Retrieve a paginated list of events for a specific job
- [List Inputs](https://docs.archetypeai.app/api-reference/batch/io/list-inputs.md): Retrieve a paginated list of inputs for a specific job
- [List Outputs](https://docs.archetypeai.app/api-reference/batch/io/list-outputs.md): Retrieve a paginated list of outputs for a specific job
- [List Inputs With Progress](https://docs.archetypeai.app/api-reference/batch/io/list-inputs-progress.md): Tracked inputs paired with their latest progress entry
- [Get Inputs Progress Counts](https://docs.archetypeai.app/api-reference/batch/io/get-inputs-progress-counts.md): Per-status counts of tracked inputs for a job
- [Get Inputs Progress Traces](https://docs.archetypeai.app/api-reference/batch/io/get-inputs-progress-traces.md): Bucketed cumulative file and per-kind item counters across the job lifetime
- [Validate Prospective Inputs](https://docs.archetypeai.app/api-reference/batch/io/validate-inputs.md): Validate the inputs for a prospective job without creating a job
- [List Job Progress](https://docs.archetypeai.app/api-reference/batch/progress/list-job-progress.md): Retrieve paginated progress entries for a specific job
- [List Pipelines](https://docs.archetypeai.app/api-reference/batch/registry/pipelines/list-pipelines.md): Retrieve a paginated list of pipelines from the registry
- [Get Pipeline](https://docs.archetypeai.app/api-reference/batch/registry/pipelines/get-pipeline.md): Retrieve details of a specific pipeline from the registry
- [Get Pipeline Schema](https://docs.archetypeai.app/api-reference/batch/registry/pipelines/get-pipeline-schema.md): Retrieve the configuration schema for a specific pipeline
- [Agent Skills](https://docs.archetypeai.app/for-agents/agent-skills.md): Use the official Archetype AI Agent Skills with your coding agent (Claude Code, Cursor, Codex, and others) to build on Newton faster.