# openvino - Doramagic AI Context Pack > Positioning: a pre-install experience and judgment asset. It helps the host AI get off to a good start, but it does not mean the project has already been installed, run, or validated. ## Sufficiency Principle - **Sufficiency over compression**: The AI Context Pack should be sufficient for the host AI to understand the project's value, capability boundaries, entrypoints, risks, and evidence sources before starting work; it may be layered, but it does not aim for the shortest possible summary. - **Compression policy**: Compress only noise and duplication, never context that affects judgment or the quality of the work. ## How the Host AI Should Use This You are reading the AI Context Pack that Doramagic compiled for openvino. Treat it as pre-work context: help the user understand who it fits, what it can do, how to start, what must be verified after install, and where the risks are. Do not claim that you have already installed, run, or executed the target project. ## Claim Consumption Rules - **Fact source**: Repo Evidence + Claim/Evidence Graph; the Human Wiki only supplies salience, terminology, and narrative structure. - **Minimum status for a fact**: `supported` - `supported`: May be used as a project fact, but the answer must cite the claim_id and evidence path. - `weak`: Usable only as a low-confidence lead; the user must be asked to keep verifying. - `inferred`: Usable only for risk notes or open questions; must not be packaged as a project fact. - `unverified`: Must not be used as fact; state clearly that evidence is insufficient. - `contradicted`: Must show the conflicting sources and must not force a single version on the user's behalf. ## Who It Fits Best - **Users who want to bring professional workflows into a host AI**: The repo contains Skill documents. Evidence: `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. Claim: `clm_0003` supported 0.86 ## What It Can Do - **AI Skill / Agent Instruction Asset Library** (Previewable before install): The project contains Skill or Agent instruction files that a host AI can read, useful for bringing professional workflows into hosts like Claude, Codex, or Cursor. Evidence: `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Command-Line Startup or Install Flow** (Verify after install): The project documentation contains runnable commands; real use requires running them in a local or host environment. Evidence: `README.md` Claim: `clm_0002` supported 0.86 ## How to Start - `pip install -U openvino` Evidence: `README.md` Claim: `clm_0004` supported 0.86 ## Continue-or-Stop Decision Card - **Current recommendation**: Sandbox trial only - **Why**: The project has signals of install commands, host configuration, or local writes; do not go straight into your primary environment—trial it in isolation first. ### 30-Second Read - **What to do now**: Sandbox trial only - **Minimum safe next step**: Run Prompt Preview first; if you still want to install, trial only in an isolated environment - **Do not trust yet**: Real output quality cannot be trusted before install. - **Continuing will touch**: Command execution, Host AI configuration, Local environment or project files ### What You Can Trust Now - **Target-audience signal: Users who want to bring professional workflows into a host AI** (supported): Backed by a supported claim or project evidence, but that still is not the same as real install results. Evidence: `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. Claim: `clm_0003` supported 0.86 - **Capability exists: AI Skill / Agent Instruction Asset Library** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Capability exists: Command-Line Startup or Install Flow** (supported): You can trust that the project contains signals of this capability; whether it fits your specific task still needs trial or after-install verification. Evidence: `README.md` Claim: `clm_0002` supported 0.86 - **There are Quick Start / install-command signals** (supported): You can trust that the docs mention a startup or install entrypoint; do not run it directly in your primary environment because of that. Evidence: `README.md` Claim: `clm_0004` supported 0.86 ### What You Cannot Trust Yet - **Real output quality cannot be trusted before install.** (unverified): Prompt Preview can only show how it guides you; it cannot prove result quality in the real project. - **Host AI version compatibility cannot be trusted before install.** (unverified): Host loading rules and version differences across Claude, Cursor, Codex, Gemini, and others must be verified in a real environment. - **That it will not pollute your existing host AI's behavior cannot be trusted directly.** (inferred): Skill, plugin, and AGENTS/CLAUDE/GEMINI instructions may change the host AI's default behavior. Evidence: `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. - **Safe rollback cannot be assumed by default.** (unverified): Unless the project clearly provides uninstall and recovery instructions, verify in an isolated environment first. - **After a real install, is it compatible with the user's current host AI version?** (unverified): Compatibility can only be verified in the actual host environment. - **Does the project's output quality meet the user's specific task?** (unverified): The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **Do the install commands require network access, permissions, or global writes?** (unverified): This affects install risk in both enterprise and personal environments. Evidence: `README.md` ### What Continuing Will Touch - **Command execution**: Package managers, network downloads, the local plugin directory, project config, or the user's home directory. Why: Running the very first command can already change your environment; decide whether it is worth running first. Evidence: `README.md` - **Host AI configuration**: The plugin, Skill, or rule-loading config of hosts like Claude/Codex/Cursor/Gemini/OpenCode. Why: Host configuration changes how the AI works afterward and may conflict with the user's existing rules. Evidence: `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. - **Local environment or project files**: Install results, plugin caches, project config, or local dependency directories. Why: The write scope and rollback path cannot be proven before install and need isolated verification. Evidence: `README.md` - **Host AI context**: The AI Context Pack, Prompt Preview, Skill routing, risk rules, and project facts. Why: Importing context affects the host AI's later judgment, so avoid packaging unverified items as facts. ### Minimum Safe Next Steps - **Run Prompt Preview first**: Use a pre-install interactive trial to judge whether the way of working fits; it needs no authorization or environment change. (applies when: Applies to any project, especially when output quality is unknown.) - **Trial-install only in an isolated directory or a test account**: Avoid letting install commands pollute your primary host AI, real projects, or home directory. (applies when: When there are signals of command execution, plugin config, or local writes.) - **Back up your host AI configuration first**: Skill, plugin, and rule files may change the default behavior of Claude/Cursor/Codex. (applies when: When there is a plugin manifest, a Skill, or a host rule entrypoint.) - **After install, verify just one minimal task**: Verify loading, compatibility, output quality, and rollback first, then decide whether to use it deeply. (applies when: When moving from a trial into a real workflow.) ### Exit Plan - **Preserve the pre-install state**: Record the original host config and project state so you can later judge whether it is recoverable. - **Be ready to remove the host plugin / Skill / rule entrypoint**: If behavior is off after the trial install, you can restore the host AI to its pre-trial state. - **Record the install commands and written paths**: Without clear uninstall instructions, you at least need to know which directories or configs to clean up manually. - **If there is no rollback path, do not enter your primary environment**: No rollback is a blocker before continuing; do not proceed on trust or luck. ## What Can Only Be Previewed - Explain who the project fits and what it can do - Demonstrate a typical conversation flow based on project docs - Help the user decide whether it is worth installing or researching further ## What Must Be Verified After Install - Actually installing the Skill, plugin, or CLI - Running scripts, modifying local files, or accessing external services - Verifying real output quality, performance, and compatibility ## Boundary & Risk Decision Card - **Mistaking the pre-install preview for a real run**: The user may overestimate how much configuration, permission, and compatibility verification the project has already done. Mitigation: Clearly separate prompt_preview_can_do from runtime_required. Claim: `clm_0005` inferred 0.45 - **Command execution will modify the local environment**: Install commands may write to the user's home directory, the host plugin directory, or project configuration. Mitigation: Run in an isolated environment or a test account first. Evidence: `README.md` Claim: `clm_0006` supported 0.86 - **To confirm**: After a real install, is it compatible with the user's current host AI version?. Why: Compatibility can only be verified in the actual host environment. - **To confirm**: Does the project's output quality meet the user's specific task?. Why: The pre-install preview can only show flow and boundaries; it cannot replace real evaluation. - **To confirm**: Do the install commands require network access, permissions, or global writes?. Why: This affects install risk in both enterprise and personal environments. ## Pre-Work Working Context ### Loading Order - First read how_to_use.host_ai_instruction to establish the boundaries of this pre-install judgment asset. - Read claim_graph_summary to confirm facts come from the Claim/Evidence Graph, not the Human Wiki narrative. - Then read intended_users, capabilities, and quick_start_candidates to judge whether the user is a match. - When you need to carry out a concrete task, check role_skill_index first, then evidence_index. - For real install, file modification, network access, performance, or compatibility questions, turn to risk_card and boundaries.runtime_required. ### Task Routes - **AI Skill / Agent Instruction Asset Library**: Use role_skill_index / evidence_index to help the user pick a usable role, Skill, or workflow first. Boundary: Can be experienced via a pre-install Prompt. Evidence: `.claude/skills/ov-debug/SKILL.md`, `.claude/skills/ov-debug-matcher-pass/SKILL.md`, `.claude/skills/ov-ensure-coding-style/SKILL.md`, `.claude/skills/ov-transformation-tests/SKILL.md` et al. Claim: `clm_0001` supported 0.86 - **Command-Line Startup or Install Flow**: State that this is an after-install capability first, then give a pre-install checklist. Boundary: Must be verified after a real install or run. Evidence: `README.md` Claim: `clm_0002` supported 0.86 ### Context Scale - Total files: 16061 - Important-file coverage: 40/16061 - Evidence index entries: 85 - Role / Skill entries: 5 ### Handling Insufficient Evidence - **missing_evidence**: State that evidence is insufficient and ask the user for the target file, a README section, or after-install verification records; do not fill in facts. - **out_of_scope_request**: State that the task is beyond the current AI Context Pack's evidence scope and suggest the user check the Human Manual or verify after a real install. - **runtime_request**: Provide a pre-install checklist and command sources, but do not run commands for the user or claim they have been run. - **source_conflict**: Show the conflicting sources side by side, mark them as unverified, and do not force a single version. ## Prompt Recipes ### Fit assessment - Goal: Judge whether this project fits the user's current task. - Expected output: A fit conclusion, key reasons, evidence citations, what can be previewed before install, what must be verified after install, and a next-step recommendation. ```text Based on the AI Context Pack for openvino, ask me 3 necessary questions first, then judge whether it fits my task. The answer must cover: who it fits, what it can do, what it cannot do, whether it is worth installing, and where the evidence comes from. Every project fact must cite evidence_refs, source_paths, or a claim_id. ``` ### Pre-install experience - Goal: Let the user feel the core workflow before installing, while avoiding packaging the preview as real capability or a marketing promise. - Expected output: An experience script with boundary labels, an after-install verification checklist, and a cautious recommendation; with no real-run promises or strong marketing language. ```text Treat openvino as a pre-install experience asset, not an already-installed tool or a real runtime environment. Output exactly four parts: 1. Ask me 3 necessary questions first. 2. Give an "experience script": use the three labels [Previewable before install], [Must verify after install], and [Insufficient evidence] to show how it might guide the workflow. 3. Give an after-install verification checklist: list which capabilities can only be confirmed after a real install, real host loading, and a real project run. 4. Give a cautious recommendation: only "worth researching/trialing further", "add information before deciding", or "not recommended to continue"; do not endorse the project. Hard boundaries: - Do not claim you have installed, run, executed tests, modified files, or produced real results. - Do not write promise-like phrasing such as "auto-adapts", "guarantees passing", "perfect fit", or "strongly recommend installing". - If you describe how it works after install, you must use a conditional such as "if installed successfully and the host loads the Skill correctly, it might...". - The experience script may only be written as "example lines / hypothetical flow": use "might ask / might suggest / might show", not "has written, has generated, has passed, is running, is generating". - Prompt Preview does not hand out install commands; if the user is ready to trial, only prompt them to read Quick Start and the Risk Card first and to verify in an isolated environment. - Every project fact must come from a supported claim, evidence_refs, or source_paths; inferred/unverified items can only be risks or open questions. ``` ### Role / Skill selection - Goal: Pick the best-matching asset from the project's roles or Skills. - Expected output: A list of candidate roles or Skills, each with an applicable scenario, evidence paths, risk boundary, and whether after-install verification is needed. ```text Read role_skill_index and recommend 3-5 of the most relevant roles or Skills for my target task. For each recommendation, state the applicable scenario, likely output, risk boundary, and evidence_refs. ``` ### Risk pre-check - Goal: Identify environment, permission, rule-conflict, and quality risks before installing or adopting. - Expected output: A checklist of environment, permission, dependency, license, host-conflict, quality risk, and unknown items. ```text Based on risk_card, boundaries, and quick_start_candidates, give me a pre-install risk pre-check list. Do not run commands for me; only explain what I should check, why, and what impact a failure would have. ``` ### Host AI kickoff instruction - Goal: Turn the project context into a host AI instruction for the start of a conversation. - Expected output: A pre-work instruction with clear boundaries and clear evidence citations, suitable to copy to a host AI. ```text Based on the AI Context Pack for openvino, generate a pre-work instruction I can paste to my host AI. This instruction must obey not_runtime=true and must not claim the project has been installed, run, or produced real results. ``` ## Role / Skill Index - Indexed 5 role / Skill / project-doc entries. - **ov-debug-matcher-pass** (skill): Activation hint: When the user's task is highly relevant to the workflow described by “ov-debug-matcher-pass”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/ov-debug-matcher-pass/SKILL.md` - **ov-debug** (skill): Troubleshooting all sorts of failures, crashes, exceptions and errors using debug capabilities. Analyze accuracy, performance, model compilation, or memory issues. Dump tensors and intermediate blobs. Serialize and visualize IRs, execution graphs. Enable verbose, logging. Profile execution. Compare layer outputs. Inspect, trace or dump transformations. Identify executed operations, nodes, primitives, kernels. Activation hint: When the user's task is highly relevant to the workflow described by “ov-debug”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/ov-debug/SKILL.md` - **ov-ensure-coding-style** (skill): Detect and fix clang-format, clang-tidy, and copyright header violations in an OpenVINO C++ codebase. Use when the user complains about code style or formatting, asks to clean up changes, fix linting, add a copyright header, or when a style check or linting CI job is failing. Do not use for build errors, compilation failures, linker errors, test failures, runtime crashes, accuracy issues, or CMake config problems. Activation hint: When the user's task is highly relevant to the workflow described by “ov-ensure-coding-style”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/ov-ensure-coding-style/SKILL.md` - **ov-transformation-tests** (skill): Activation hint: When the user's task is highly relevant to the workflow described by “ov-transformation-tests”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/ov-transformation-tests/SKILL.md` - **ov-update-pytorch-version** (skill): Upgrade the PyTorch version used by OpenVINO tests torch / torchvision / torchaudio and resolve fallout — missing operator translators, new functionalized copy aten ops, decomposition changes, FX-only tests failing in TorchScript mode, and accuracy regressions caused by stricter typing. Use when the user asks to "bump torch", "update pytorch to X.Y", "upgrade torch tests", or when pytorch tests / model hub pytorch t… Activation hint: When the user's task is highly relevant to the workflow described by “ov-update-pytorch-version”, use it for a pre-install experience first, then decide whether to install. Evidence: `.claude/skills/ov-update-pytorch-version/SKILL.md` ## Evidence Index - Indexed 85 evidence entries. - **Explanation** (documentation): architecture inference runtime configuration manifests cli robots cameras Evidence: `docs/articles_en/physical-ai/explanation/README.md` - **Getting Started** (documentation): installation quickstart run-a-policy Evidence: `docs/articles_en/physical-ai/getting-started/README.md` - **How-To Guides** (documentation): runtime/run-policy-on-robot runtime/use-execution-modes runtime/add-runtime-callbacks inference/load-exported-policy inference/use-manifest inference/configure-pre-post-processing config/write-runtime-config config/write-inference-config config/instantiate-components cli/run Evidence: `docs/articles_en/physical-ai/how-to/README.md` - **Reference** (documentation): cli config-schema manifest-schema inference-api runtime-api robot-api camera-api benchmark-api Evidence: `docs/articles_en/physical-ai/reference/README.md` - **openvino sphinx theme** (documentation): 1. Install the openvino sphinx theme using python : Evidence: `docs/openvino_sphinx_theme/README.md` - **OpenVINO™ JavaScript Bindings** (documentation): - ./docs ../docs/ - documentation - ./node ../node/ - openvino-node npm package Evidence: `src/bindings/js/docs/README.md` - **Debug capabilities** (documentation): Debug capabilities Debug capabilities are the set of useful debug features, most of them are controlled by environment variables. Evidence: `src/common/snippets/docs/debug_capabilities/README.md` - **Transformations documentation** (documentation): Writing transformation tests ./writing tests.md Evidence: `src/common/transformations/docs/README.md` - **Debug capabilities** (documentation): Debug capabilities Debug capabilities are the set of useful debug features for OpenVINO transformations, controlled by environment variables. Evidence: `src/common/transformations/docs/debug_capabilities/README.md` - **Debug capabilities** (documentation): Debug capabilities Debug capabilities are the set of useful debug features, controlled by environment variables. Evidence: `src/plugins/intel_cpu/docs/debug_capabilities/README.md` - **Installation** (documentation): Open-source software toolkit for optimizing and deploying deep learning models. Evidence: `README.md` - **OpenVINO™ Core Components** (documentation): This section provides references and information about OpenVINO core components. Evidence: `src/README.md` - **OpenVINO™ Python development tools** (documentation): General OpenVINO includes following tools: openvino.tools.benchmark Evidence: `tools/README.md` - **Hello Classification C Sample** (documentation): This sample demonstrates how to execute an inference of image classification networks like AlexNet and GoogLeNet using Synchronous Inference Request API and input auto-resize feature. Evidence: `samples/c/hello_classification/README.md` - **Hello NV12 Input Classification C Sample** (documentation): Hello NV12 Input Classification C Sample Evidence: `samples/c/hello_nv12_input_classification/README.md` - **Sync Benchmark C++ Sample** (documentation): This sample demonstrates how to estimate performance of a model using Synchronous Inference Request API. It makes sense to use synchronous inference only in latency oriented scenarios. Models with static input shapes are supported. Unlike demos https://github.com/openvinotoolkit/open model zoo/tree/master/demos this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. Evidence: `samples/cpp/benchmark/sync_benchmark/README.md` - **Throughput Benchmark C++ Sample** (documentation): This sample demonstrates how to estimate performance of a model using Asynchronous Inference Request API in throughput mode. Unlike demos https://github.com/openvinotoolkit/open model zoo/tree/master/demos this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. Evidence: `samples/cpp/benchmark/throughput_benchmark/README.md` - **Benchmark C++ Tool** (documentation): This page demonstrates how to use the Benchmark C++ Tool to estimate deep learning inference performance on supported devices. Evidence: `samples/cpp/benchmark_app/README.md` - **Image Classification Async C++ Sample** (documentation): Image Classification Async C++ Sample Evidence: `samples/cpp/classification_sample_async/README.md` - **Hello Classification C++ Sample** (documentation): This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API. Evidence: `samples/cpp/hello_classification/README.md` - **Hello NV12 Input Classification C++ Sample** (documentation): Hello NV12 Input Classification C++ Sample Evidence: `samples/cpp/hello_nv12_input_classification/README.md` - **Hello Query Device C++ Sample** (documentation): This sample demonstrates how to execute an query OpenVINO™ Runtime devices, prints their metrics and default configuration values, using Properties API https://docs.openvino.ai/2026/openvino-workflow/running-inference/inference-devices-and-modes/query-device-properties.html . Evidence: `samples/cpp/hello_query_device/README.md` - **Hello Reshape SSD C++ Sample** (documentation): This sample demonstrates how to do synchronous inference of object detection models using input reshape feature https://docs.openvino.ai/2026/openvino-workflow/running-inference/model-input-output/changing-input-shape.html . Models with only one input and output are supported. Evidence: `samples/cpp/hello_reshape_ssd/README.md` - **Model Creation C++ Sample** (documentation): This sample demonstrates how to execute an synchronous inference using model https://docs.openvino.ai/2026/openvino-workflow/running-inference/model-representation.html built on the fly which uses weights from LeNet classification model, which is known to work well on digit classification tasks. Evidence: `samples/cpp/model_creation_sample/README.md` - **OpenVINO™ Node.js Bindings Examples of Usage** (documentation): OpenVINO™ Node.js Bindings Examples of Usage Evidence: `samples/js/node/README.md` - **Benchmark Information** (documentation): The benchmarks in this folder were tested using single input models with FP32 precision on the following models: - mobilenet-v3-small-1.0-224-tf https://docs.openvino.ai/2023.3/omz models model mobilenet v3 small 1 0 224 tf.html - text-recognition-resnet-fc https://github.com/openvinotoolkit/open model zoo/blob/master/models/public/text-recognition-resnet-fc/README.md - Multiclass Selfie-segmentation model https://ai.google.dev/edge/mediapipe/solutions/vision/image segmenter multiclass-model Evidence: `samples/js/node/benchmark/README.md` - **Image Classification Async Node.js Sample** (documentation): Image Classification Async Node.js Sample Evidence: `samples/js/node/classification_sample_async/README.md` - **Hello Classification Node.js Sample** (documentation): Hello Classification Node.js Sample Evidence: `samples/js/node/hello_classification/README.md` - **Hello Reshape SSD Node.js Sample** (documentation): Models with only 1 input and output are supported. Evidence: `samples/js/node/hello_reshape_ssd/README.md` - **Optical Character Recognition Node.js Sample** (documentation): Optical Character Recognition Node.js Sample Evidence: `samples/js/node/optical_character_recognition/README.md` - **Vision Background Removal Node.js Sample** (documentation): Vision Background Removal Node.js Sample Evidence: `samples/js/node/vision_background_removal/README.md` - **Bert Benchmark Python Sample** (documentation): This sample demonstrates how to estimate performance of a Bert model using Asynchronous Inference Request API. Unlike demos https://github.com/openvinotoolkit/open model zoo/tree/master/demos this sample doesn't have configurable command line arguments. Feel free to modify sample's source code to try out different options. Evidence: `samples/python/benchmark/bert_benchmark/README.md` - **Sync Benchmark Python Sample** (documentation): This sample demonstrates how to estimate performance of a model using Synchronous Inference Request API. It makes sense to use synchronous inference only in latency oriented scenarios. Models with static input shapes are supported. Unlike demos https://github.com/openvinotoolkit/open model zoo/tree/master/demos this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. Evidence: `samples/python/benchmark/sync_benchmark/README.md` - **Throughput Benchmark Python Sample** (documentation): This sample demonstrates how to estimate performance of a model using Asynchronous Inference Request API in throughput mode. Unlike demos https://github.com/openvinotoolkit/open model zoo/tree/master/demos this sample doesn't have other configurable command line arguments. Feel free to modify sample's source code to try out different options. Evidence: `samples/python/benchmark/throughput_benchmark/README.md` - **Image Classification Async Python Sample** (documentation): Image Classification Async Python Sample Evidence: `samples/python/classification_sample_async/README.md` - **Hello Classification Python Sample** (documentation): This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API. Evidence: `samples/python/hello_classification/README.md` - **Hello Query Device Python Sample** (documentation): This sample demonstrates how to show OpenVINO™ Runtime devices and prints their metrics and default configuration values using Query Device API feature https://docs.openvino.ai/2026/openvino-workflow/running-inference/inference-devices-and-modes/query-device-properties.html . Evidence: `samples/python/hello_query_device/README.md` - **Hello Reshape SSD Python Sample** (documentation): This sample demonstrates how to do synchronous inference of object detection models using Shape Inference feature https://docs.openvino.ai/2026/openvino-workflow/running-inference/model-input-output/changing-input-shape.html . Evidence: `samples/python/hello_reshape_ssd/README.md` - **Model Creation Python Sample** (documentation): This sample demonstrates how to run inference using a model https://docs.openvino.ai/2026/openvino-workflow/running-inference/model-representation.html built on the fly that uses weights from the LeNet classification model, which is known to work well on digit classification tasks. You do not need an XML file, the model is created from the source code on the fly. Evidence: `samples/python/model_creation_sample/README.md` - **OpenVINO Bindings** (documentation): OpenVINO provides bindings for several languages: Evidence: `src/bindings/README.md` - **OpenVINO C API** (documentation): OpenVINO C API is a key part of the OpenVINO extension for C API users. This component provides C API for OpenVINO Toolkit. Evidence: `src/bindings/c/README.md` - **OpenVINO™ JavaScript API** (documentation): - ./node ./node - openvino-node npm package with OpenVINO Node.js bindings Evidence: `src/bindings/js/README.md` - **OpenVINO™ for Node.js** (documentation): ! OpenVINO logo https://github.com/openvinotoolkit/openvino/blob/master/docs/dev/assets/openvino-logo-purple-black.svg?raw=1 Evidence: `src/bindings/js/node/README.md` - **OpenVINO Python API** (documentation): OpenVINO Python API is a part of the OpenVINO library. The component is responsible for: Evidence: `src/bindings/python/README.md` - **Torchvision to OpenVINO preprocessing converter** (documentation): Torchvision to OpenVINO preprocessing converter Evidence: `src/bindings/python/src/openvino/preprocess/README.md` - **OpenVINO Conditional Compilation** (documentation): OpenVINO Conditional Compilation CC feature can significantly optimize OpenVINO™ binaries size by excluding unnecessary code regions with ITT profiler, especially when building an application with a static OpenVINO package. Evidence: `src/common/conditional_compilation/README.md` - **Snippets** (documentation): For assistance regarding snippets, contact a member of openvino-ie-cpu-maintainers https://github.com/orgs/openvinotoolkit/teams/openvino-ie-cpu-maintainers group. Evidence: `src/common/snippets/README.md` - **OpenVINO Level Zero loader** (documentation): OpenVINO Level Zero loader aims to unify Level Zero loading logic across multiple plugins. Evidence: `src/common/zero_loader/README.md` - **OpenVINO™ Core** (documentation): OpenVINO Core is a part of OpenVINO Runtime library. The component is responsible for: Model representation - component provides classes for manipulation with models inside the OpenVINO Runtime. For more information please read Model representation in OpenVINO Runtime User Guide https://docs.openvino.ai/2026/openvino-workflow/running-inference/model-representation.html Operation representation - contains all from the box supported OpenVINO operations and opsets. For more information read Operations enabling flow guide ./docs/operation enabling flow.md . Model modification - component provides base classes which allow to develop transformation passes for model modification. For more informat… Evidence: `src/core/README.md` - **OpenVINO Frontends** (documentation): OpenVINO Frontends allow converting models from the native framework to OpenVINO representation. Evidence: `src/frontends/README.md` - **OpenVINO IR Frontend** (documentation): openvino openvino library ir--Read ir---ir fe ir fe--Create ov::Model--- openvino click ir "https://docs.openvino.ai/2026/documentation/openvino-ir-format/operation-sets.html" Evidence: `src/frontends/ir/README.md` - **OpenVINO ONNX Frontend** (documentation): The main responsibility of the ONNX Frontend is to import ONNX models and convert them into the ov::Model representation. Other capabilities of the ONNX Frontend: modification of tensors properties like data type and shapes changing the topology of models like cutting subgraphs, inserting additional inputs and outputs searching the models in a user-friendly way via tensors and operators names Evidence: `src/frontends/onnx/README.md` - **OpenVINO™ Paddle Frontend** (documentation): OpenVINO Paddle Frontend is one of the OpenVINO Frontend libraries created for the Baidu PaddlePaddle™ framework. The component is responsible for: Paddle Reader - reads a PaddlePaddle protobuf model and parses it to the frontend InputModel. Learn more about Paddle Frontend architecture. ./docs/paddle frontend architecture.md . Paddle Converter - decodes a PaddlePaddle model and operators and maps them semantically to the OpenVINO opset. Learn more about the operator mapping flow. ./docs/operation mapping flow.md . Evidence: `src/frontends/paddle/README.md` - **OpenVINO PyTorch Frontend** (documentation): The PyTorch Frontend PT FE is a C++ based OpenVINO Frontend component that is responsible for reading and converting a PyTorch model to an ov::Model object that can be further serialized into the Intermediate Representation IR format. Evidence: `src/frontends/pytorch/README.md` - **OpenVINO TensorFlow Frontend** (documentation): The TensorFlow Frontend TF FE is a C++ based OpenVINO Frontend component that is responsible for reading and converting a TensorFlow model to an ov::Model object that further can be serialized into the Intermediate Representation IR format. This is an internal API for OpenVINO that is used to implement user-facing API such as OVC tool, Model Conversion API, and OpenVINO Runtime read model function for reading TensorFlow models of the original format in run-time. Also, OpenVINO Model Server uses the frontend for serving models. Regular users should not use the frontend directly. Evidence: `src/frontends/tensorflow/README.md` - **OpenVINO™ Inference** (documentation): OpenVINO Inference is a part of the OpenVINO Runtime library. The component is responsible for model inference on hardware devices and provides API for OpenVINO Plugin development. Evidence: `src/inference/README.md` - **OpenVINO Plugins** (documentation): OpenVINO Plugins provide support for hardware devices. Evidence: `src/plugins/README.md` - **OpenVINO™ AUTO Plugin** (documentation): The main responsibility of the AUTO plugin is to provide a unified device that enables developers to code deep learning applications once and deploy them anywhere. Evidence: `src/plugins/auto/README.md` - **OpenVINO Hetero Plugin Design Overview** (documentation): OpenVINO Hetero Plugin Design Overview Evidence: `src/plugins/hetero/README.md` - **OpenVINO Intel CPU Plugin** (documentation): For assistance regarding CPU, contact a member of openvino-ie-cpu-maintainers group. Evidence: `src/plugins/intel_cpu/README.md` - The remaining 25 evidence entries are in `AI_CONTEXT_PACK.json` or `EVIDENCE_INDEX.json`. ## Rules the Host AI Must Follow - **Treat this asset as pre-work context, not a runtime environment.**: The AI Context Pack contains only an evidence-backed understanding of the project, not the project's executable state. Evidence: `docs/articles_en/physical-ai/explanation/README.md`, `docs/articles_en/physical-ai/getting-started/README.md`, `docs/articles_en/physical-ai/how-to/README.md` - **When answering the user, distinguish what can be previewed from what can only be verified after install.**: The consumer value of the pre-install experience comes from reducing bad installs and misjudgments, not from pretending to be a real run. Evidence: `docs/articles_en/physical-ai/explanation/README.md`, `docs/articles_en/physical-ai/getting-started/README.md`, `docs/articles_en/physical-ai/how-to/README.md` ## Questions the User Should Answer First - Which host AI or local environment do you plan to use it in? - Do you just want to experience the workflow first, or are you ready to actually install? - What matters most to you: install cost, output quality, or conflicts with your existing rules? ## Acceptance Checks - Every capability claim can be traced back to a file path in evidence_refs. - AI_CONTEXT_PACK.md does not package previews as a real run. - The user can understand who it fits, what it can do, how to start, and the risk boundaries within 3 minutes. --- ## Doramagic Context Augmentation The following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints. ## Human Manual Outline Usage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph. Host AI hard rules: - Do not treat page titles, section order, summaries, or importance values as factual project evidence. - When explaining the Human Manual outline, state that it is only a reading route or salience signal. - Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph. - **Overview, Installation & Quick Start**: importance `high` - source_paths: README.md, setup.py, src/bindings/python/setup.cfg, src/bindings/python/constraints.txt, src/bindings/python/README.md - **Core Library, Opsets & OpenVINO IR Format**: importance `high` - source_paths: src/core/README.md, src/core/include/openvino/core/model.hpp, src/core/include/openvino/core/node.hpp, src/core/include/openvino/opsets/opset1.hpp, src/core/include/openvino/opsets/opset17.hpp - **Model Frontends & Conversion Pipelines**: importance `high` - source_paths: src/bindings/python/src/openvino/frontend/pytorch/__init__.py, src/bindings/python/src/openvino/frontend/pytorch/torchdynamo/backend.py, src/bindings/python/src/openvino/frontend/pytorch/fx_decoder.py, src/bindings/python/src/openvino/frontend/pytorch/ov_custom_ops.py, src/bindings/python/src/openvino/frontend/pytorch/inlined_extension.py - **Inference Runtime, Device Plugins & Deployment**: importance `high` - source_paths: src/bindings/python/src/openvino/_ov_api.py, src/bindings/python/src/openvino/_pyopenvino/__init__.pyi, src/bindings/c/include/openvino/c/openvino.h, src/bindings/c/src/ov_core.cpp, src/bindings/js/node/include/core_wrap.hpp ## Repo Inspection Evidence - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `f7a1b8249a9f803c7bda4b9fb05e9bdbf00f919c` - inspected_files: `README.md`, `pyproject.toml`, `docs/RELEASE.MD`, `docs/articles_en/assets/snippets/Bfloat16Inference.py`, `docs/articles_en/assets/snippets/ShapeInference.py`, `docs/articles_en/assets/snippets/__init__.py`, `docs/articles_en/assets/snippets/compile_model_cpu.py`, `docs/articles_en/assets/snippets/compile_model_npu.py`, `docs/articles_en/assets/snippets/dynamic_shape.py`, `docs/articles_en/assets/snippets/export_compiled_model.py`, `docs/articles_en/assets/snippets/gpu/compile_model_gpu.py`, `docs/articles_en/assets/snippets/gpu/custom_kernels_api.py`, `docs/articles_en/assets/snippets/gpu/dynamic_batch.py`, `docs/articles_en/assets/snippets/gpu/preprocessing_nv12_two_planes.py`, `docs/articles_en/assets/snippets/main.py`, `docs/articles_en/assets/snippets/multi_threading.py`, `docs/articles_en/assets/snippets/ov_auto.py`, `docs/articles_en/assets/snippets/ov_auto_batching.py`, `docs/articles_en/assets/snippets/ov_caching.py`, `docs/articles_en/assets/snippets/ov_custom_op.py` Host AI hard rules: - Without repo_clone_verified=true, do not claim that the source code has been read. - Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts. - Without quick_start_verified=true, do not claim that the Quick Start path has run successfully. ## Doramagic Pitfall Constraints These rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes. ### Constraint 1: Capability evidence risk requires verification - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: capability.assumptions | https://github.com/openvinotoolkit/openvino - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 2: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: downstream_validation.risk_items | https://github.com/openvinotoolkit/openvino - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 3: Security or permission risk requires verification - Trigger: no_demo - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: risks.scoring_risks | https://github.com/openvinotoolkit/openvino - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 4: Maintenance risk requires verification - Trigger: issue_or_pr_quality=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/openvinotoolkit/openvino - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it. ### Constraint 5: Maintenance risk requires verification - Trigger: release_recency=unknown。 - Host AI rule: Reproduce the official install and quickstart path in an isolated environment. - Why it matters: May increase setup, validation, or first-run risk for the user. - Evidence: evidence.maintainer_signals | https://github.com/openvinotoolkit/openvino - Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.