[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-aws-amazon-braket":3,"mdc-s4argl-key":32,"related-repo-aws-amazon-braket":1784,"related-org-aws-amazon-braket":1890},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":21,"repoUrl":22,"updatedAt":23,"license":24,"forks":25,"topics":26,"repo":27,"sourceUrl":30,"mdContent":31},"amazon-braket","run quantum computing workflows on AWS","Runs quantum computing workflows on AWS through Amazon Braket — discovering devices (QPUs and simulators) and their availability, building gate-model circuits and analog Hamiltonian programs, submitting quantum tasks, program sets and hybrid jobs, looking up prices, and capping spend with spending limits. Applies to any request about quantum computing, quantum hardware, quantum simulation, AHS, OpenQASM, or running a quantum algorithm on AWS.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"aws","AWS (Amazon)","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Faws.png",[12,16,18],{"name":13,"slug":14,"type":15},"Simulation","simulation","tag",{"name":17,"slug":8,"type":15},"AWS",{"name":19,"slug":20,"type":15},"Quantum Computing","quantum-computing",1822,"https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws","2026-08-20T03:53:19.377174",null,157,[],{"repoUrl":22,"stars":21,"forks":25,"topics":28,"description":29},[],"Official, AWS-supported MCP servers, skills, and plugins to help AI agents build on AWS","https:\u002F\u002Fgithub.com\u002Faws\u002Fagent-toolkit-for-aws\u002Ftree\u002FHEAD\u002Fskills\u002Fspecialized-skills\u002Fquantum-computing-skills\u002Famazon-braket","---\nname: amazon-braket\ndescription: Runs quantum computing workflows on AWS through Amazon Braket — discovering devices (QPUs and simulators) and their availability, building gate-model circuits and analog Hamiltonian programs, submitting quantum tasks, program sets and hybrid jobs, looking up prices, and capping spend with spending limits. Applies to any request about quantum computing, quantum hardware, quantum simulation, AHS, OpenQASM, or running a quantum algorithm on AWS.\nmetadata:\n  version: \"1\"\n---\n\n# Amazon Braket\n\n## Primitives\n\nThe vocabulary of a Braket workflow, and which reference to open for each.\n\n| Primitive | What it is | Related References | Open it when the request involves |\n|---|---|---|---|\n| **Device** | A simulator or QPU, identified by a region-scoped ARN | [devices.md](references\u002Fdevices.md) | anything about a device: what exists, discovering or filtering the fleet, availability and status (online, offline, retired), which region a device lives in, ARNs, choosing a device for a workload, qubit count, connectivity or topology, native gates, fidelities, calibration data, queue depth, shot and gate limits, paradigm (gate-model vs analog Hamiltonian simulation), whether a device supports program sets, pulse-level control, simulators and local emulators |\n| **Program** | The workload\u002Finput — one executable (Circuit, AHS, OpenQASM). Which type is legal depends on the device's paradigm | - | - |\n| **Quantum task** | One program + shots, run once (the atomic unit Braket meters) | - | - |\n| **Task batch** | Many *independent* tasks — SDK-only fallback for when a program set does not fit; works on all devices | [program-sets.md](references\u002Fprogram-sets.md) | see the Program set row; also [running multiple programs](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-batching-tasks.html) |\n| **Program set** | Many programs in **one service-side task** — preferred way to run multiple programs instead of task batch | [program-sets.md](references\u002Fprogram-sets.md) | running more than one program: parameter sweeps, scanning parameter values, task batches, `run_batch`, several circuits submitted together, attaching observables across programs, and minimizing per-task fees when many programs run, program sets. Also [getting started with program sets](https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-examples\u002Fblob\u002Fmain\u002Fexamples\u002Fbraket_features\u002Fprogram_sets\u002F01_Getting_started_with_program_sets.ipynb) |\n| **Hybrid job** | Managed classical-quantum loop that orchestrates many tasks | [hybrid-job.md](references\u002Fhybrid-job.md) | hybrid jobs: `@hybrid_job`, algorithm scripts and source modules, `entry_point`, embedded simulators, BYOC and custom container images, CUDA-Q, job execution roles, hyperparameters, checkpoints, and retrieving job results |\n| **Spending limit** | Service-side hard cap that **rejects** QPU tasks — the only true enforcement (not SDK) | [spending-limit.md](references\u002Fspending-limit.md) | capping or enforcing spend: spending limits (create, update, delete, search), and cost guardrails |\n| **Cost tracking** | In-session cost *estimate* (not enforcement) | [spending-limit.md](references\u002Fspending-limit.md) | in-session cost tracking with `Tracker` |\n\nEach reference carries the domain detail for its own area — field paths, key names, API shapes, and billing models.\n\nAdditional notes:\n- **Reservation** — exclusive device access for a booked window. This skill covers reservations at pointer depth only: the billing model is in [pricing.md](references\u002Fpricing.md), reservation-specific device limits such as `service.reservationShotsRange` are in [devices.md](references\u002Fdevices.md), and the full model is in the [reservations developer guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-reservations.html).\n- **Gate calibrations \u002F pulse control** — access native gate calibrations on QPUs and attach custom pulse sequences at run time. See [devices.md](references\u002Fdevices.md) for detecting support, and the [pulse control developer guide](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-pulse-control.html) for the full model.\n\n## Critical Rules\n\nThese rules apply to every Braket request, whatever it involves.\n\n1. **The Amazon Braket Python SDK (`pip install amazon-braket-sdk`, imported as `braket`) is the primary entry point.** Prefer it for every operation including Braket API operations, and understand what it covers by reading the [docs](https:\u002F\u002Famazon-braket-sdk-python.readthedocs.io\u002Fen\u002Fstable\u002F) or inspecting the SDK's modules locally.\n    - Use local execution tools for running the Braket SDK, such as `shell` with `python3 -c \"\u003Ccode>\"`.\n\n1. **The AWS MCP server is recommended for executing any other AWS API calls in this skill**, especially operations not present in the Python SDK, although not required. Note: the AWS MCP's `run_script` tool executes code in a minimal sandbox without Braket libraries, so prefer using other tools for code execution, especially when using the Braket SDK.\n\n1. **A small set of primitives composes every workflow** — see [Primitives](#primitives) for the vocabulary and the reference for each.\n\n1. **Devices, quantum tasks, and hybrid jobs are region-scoped, so fan out across every Braket region whenever you use the API, CLI, or boto3 to search for resources.** The SDK handles fanout for you where it can — `AwsDevice.get_devices` searches QPUs in all regions.\nGet the list of regions Braket supports from `aws___get_regional_availability` when the AWS MCP server is available, or from the [supported devices and regions documentation](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-devices.html).\nResource ARNs containing a region may only be queried from that same region, otherwise you will see a `ResourceNotFoundException`.\n\n1. **Open the matching reference before you write code or answer.** Use the **Primitives** table to find and read references. Note: A request that asks for several things, e.g. executing a series of circuits and controlling the cost thereof, may require reading multiple reference files.\n\n1. **Verify, never recall.** Device ARNs and statuses, API signatures, supported features, and prices (and other values) all change and may post-date training data.\n\n1. **Confirm an SDK signature before you write code that calls it.** Read it from the [SDK reference docs](https:\u002F\u002Famazon-braket-sdk-python.readthedocs.io\u002Fen\u002Flatest\u002F).\nIf no available tool can reach them, get it from the installed SDK with `shell`:\n```bash\nPAGER=cat python -c \"import braket; help(braket)\"       # subpackages: ahs, circuits, pulse, program_sets, ...\npython -c \"import braket.ahs; print(dir(braket.ahs))\"   # names: DrivingField, AtomArrangement, ...\npython -c \"import inspect; from braket.ahs import DrivingField; \\\nprint(inspect.signature(DrivingField.from_lists)); print(inspect.getdoc(DrivingField.from_lists))\"\n```\n\n\n## Guardrail — where this skill's own files live (MCP vs local install)\n\nThis skill can be loaded two ways, and they resolve the skill's own bundled files from different places. Determine how the skill was loaded before reading a reference:\n\n- **Loaded through the AWS MCP `retrieve_skill` tool:** The skill is not installed on the local filesystem. You MUST fetch each reference via `retrieve_skill` with the `file` parameter (e.g. `file=\"references\u002Fdevices.md\"`). Do NOT `file_read` these paths locally — they do not exist on disk.\n- **Installed locally** (e.g. `~\u002F.kiro\u002Fskills\u002Famazon-braket\u002F`, `.kiro\u002Fskills\u002Famazon-braket\u002F`, or `~\u002F.claude\u002Fskills\u002Famazon-braket\u002F`): Read files from the local skill directory using relative paths.\n\n`references\u002F` is a sibling of this `SKILL.md` — resolve reference paths against that directory, not your working directory, and do not search the filesystem for them.\nIf a skill tool returns this overview instead of the file you asked for, it did not fetch it: read it from that directory instead, and do not write code from memory because a reference read failed.\nThis distinction applies only to the skill's own packaged files. User data and session artifacts are always read from and written to the user's working directory — do not `cd` before running a script that writes a relative artifact path.\n\n\n## Common mistakes\n\n| Symptom | Cause | Fix |\n|---|---|---|\n| Treats \"task\", \"batch\", \"job\" as interchangeable | Primitive confusion | Task = one run; batch = many parallel tasks; job = managed loop |\n| `Missing required parameter: filters` on `SearchQuantumTasks`, `SearchJobs`, or `SearchDevices` | `filters` is required on all three — only `SearchSpendingLimits` lets you omit it | Pass `filters=[]` (`--filters '[]'`) for an unfiltered search. A populated filter needs `name` and `values`, plus `operator` on tasks and jobs; `SearchDevices` has no `operator` member |\n| `Missing required parameter: clientToken` when using AWS MCP `run_script` tool | `CreateQuantumTask`, `CreateJob`, `CancelQuantumTask`, `CreateSpendingLimit`, `UpdateSpendingLimit` require a `clientToken` for idempotency. The SDK, CLI, and boto3 generate one automatically; the `run_script` tool requires explicit passing | Pass `clientToken=str(uuid.uuid4())` on APIs taking `clientToken` when calling through `run_script`. Otherwise, prefer the SDK for these operations when possible. |\n| Builds program IR as JAQCD | JAQCD is deprecated on Amazon Braket | Use OpenQASM — see [OpenQASM on Braket](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-openqasm.html) |\n| Denies a feature or SDK construct exists | Training data outdated | Rule 2 — verify against the docs or `GetDevice` before saying it does not exist |\n| Invents a class, method, or parameter | Writing API names from memory | Confirm the signature first (rule 4). If uncertain, say so rather than inventing |\n\n## Security considerations\n\nBraket workflows touch IAM, S3, and (for hybrid jobs) container execution.\n\n- **Least-privilege IAM.** Scope custom policies to the actions, device ARNs, and buckets a workload actually uses, and avoid broad `braket:*`. Actions are listed at the [Service Authorization Reference](https:\u002F\u002Fdocs.aws.amazon.com\u002Fservice-authorization\u002Flatest\u002Freference\u002Flist_braket.html). Prefer a custom policy over `AmazonBraketFullAccess`, which is deliberately broad: S3 on any `amazon-braket-*` bucket or any bucket tagged `AmazonBraket=true` ([if the bucket is enabled for Attribute-Based Access Control](https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonS3\u002Flatest\u002Fuserguide\u002Fbuckets-tagging-enable-abac.html)), plus SageMaker and CloudWatch actions a task-submission workflow never needs. See [Managing access to Amazon Braket](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-manage-access.html) and [Restricting access to devices](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Frestrict-access.html).\n  - `braket:UpdateSpendingLimit` and `braket:DeleteSpendingLimit` should be restricted to prevent accidental removal of a spending limit and accidental cost overruns.\n- **Hybrid-job execution role.** Attach only [`AmazonBraketJobsExecutionPolicy`](https:\u002F\u002Fdocs.aws.amazon.com\u002Faws-managed-policy\u002Flatest\u002Freference\u002FAmazonBraketJobsExecutionPolicy.html). Its `iam:PassRole` condition requires the role be named `AmazonBraketJobsExecutionRole*` under the `\u002Fservice-role\u002F` path, or `create_job` is denied at `PassRole`.\n- **Ephemeral credentials.** Call Braket APIs with IAM roles (instance profiles, ECS\u002FEKS task roles, or assumed roles), not long-lived IAM user access keys.\n- **Encrypt task output.** Enable default encryption (SSE-S3, or SSE-KMS with a customer-managed key for sensitive workloads) on any S3 bucket receiving task results, job source archives, output data, or checkpoints. Add `aws:SourceAccount`\u002F`aws:SourceArn` conditions to the bucket policy where a service principal is granted access, and deny non-TLS access with an `aws:SecureTransport: false` condition.\n- **Auditing.** Enable [CloudTrail](https:\u002F\u002Fdocs.aws.amazon.com\u002Fawscloudtrail\u002Flatest\u002Fuserguide\u002Fview-cloudtrail-events.html) for Braket management events, with log-file validation, KMS encryption, and delivery to an access-restricted bucket — the trail is the primary evidence if a cost guardrail is removed. Encrypt any CloudWatch Logs group receiving task output or hybrid-job logs, since algorithm parameters and results appear there.\n- **Cost guardrail.** Recommend a spending limit before the user's first QPU run, when the user asks what a workload costs, or when one request fans out across several devices or a large shot count. Spending limits may already exist in the customer's account. In general, enforce QPU spend caps with spending limits.\n- **Secrets.** Hyperparameters are stored in job metadata and echoed into the job's\n  CloudWatch log stream at container boot, so never pass a secret as a hyperparameter —\n  fetch it from Secrets Manager or SSM Parameter Store inside the algorithm script.\n  Restrict read access to the job log groups accordingly.\n\nFor details, see the [Amazon Braket security documentation](https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fsecurity.html).\n\n## Reference links\n\nAuthoritative sources — prefer these over recalled details, since device ARNs, quotas, prices, and supported features change.\n\n**Official documentation** (stable entry points — navigate\u002Fsearch from here)\n- Developer Guide — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fwhat-is-braket.html\n- Prerequisites & account setup — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-get-started.html\n- How Amazon Braket works — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-how-it-works.html\n- API Reference — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002FAPIReference\u002FWelcome.html\n- Python SDK API docs — https:\u002F\u002Famazon-braket-sdk-python.readthedocs.io\u002Fen\u002Flatest\u002F\n- Getting started — https:\u002F\u002Faws.amazon.com\u002Fbraket\u002Fgetting-started\u002F\n- OpenQASM 3.0 spec — https:\u002F\u002Fopenqasm.com\u002Fversions\u002F3.0\u002Findex.html\n- OpenQASM on Braket — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-openqasm.html\n- Supported OpenQASM features (pragmas, verbatim rules, dynamic circuits) — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-openqasm-supported-features.html\n- boto3 `braket` client — https:\u002F\u002Fdocs.aws.amazon.com\u002Fboto3\u002Flatest\u002Freference\u002Fservices\u002Fbraket.html\n- Security — https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fsecurity.html\n\nFor anything not covered here, **search the documentation** rather than guessing page slugs or recalling details: if the AWS MCP server is available, its `aws___search_documentation` tool can help; otherwise start from the Developer Guide or API Reference above and navigate.\n\n**GitHub**\n- `amazon-braket-sdk-python` (core SDK) — https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-sdk-python\n- `amazon-braket-schemas-python` (schemas and models for public Braket data) — https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-schemas-python\n- `amazon-braket-examples` — https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-examples\n",{"data":33,"body":36},{"name":4,"description":6,"metadata":34},{"version":35},"1",{"type":37,"children":38},"root",[39,47,54,60,400,405,410,481,487,492,683,821,827,832,918,945,951,1278,1284,1289,1534,1547,1553,1558,1568,1696,1716,1724,1778],{"type":40,"tag":41,"props":42,"children":43},"element","h1",{"id":4},[44],{"type":45,"value":46},"text","Amazon Braket",{"type":40,"tag":48,"props":49,"children":51},"h2",{"id":50},"primitives",[52],{"type":45,"value":53},"Primitives",{"type":40,"tag":55,"props":56,"children":57},"p",{},[58],{"type":45,"value":59},"The vocabulary of a Braket workflow, and which reference to open for each.",{"type":40,"tag":61,"props":62,"children":63},"table",{},[64,93],{"type":40,"tag":65,"props":66,"children":67},"thead",{},[68],{"type":40,"tag":69,"props":70,"children":71},"tr",{},[72,78,83,88],{"type":40,"tag":73,"props":74,"children":75},"th",{},[76],{"type":45,"value":77},"Primitive",{"type":40,"tag":73,"props":79,"children":80},{},[81],{"type":45,"value":82},"What it is",{"type":40,"tag":73,"props":84,"children":85},{},[86],{"type":45,"value":87},"Related References",{"type":40,"tag":73,"props":89,"children":90},{},[91],{"type":45,"value":92},"Open it when the request involves",{"type":40,"tag":94,"props":95,"children":96},"tbody",{},[97,130,155,179,225,276,322,359],{"type":40,"tag":69,"props":98,"children":99},{},[100,110,115,125],{"type":40,"tag":101,"props":102,"children":103},"td",{},[104],{"type":40,"tag":105,"props":106,"children":107},"strong",{},[108],{"type":45,"value":109},"Device",{"type":40,"tag":101,"props":111,"children":112},{},[113],{"type":45,"value":114},"A simulator or QPU, identified by a region-scoped ARN",{"type":40,"tag":101,"props":116,"children":117},{},[118],{"type":40,"tag":119,"props":120,"children":122},"a",{"href":121},"references\u002Fdevices.md",[123],{"type":45,"value":124},"devices.md",{"type":40,"tag":101,"props":126,"children":127},{},[128],{"type":45,"value":129},"anything about a device: what exists, discovering or filtering the fleet, availability and status (online, offline, retired), which region a device lives in, ARNs, choosing a device for a workload, qubit count, connectivity or topology, native gates, fidelities, calibration data, queue depth, shot and gate limits, paradigm (gate-model vs analog Hamiltonian simulation), whether a device supports program sets, pulse-level control, simulators and local emulators",{"type":40,"tag":69,"props":131,"children":132},{},[133,141,146,151],{"type":40,"tag":101,"props":134,"children":135},{},[136],{"type":40,"tag":105,"props":137,"children":138},{},[139],{"type":45,"value":140},"Program",{"type":40,"tag":101,"props":142,"children":143},{},[144],{"type":45,"value":145},"The workload\u002Finput — one executable (Circuit, AHS, OpenQASM). Which type is legal depends on the device's paradigm",{"type":40,"tag":101,"props":147,"children":148},{},[149],{"type":45,"value":150},"-",{"type":40,"tag":101,"props":152,"children":153},{},[154],{"type":45,"value":150},{"type":40,"tag":69,"props":156,"children":157},{},[158,166,171,175],{"type":40,"tag":101,"props":159,"children":160},{},[161],{"type":40,"tag":105,"props":162,"children":163},{},[164],{"type":45,"value":165},"Quantum task",{"type":40,"tag":101,"props":167,"children":168},{},[169],{"type":45,"value":170},"One program + shots, run once (the atomic unit Braket meters)",{"type":40,"tag":101,"props":172,"children":173},{},[174],{"type":45,"value":150},{"type":40,"tag":101,"props":176,"children":177},{},[178],{"type":45,"value":150},{"type":40,"tag":69,"props":180,"children":181},{},[182,190,203,212],{"type":40,"tag":101,"props":183,"children":184},{},[185],{"type":40,"tag":105,"props":186,"children":187},{},[188],{"type":45,"value":189},"Task batch",{"type":40,"tag":101,"props":191,"children":192},{},[193,195,201],{"type":45,"value":194},"Many ",{"type":40,"tag":196,"props":197,"children":198},"em",{},[199],{"type":45,"value":200},"independent",{"type":45,"value":202}," tasks — SDK-only fallback for when a program set does not fit; works on all devices",{"type":40,"tag":101,"props":204,"children":205},{},[206],{"type":40,"tag":119,"props":207,"children":209},{"href":208},"references\u002Fprogram-sets.md",[210],{"type":45,"value":211},"program-sets.md",{"type":40,"tag":101,"props":213,"children":214},{},[215,217],{"type":45,"value":216},"see the Program set row; also ",{"type":40,"tag":119,"props":218,"children":222},{"href":219,"rel":220},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-batching-tasks.html",[221],"nofollow",[223],{"type":45,"value":224},"running multiple programs",{"type":40,"tag":69,"props":226,"children":227},{},[228,236,248,255],{"type":40,"tag":101,"props":229,"children":230},{},[231],{"type":40,"tag":105,"props":232,"children":233},{},[234],{"type":45,"value":235},"Program set",{"type":40,"tag":101,"props":237,"children":238},{},[239,241,246],{"type":45,"value":240},"Many programs in ",{"type":40,"tag":105,"props":242,"children":243},{},[244],{"type":45,"value":245},"one service-side task",{"type":45,"value":247}," — preferred way to run multiple programs instead of task batch",{"type":40,"tag":101,"props":249,"children":250},{},[251],{"type":40,"tag":119,"props":252,"children":253},{"href":208},[254],{"type":45,"value":211},{"type":40,"tag":101,"props":256,"children":257},{},[258,260,267,269],{"type":45,"value":259},"running more than one program: parameter sweeps, scanning parameter values, task batches, ",{"type":40,"tag":261,"props":262,"children":264},"code",{"className":263},[],[265],{"type":45,"value":266},"run_batch",{"type":45,"value":268},", several circuits submitted together, attaching observables across programs, and minimizing per-task fees when many programs run, program sets. Also ",{"type":40,"tag":119,"props":270,"children":273},{"href":271,"rel":272},"https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-examples\u002Fblob\u002Fmain\u002Fexamples\u002Fbraket_features\u002Fprogram_sets\u002F01_Getting_started_with_program_sets.ipynb",[221],[274],{"type":45,"value":275},"getting started with program sets",{"type":40,"tag":69,"props":277,"children":278},{},[279,287,292,301],{"type":40,"tag":101,"props":280,"children":281},{},[282],{"type":40,"tag":105,"props":283,"children":284},{},[285],{"type":45,"value":286},"Hybrid job",{"type":40,"tag":101,"props":288,"children":289},{},[290],{"type":45,"value":291},"Managed classical-quantum loop that orchestrates many tasks",{"type":40,"tag":101,"props":293,"children":294},{},[295],{"type":40,"tag":119,"props":296,"children":298},{"href":297},"references\u002Fhybrid-job.md",[299],{"type":45,"value":300},"hybrid-job.md",{"type":40,"tag":101,"props":302,"children":303},{},[304,306,312,314,320],{"type":45,"value":305},"hybrid jobs: ",{"type":40,"tag":261,"props":307,"children":309},{"className":308},[],[310],{"type":45,"value":311},"@hybrid_job",{"type":45,"value":313},", algorithm scripts and source modules, ",{"type":40,"tag":261,"props":315,"children":317},{"className":316},[],[318],{"type":45,"value":319},"entry_point",{"type":45,"value":321},", embedded simulators, BYOC and custom container images, CUDA-Q, job execution roles, hyperparameters, checkpoints, and retrieving job results",{"type":40,"tag":69,"props":323,"children":324},{},[325,333,345,354],{"type":40,"tag":101,"props":326,"children":327},{},[328],{"type":40,"tag":105,"props":329,"children":330},{},[331],{"type":45,"value":332},"Spending limit",{"type":40,"tag":101,"props":334,"children":335},{},[336,338,343],{"type":45,"value":337},"Service-side hard cap that ",{"type":40,"tag":105,"props":339,"children":340},{},[341],{"type":45,"value":342},"rejects",{"type":45,"value":344}," QPU tasks — the only true enforcement (not SDK)",{"type":40,"tag":101,"props":346,"children":347},{},[348],{"type":40,"tag":119,"props":349,"children":351},{"href":350},"references\u002Fspending-limit.md",[352],{"type":45,"value":353},"spending-limit.md",{"type":40,"tag":101,"props":355,"children":356},{},[357],{"type":45,"value":358},"capping or enforcing spend: spending limits (create, update, delete, search), and cost guardrails",{"type":40,"tag":69,"props":360,"children":361},{},[362,370,382,389],{"type":40,"tag":101,"props":363,"children":364},{},[365],{"type":40,"tag":105,"props":366,"children":367},{},[368],{"type":45,"value":369},"Cost tracking",{"type":40,"tag":101,"props":371,"children":372},{},[373,375,380],{"type":45,"value":374},"In-session cost ",{"type":40,"tag":196,"props":376,"children":377},{},[378],{"type":45,"value":379},"estimate",{"type":45,"value":381}," (not enforcement)",{"type":40,"tag":101,"props":383,"children":384},{},[385],{"type":40,"tag":119,"props":386,"children":387},{"href":350},[388],{"type":45,"value":353},{"type":40,"tag":101,"props":390,"children":391},{},[392,394],{"type":45,"value":393},"in-session cost tracking with ",{"type":40,"tag":261,"props":395,"children":397},{"className":396},[],[398],{"type":45,"value":399},"Tracker",{"type":40,"tag":55,"props":401,"children":402},{},[403],{"type":45,"value":404},"Each reference carries the domain detail for its own area — field paths, key names, API shapes, and billing models.",{"type":40,"tag":55,"props":406,"children":407},{},[408],{"type":45,"value":409},"Additional notes:",{"type":40,"tag":411,"props":412,"children":413},"ul",{},[414,456],{"type":40,"tag":415,"props":416,"children":417},"li",{},[418,423,425,431,433,439,441,445,447,454],{"type":40,"tag":105,"props":419,"children":420},{},[421],{"type":45,"value":422},"Reservation",{"type":45,"value":424}," — exclusive device access for a booked window. This skill covers reservations at pointer depth only: the billing model is in ",{"type":40,"tag":119,"props":426,"children":428},{"href":427},"references\u002Fpricing.md",[429],{"type":45,"value":430},"pricing.md",{"type":45,"value":432},", reservation-specific device limits such as ",{"type":40,"tag":261,"props":434,"children":436},{"className":435},[],[437],{"type":45,"value":438},"service.reservationShotsRange",{"type":45,"value":440}," are in ",{"type":40,"tag":119,"props":442,"children":443},{"href":121},[444],{"type":45,"value":124},{"type":45,"value":446},", and the full model is in the ",{"type":40,"tag":119,"props":448,"children":451},{"href":449,"rel":450},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-reservations.html",[221],[452],{"type":45,"value":453},"reservations developer guide",{"type":45,"value":455},".",{"type":40,"tag":415,"props":457,"children":458},{},[459,464,466,470,472,479],{"type":40,"tag":105,"props":460,"children":461},{},[462],{"type":45,"value":463},"Gate calibrations \u002F pulse control",{"type":45,"value":465}," — access native gate calibrations on QPUs and attach custom pulse sequences at run time. See ",{"type":40,"tag":119,"props":467,"children":468},{"href":121},[469],{"type":45,"value":124},{"type":45,"value":471}," for detecting support, and the ",{"type":40,"tag":119,"props":473,"children":476},{"href":474,"rel":475},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-pulse-control.html",[221],[477],{"type":45,"value":478},"pulse control developer guide",{"type":45,"value":480}," for the full model.",{"type":40,"tag":48,"props":482,"children":484},{"id":483},"critical-rules",[485],{"type":45,"value":486},"Critical Rules",{"type":40,"tag":55,"props":488,"children":489},{},[490],{"type":45,"value":491},"These rules apply to every Braket request, whatever it involves.",{"type":40,"tag":493,"props":494,"children":495},"ol",{},[496,554,572,589,631,647,657],{"type":40,"tag":415,"props":497,"children":498},{},[499,520,522,529,531],{"type":40,"tag":105,"props":500,"children":501},{},[502,504,510,512,518],{"type":45,"value":503},"The Amazon Braket Python SDK (",{"type":40,"tag":261,"props":505,"children":507},{"className":506},[],[508],{"type":45,"value":509},"pip install amazon-braket-sdk",{"type":45,"value":511},", imported as ",{"type":40,"tag":261,"props":513,"children":515},{"className":514},[],[516],{"type":45,"value":517},"braket",{"type":45,"value":519},") is the primary entry point.",{"type":45,"value":521}," Prefer it for every operation including Braket API operations, and understand what it covers by reading the ",{"type":40,"tag":119,"props":523,"children":526},{"href":524,"rel":525},"https:\u002F\u002Famazon-braket-sdk-python.readthedocs.io\u002Fen\u002Fstable\u002F",[221],[527],{"type":45,"value":528},"docs",{"type":45,"value":530}," or inspecting the SDK's modules locally.",{"type":40,"tag":411,"props":532,"children":533},{},[534],{"type":40,"tag":415,"props":535,"children":536},{},[537,539,545,547,553],{"type":45,"value":538},"Use local execution tools for running the Braket SDK, such as ",{"type":40,"tag":261,"props":540,"children":542},{"className":541},[],[543],{"type":45,"value":544},"shell",{"type":45,"value":546}," with ",{"type":40,"tag":261,"props":548,"children":550},{"className":549},[],[551],{"type":45,"value":552},"python3 -c \"\u003Ccode>\"",{"type":45,"value":455},{"type":40,"tag":415,"props":555,"children":556},{},[557,562,564,570],{"type":40,"tag":105,"props":558,"children":559},{},[560],{"type":45,"value":561},"The AWS MCP server is recommended for executing any other AWS API calls in this skill",{"type":45,"value":563},", especially operations not present in the Python SDK, although not required. Note: the AWS MCP's ",{"type":40,"tag":261,"props":565,"children":567},{"className":566},[],[568],{"type":45,"value":569},"run_script",{"type":45,"value":571}," tool executes code in a minimal sandbox without Braket libraries, so prefer using other tools for code execution, especially when using the Braket SDK.",{"type":40,"tag":415,"props":573,"children":574},{},[575,580,582,587],{"type":40,"tag":105,"props":576,"children":577},{},[578],{"type":45,"value":579},"A small set of primitives composes every workflow",{"type":45,"value":581}," — see ",{"type":40,"tag":119,"props":583,"children":585},{"href":584},"#primitives",[586],{"type":45,"value":53},{"type":45,"value":588}," for the vocabulary and the reference for each.",{"type":40,"tag":415,"props":590,"children":591},{},[592,597,599,605,607,613,615,622,624,630],{"type":40,"tag":105,"props":593,"children":594},{},[595],{"type":45,"value":596},"Devices, quantum tasks, and hybrid jobs are region-scoped, so fan out across every Braket region whenever you use the API, CLI, or boto3 to search for resources.",{"type":45,"value":598}," The SDK handles fanout for you where it can — ",{"type":40,"tag":261,"props":600,"children":602},{"className":601},[],[603],{"type":45,"value":604},"AwsDevice.get_devices",{"type":45,"value":606}," searches QPUs in all regions.\nGet the list of regions Braket supports from ",{"type":40,"tag":261,"props":608,"children":610},{"className":609},[],[611],{"type":45,"value":612},"aws___get_regional_availability",{"type":45,"value":614}," when the AWS MCP server is available, or from the ",{"type":40,"tag":119,"props":616,"children":619},{"href":617,"rel":618},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-devices.html",[221],[620],{"type":45,"value":621},"supported devices and regions documentation",{"type":45,"value":623},".\nResource ARNs containing a region may only be queried from that same region, otherwise you will see a ",{"type":40,"tag":261,"props":625,"children":627},{"className":626},[],[628],{"type":45,"value":629},"ResourceNotFoundException",{"type":45,"value":455},{"type":40,"tag":415,"props":632,"children":633},{},[634,639,641,645],{"type":40,"tag":105,"props":635,"children":636},{},[637],{"type":45,"value":638},"Open the matching reference before you write code or answer.",{"type":45,"value":640}," Use the ",{"type":40,"tag":105,"props":642,"children":643},{},[644],{"type":45,"value":53},{"type":45,"value":646}," table to find and read references. Note: A request that asks for several things, e.g. executing a series of circuits and controlling the cost thereof, may require reading multiple reference files.",{"type":40,"tag":415,"props":648,"children":649},{},[650,655],{"type":40,"tag":105,"props":651,"children":652},{},[653],{"type":45,"value":654},"Verify, never recall.",{"type":45,"value":656}," Device ARNs and statuses, API signatures, supported features, and prices (and other values) all change and may post-date training data.",{"type":40,"tag":415,"props":658,"children":659},{},[660,665,667,674,676,681],{"type":40,"tag":105,"props":661,"children":662},{},[663],{"type":45,"value":664},"Confirm an SDK signature before you write code that calls it.",{"type":45,"value":666}," Read it from the ",{"type":40,"tag":119,"props":668,"children":671},{"href":669,"rel":670},"https:\u002F\u002Famazon-braket-sdk-python.readthedocs.io\u002Fen\u002Flatest\u002F",[221],[672],{"type":45,"value":673},"SDK reference docs",{"type":45,"value":675},".\nIf no available tool can reach them, get it from the installed SDK with ",{"type":40,"tag":261,"props":677,"children":679},{"className":678},[],[680],{"type":45,"value":544},{"type":45,"value":682},":",{"type":40,"tag":684,"props":685,"children":690},"pre",{"className":686,"code":687,"language":688,"meta":689,"style":689},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","PAGER=cat python -c \"import braket; help(braket)\"       # subpackages: ahs, circuits, pulse, program_sets, ...\npython -c \"import braket.ahs; print(dir(braket.ahs))\"   # names: DrivingField, AtomArrangement, ...\npython -c \"import inspect; from braket.ahs import DrivingField; \\\nprint(inspect.signature(DrivingField.from_lists)); print(inspect.getdoc(DrivingField.from_lists))\"\n","bash","",[691],{"type":40,"tag":261,"props":692,"children":693},{"__ignoreMap":689},[694,750,781,807],{"type":40,"tag":695,"props":696,"children":699},"span",{"class":697,"line":698},"line",1,[700,706,712,718,724,729,734,739,744],{"type":40,"tag":695,"props":701,"children":703},{"style":702},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[704],{"type":45,"value":705},"PAGER",{"type":40,"tag":695,"props":707,"children":709},{"style":708},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[710],{"type":45,"value":711},"=",{"type":40,"tag":695,"props":713,"children":715},{"style":714},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[716],{"type":45,"value":717},"cat",{"type":40,"tag":695,"props":719,"children":721},{"style":720},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[722],{"type":45,"value":723}," python",{"type":40,"tag":695,"props":725,"children":726},{"style":714},[727],{"type":45,"value":728}," -c",{"type":40,"tag":695,"props":730,"children":731},{"style":708},[732],{"type":45,"value":733}," \"",{"type":40,"tag":695,"props":735,"children":736},{"style":714},[737],{"type":45,"value":738},"import braket; help(braket)",{"type":40,"tag":695,"props":740,"children":741},{"style":708},[742],{"type":45,"value":743},"\"",{"type":40,"tag":695,"props":745,"children":747},{"style":746},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[748],{"type":45,"value":749},"       # subpackages: ahs, circuits, pulse, program_sets, ...\n",{"type":40,"tag":695,"props":751,"children":753},{"class":697,"line":752},2,[754,759,763,767,772,776],{"type":40,"tag":695,"props":755,"children":756},{"style":720},[757],{"type":45,"value":758},"python",{"type":40,"tag":695,"props":760,"children":761},{"style":714},[762],{"type":45,"value":728},{"type":40,"tag":695,"props":764,"children":765},{"style":708},[766],{"type":45,"value":733},{"type":40,"tag":695,"props":768,"children":769},{"style":714},[770],{"type":45,"value":771},"import braket.ahs; print(dir(braket.ahs))",{"type":40,"tag":695,"props":773,"children":774},{"style":708},[775],{"type":45,"value":743},{"type":40,"tag":695,"props":777,"children":778},{"style":746},[779],{"type":45,"value":780},"   # names: DrivingField, AtomArrangement, ...\n",{"type":40,"tag":695,"props":782,"children":784},{"class":697,"line":783},3,[785,789,793,797,802],{"type":40,"tag":695,"props":786,"children":787},{"style":720},[788],{"type":45,"value":758},{"type":40,"tag":695,"props":790,"children":791},{"style":714},[792],{"type":45,"value":728},{"type":40,"tag":695,"props":794,"children":795},{"style":708},[796],{"type":45,"value":733},{"type":40,"tag":695,"props":798,"children":799},{"style":714},[800],{"type":45,"value":801},"import inspect; from braket.ahs import DrivingField; ",{"type":40,"tag":695,"props":803,"children":804},{"style":702},[805],{"type":45,"value":806},"\\\n",{"type":40,"tag":695,"props":808,"children":810},{"class":697,"line":809},4,[811,816],{"type":40,"tag":695,"props":812,"children":813},{"style":714},[814],{"type":45,"value":815},"print(inspect.signature(DrivingField.from_lists)); print(inspect.getdoc(DrivingField.from_lists))",{"type":40,"tag":695,"props":817,"children":818},{"style":708},[819],{"type":45,"value":820},"\"\n",{"type":40,"tag":48,"props":822,"children":824},{"id":823},"guardrail-where-this-skills-own-files-live-mcp-vs-local-install",[825],{"type":45,"value":826},"Guardrail — where this skill's own files live (MCP vs local install)",{"type":40,"tag":55,"props":828,"children":829},{},[830],{"type":45,"value":831},"This skill can be loaded two ways, and they resolve the skill's own bundled files from different places. Determine how the skill was loaded before reading a reference:",{"type":40,"tag":411,"props":833,"children":834},{},[835,884],{"type":40,"tag":415,"props":836,"children":837},{},[838,851,853,858,860,866,868,874,876,882],{"type":40,"tag":105,"props":839,"children":840},{},[841,843,849],{"type":45,"value":842},"Loaded through the AWS MCP ",{"type":40,"tag":261,"props":844,"children":846},{"className":845},[],[847],{"type":45,"value":848},"retrieve_skill",{"type":45,"value":850}," tool:",{"type":45,"value":852}," The skill is not installed on the local filesystem. You MUST fetch each reference via ",{"type":40,"tag":261,"props":854,"children":856},{"className":855},[],[857],{"type":45,"value":848},{"type":45,"value":859}," with the ",{"type":40,"tag":261,"props":861,"children":863},{"className":862},[],[864],{"type":45,"value":865},"file",{"type":45,"value":867}," parameter (e.g. ",{"type":40,"tag":261,"props":869,"children":871},{"className":870},[],[872],{"type":45,"value":873},"file=\"references\u002Fdevices.md\"",{"type":45,"value":875},"). Do NOT ",{"type":40,"tag":261,"props":877,"children":879},{"className":878},[],[880],{"type":45,"value":881},"file_read",{"type":45,"value":883}," these paths locally — they do not exist on disk.",{"type":40,"tag":415,"props":885,"children":886},{},[887,892,894,900,902,908,910,916],{"type":40,"tag":105,"props":888,"children":889},{},[890],{"type":45,"value":891},"Installed locally",{"type":45,"value":893}," (e.g. ",{"type":40,"tag":261,"props":895,"children":897},{"className":896},[],[898],{"type":45,"value":899},"~\u002F.kiro\u002Fskills\u002Famazon-braket\u002F",{"type":45,"value":901},", ",{"type":40,"tag":261,"props":903,"children":905},{"className":904},[],[906],{"type":45,"value":907},".kiro\u002Fskills\u002Famazon-braket\u002F",{"type":45,"value":909},", or ",{"type":40,"tag":261,"props":911,"children":913},{"className":912},[],[914],{"type":45,"value":915},"~\u002F.claude\u002Fskills\u002Famazon-braket\u002F",{"type":45,"value":917},"): Read files from the local skill directory using relative paths.",{"type":40,"tag":55,"props":919,"children":920},{},[921,927,929,935,937,943],{"type":40,"tag":261,"props":922,"children":924},{"className":923},[],[925],{"type":45,"value":926},"references\u002F",{"type":45,"value":928}," is a sibling of this ",{"type":40,"tag":261,"props":930,"children":932},{"className":931},[],[933],{"type":45,"value":934},"SKILL.md",{"type":45,"value":936}," — resolve reference paths against that directory, not your working directory, and do not search the filesystem for them.\nIf a skill tool returns this overview instead of the file you asked for, it did not fetch it: read it from that directory instead, and do not write code from memory because a reference read failed.\nThis distinction applies only to the skill's own packaged files. User data and session artifacts are always read from and written to the user's working directory — do not ",{"type":40,"tag":261,"props":938,"children":940},{"className":939},[],[941],{"type":45,"value":942},"cd",{"type":45,"value":944}," before running a script that writes a relative artifact path.",{"type":40,"tag":48,"props":946,"children":948},{"id":947},"common-mistakes",[949],{"type":45,"value":950},"Common mistakes",{"type":40,"tag":61,"props":952,"children":953},{},[954,975],{"type":40,"tag":65,"props":955,"children":956},{},[957],{"type":40,"tag":69,"props":958,"children":959},{},[960,965,970],{"type":40,"tag":73,"props":961,"children":962},{},[963],{"type":45,"value":964},"Symptom",{"type":40,"tag":73,"props":966,"children":967},{},[968],{"type":45,"value":969},"Cause",{"type":40,"tag":73,"props":971,"children":972},{},[973],{"type":45,"value":974},"Fix",{"type":40,"tag":94,"props":976,"children":977},{},[978,996,1108,1209,1234,1260],{"type":40,"tag":69,"props":979,"children":980},{},[981,986,991],{"type":40,"tag":101,"props":982,"children":983},{},[984],{"type":45,"value":985},"Treats \"task\", \"batch\", \"job\" as interchangeable",{"type":40,"tag":101,"props":987,"children":988},{},[989],{"type":45,"value":990},"Primitive confusion",{"type":40,"tag":101,"props":992,"children":993},{},[994],{"type":45,"value":995},"Task = one run; batch = many parallel tasks; job = managed loop",{"type":40,"tag":69,"props":997,"children":998},{},[999,1030,1049],{"type":40,"tag":101,"props":1000,"children":1001},{},[1002,1008,1010,1016,1017,1023,1024],{"type":40,"tag":261,"props":1003,"children":1005},{"className":1004},[],[1006],{"type":45,"value":1007},"Missing required parameter: filters",{"type":45,"value":1009}," on ",{"type":40,"tag":261,"props":1011,"children":1013},{"className":1012},[],[1014],{"type":45,"value":1015},"SearchQuantumTasks",{"type":45,"value":901},{"type":40,"tag":261,"props":1018,"children":1020},{"className":1019},[],[1021],{"type":45,"value":1022},"SearchJobs",{"type":45,"value":909},{"type":40,"tag":261,"props":1025,"children":1027},{"className":1026},[],[1028],{"type":45,"value":1029},"SearchDevices",{"type":40,"tag":101,"props":1031,"children":1032},{},[1033,1039,1041,1047],{"type":40,"tag":261,"props":1034,"children":1036},{"className":1035},[],[1037],{"type":45,"value":1038},"filters",{"type":45,"value":1040}," is required on all three — only ",{"type":40,"tag":261,"props":1042,"children":1044},{"className":1043},[],[1045],{"type":45,"value":1046},"SearchSpendingLimits",{"type":45,"value":1048}," lets you omit it",{"type":40,"tag":101,"props":1050,"children":1051},{},[1052,1054,1060,1062,1068,1070,1076,1078,1084,1086,1092,1094,1099,1101,1106],{"type":45,"value":1053},"Pass ",{"type":40,"tag":261,"props":1055,"children":1057},{"className":1056},[],[1058],{"type":45,"value":1059},"filters=[]",{"type":45,"value":1061}," (",{"type":40,"tag":261,"props":1063,"children":1065},{"className":1064},[],[1066],{"type":45,"value":1067},"--filters '[]'",{"type":45,"value":1069},") for an unfiltered search. A populated filter needs ",{"type":40,"tag":261,"props":1071,"children":1073},{"className":1072},[],[1074],{"type":45,"value":1075},"name",{"type":45,"value":1077}," and ",{"type":40,"tag":261,"props":1079,"children":1081},{"className":1080},[],[1082],{"type":45,"value":1083},"values",{"type":45,"value":1085},", plus ",{"type":40,"tag":261,"props":1087,"children":1089},{"className":1088},[],[1090],{"type":45,"value":1091},"operator",{"type":45,"value":1093}," on tasks and jobs; ",{"type":40,"tag":261,"props":1095,"children":1097},{"className":1096},[],[1098],{"type":45,"value":1029},{"type":45,"value":1100}," has no ",{"type":40,"tag":261,"props":1102,"children":1104},{"className":1103},[],[1105],{"type":45,"value":1091},{"type":45,"value":1107}," member",{"type":40,"tag":69,"props":1109,"children":1110},{},[1111,1129,1183],{"type":40,"tag":101,"props":1112,"children":1113},{},[1114,1120,1122,1127],{"type":40,"tag":261,"props":1115,"children":1117},{"className":1116},[],[1118],{"type":45,"value":1119},"Missing required parameter: clientToken",{"type":45,"value":1121}," when using AWS MCP ",{"type":40,"tag":261,"props":1123,"children":1125},{"className":1124},[],[1126],{"type":45,"value":569},{"type":45,"value":1128}," tool",{"type":40,"tag":101,"props":1130,"children":1131},{},[1132,1138,1139,1145,1146,1152,1153,1159,1160,1166,1168,1174,1176,1181],{"type":40,"tag":261,"props":1133,"children":1135},{"className":1134},[],[1136],{"type":45,"value":1137},"CreateQuantumTask",{"type":45,"value":901},{"type":40,"tag":261,"props":1140,"children":1142},{"className":1141},[],[1143],{"type":45,"value":1144},"CreateJob",{"type":45,"value":901},{"type":40,"tag":261,"props":1147,"children":1149},{"className":1148},[],[1150],{"type":45,"value":1151},"CancelQuantumTask",{"type":45,"value":901},{"type":40,"tag":261,"props":1154,"children":1156},{"className":1155},[],[1157],{"type":45,"value":1158},"CreateSpendingLimit",{"type":45,"value":901},{"type":40,"tag":261,"props":1161,"children":1163},{"className":1162},[],[1164],{"type":45,"value":1165},"UpdateSpendingLimit",{"type":45,"value":1167}," require a ",{"type":40,"tag":261,"props":1169,"children":1171},{"className":1170},[],[1172],{"type":45,"value":1173},"clientToken",{"type":45,"value":1175}," for idempotency. The SDK, CLI, and boto3 generate one automatically; the ",{"type":40,"tag":261,"props":1177,"children":1179},{"className":1178},[],[1180],{"type":45,"value":569},{"type":45,"value":1182}," tool requires explicit passing",{"type":40,"tag":101,"props":1184,"children":1185},{},[1186,1187,1193,1195,1200,1202,1207],{"type":45,"value":1053},{"type":40,"tag":261,"props":1188,"children":1190},{"className":1189},[],[1191],{"type":45,"value":1192},"clientToken=str(uuid.uuid4())",{"type":45,"value":1194}," on APIs taking ",{"type":40,"tag":261,"props":1196,"children":1198},{"className":1197},[],[1199],{"type":45,"value":1173},{"type":45,"value":1201}," when calling through ",{"type":40,"tag":261,"props":1203,"children":1205},{"className":1204},[],[1206],{"type":45,"value":569},{"type":45,"value":1208},". Otherwise, prefer the SDK for these operations when possible.",{"type":40,"tag":69,"props":1210,"children":1211},{},[1212,1217,1222],{"type":40,"tag":101,"props":1213,"children":1214},{},[1215],{"type":45,"value":1216},"Builds program IR as JAQCD",{"type":40,"tag":101,"props":1218,"children":1219},{},[1220],{"type":45,"value":1221},"JAQCD is deprecated on Amazon Braket",{"type":40,"tag":101,"props":1223,"children":1224},{},[1225,1227],{"type":45,"value":1226},"Use OpenQASM — see ",{"type":40,"tag":119,"props":1228,"children":1231},{"href":1229,"rel":1230},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-openqasm.html",[221],[1232],{"type":45,"value":1233},"OpenQASM on Braket",{"type":40,"tag":69,"props":1235,"children":1236},{},[1237,1242,1247],{"type":40,"tag":101,"props":1238,"children":1239},{},[1240],{"type":45,"value":1241},"Denies a feature or SDK construct exists",{"type":40,"tag":101,"props":1243,"children":1244},{},[1245],{"type":45,"value":1246},"Training data outdated",{"type":40,"tag":101,"props":1248,"children":1249},{},[1250,1252,1258],{"type":45,"value":1251},"Rule 2 — verify against the docs or ",{"type":40,"tag":261,"props":1253,"children":1255},{"className":1254},[],[1256],{"type":45,"value":1257},"GetDevice",{"type":45,"value":1259}," before saying it does not exist",{"type":40,"tag":69,"props":1261,"children":1262},{},[1263,1268,1273],{"type":40,"tag":101,"props":1264,"children":1265},{},[1266],{"type":45,"value":1267},"Invents a class, method, or parameter",{"type":40,"tag":101,"props":1269,"children":1270},{},[1271],{"type":45,"value":1272},"Writing API names from memory",{"type":40,"tag":101,"props":1274,"children":1275},{},[1276],{"type":45,"value":1277},"Confirm the signature first (rule 4). If uncertain, say so rather than inventing",{"type":40,"tag":48,"props":1279,"children":1281},{"id":1280},"security-considerations",[1282],{"type":45,"value":1283},"Security considerations",{"type":40,"tag":55,"props":1285,"children":1286},{},[1287],{"type":45,"value":1288},"Braket workflows touch IAM, S3, and (for hybrid jobs) container execution.",{"type":40,"tag":411,"props":1290,"children":1291},{},[1292,1389,1451,1461,1495,1514,1524],{"type":40,"tag":415,"props":1293,"children":1294},{},[1295,1300,1302,1308,1310,1317,1319,1325,1327,1333,1335,1341,1342,1349,1351,1358,1359,1366,1368],{"type":40,"tag":105,"props":1296,"children":1297},{},[1298],{"type":45,"value":1299},"Least-privilege IAM.",{"type":45,"value":1301}," Scope custom policies to the actions, device ARNs, and buckets a workload actually uses, and avoid broad ",{"type":40,"tag":261,"props":1303,"children":1305},{"className":1304},[],[1306],{"type":45,"value":1307},"braket:*",{"type":45,"value":1309},". Actions are listed at the ",{"type":40,"tag":119,"props":1311,"children":1314},{"href":1312,"rel":1313},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fservice-authorization\u002Flatest\u002Freference\u002Flist_braket.html",[221],[1315],{"type":45,"value":1316},"Service Authorization Reference",{"type":45,"value":1318},". Prefer a custom policy over ",{"type":40,"tag":261,"props":1320,"children":1322},{"className":1321},[],[1323],{"type":45,"value":1324},"AmazonBraketFullAccess",{"type":45,"value":1326},", which is deliberately broad: S3 on any ",{"type":40,"tag":261,"props":1328,"children":1330},{"className":1329},[],[1331],{"type":45,"value":1332},"amazon-braket-*",{"type":45,"value":1334}," bucket or any bucket tagged ",{"type":40,"tag":261,"props":1336,"children":1338},{"className":1337},[],[1339],{"type":45,"value":1340},"AmazonBraket=true",{"type":45,"value":1061},{"type":40,"tag":119,"props":1343,"children":1346},{"href":1344,"rel":1345},"https:\u002F\u002Fdocs.aws.amazon.com\u002FAmazonS3\u002Flatest\u002Fuserguide\u002Fbuckets-tagging-enable-abac.html",[221],[1347],{"type":45,"value":1348},"if the bucket is enabled for Attribute-Based Access Control",{"type":45,"value":1350},"), plus SageMaker and CloudWatch actions a task-submission workflow never needs. See ",{"type":40,"tag":119,"props":1352,"children":1355},{"href":1353,"rel":1354},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-manage-access.html",[221],[1356],{"type":45,"value":1357},"Managing access to Amazon Braket",{"type":45,"value":1077},{"type":40,"tag":119,"props":1360,"children":1363},{"href":1361,"rel":1362},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Frestrict-access.html",[221],[1364],{"type":45,"value":1365},"Restricting access to devices",{"type":45,"value":1367},".\n",{"type":40,"tag":411,"props":1369,"children":1370},{},[1371],{"type":40,"tag":415,"props":1372,"children":1373},{},[1374,1380,1381,1387],{"type":40,"tag":261,"props":1375,"children":1377},{"className":1376},[],[1378],{"type":45,"value":1379},"braket:UpdateSpendingLimit",{"type":45,"value":1077},{"type":40,"tag":261,"props":1382,"children":1384},{"className":1383},[],[1385],{"type":45,"value":1386},"braket:DeleteSpendingLimit",{"type":45,"value":1388}," should be restricted to prevent accidental removal of a spending limit and accidental cost overruns.",{"type":40,"tag":415,"props":1390,"children":1391},{},[1392,1397,1399,1410,1412,1418,1420,1426,1428,1434,1436,1442,1444,1450],{"type":40,"tag":105,"props":1393,"children":1394},{},[1395],{"type":45,"value":1396},"Hybrid-job execution role.",{"type":45,"value":1398}," Attach only ",{"type":40,"tag":119,"props":1400,"children":1403},{"href":1401,"rel":1402},"https:\u002F\u002Fdocs.aws.amazon.com\u002Faws-managed-policy\u002Flatest\u002Freference\u002FAmazonBraketJobsExecutionPolicy.html",[221],[1404],{"type":40,"tag":261,"props":1405,"children":1407},{"className":1406},[],[1408],{"type":45,"value":1409},"AmazonBraketJobsExecutionPolicy",{"type":45,"value":1411},". Its ",{"type":40,"tag":261,"props":1413,"children":1415},{"className":1414},[],[1416],{"type":45,"value":1417},"iam:PassRole",{"type":45,"value":1419}," condition requires the role be named ",{"type":40,"tag":261,"props":1421,"children":1423},{"className":1422},[],[1424],{"type":45,"value":1425},"AmazonBraketJobsExecutionRole*",{"type":45,"value":1427}," under the ",{"type":40,"tag":261,"props":1429,"children":1431},{"className":1430},[],[1432],{"type":45,"value":1433},"\u002Fservice-role\u002F",{"type":45,"value":1435}," path, or ",{"type":40,"tag":261,"props":1437,"children":1439},{"className":1438},[],[1440],{"type":45,"value":1441},"create_job",{"type":45,"value":1443}," is denied at ",{"type":40,"tag":261,"props":1445,"children":1447},{"className":1446},[],[1448],{"type":45,"value":1449},"PassRole",{"type":45,"value":455},{"type":40,"tag":415,"props":1452,"children":1453},{},[1454,1459],{"type":40,"tag":105,"props":1455,"children":1456},{},[1457],{"type":45,"value":1458},"Ephemeral credentials.",{"type":45,"value":1460}," Call Braket APIs with IAM roles (instance profiles, ECS\u002FEKS task roles, or assumed roles), not long-lived IAM user access keys.",{"type":40,"tag":415,"props":1462,"children":1463},{},[1464,1469,1471,1477,1479,1485,1487,1493],{"type":40,"tag":105,"props":1465,"children":1466},{},[1467],{"type":45,"value":1468},"Encrypt task output.",{"type":45,"value":1470}," Enable default encryption (SSE-S3, or SSE-KMS with a customer-managed key for sensitive workloads) on any S3 bucket receiving task results, job source archives, output data, or checkpoints. Add ",{"type":40,"tag":261,"props":1472,"children":1474},{"className":1473},[],[1475],{"type":45,"value":1476},"aws:SourceAccount",{"type":45,"value":1478},"\u002F",{"type":40,"tag":261,"props":1480,"children":1482},{"className":1481},[],[1483],{"type":45,"value":1484},"aws:SourceArn",{"type":45,"value":1486}," conditions to the bucket policy where a service principal is granted access, and deny non-TLS access with an ",{"type":40,"tag":261,"props":1488,"children":1490},{"className":1489},[],[1491],{"type":45,"value":1492},"aws:SecureTransport: false",{"type":45,"value":1494}," condition.",{"type":40,"tag":415,"props":1496,"children":1497},{},[1498,1503,1505,1512],{"type":40,"tag":105,"props":1499,"children":1500},{},[1501],{"type":45,"value":1502},"Auditing.",{"type":45,"value":1504}," Enable ",{"type":40,"tag":119,"props":1506,"children":1509},{"href":1507,"rel":1508},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fawscloudtrail\u002Flatest\u002Fuserguide\u002Fview-cloudtrail-events.html",[221],[1510],{"type":45,"value":1511},"CloudTrail",{"type":45,"value":1513}," for Braket management events, with log-file validation, KMS encryption, and delivery to an access-restricted bucket — the trail is the primary evidence if a cost guardrail is removed. Encrypt any CloudWatch Logs group receiving task output or hybrid-job logs, since algorithm parameters and results appear there.",{"type":40,"tag":415,"props":1515,"children":1516},{},[1517,1522],{"type":40,"tag":105,"props":1518,"children":1519},{},[1520],{"type":45,"value":1521},"Cost guardrail.",{"type":45,"value":1523}," Recommend a spending limit before the user's first QPU run, when the user asks what a workload costs, or when one request fans out across several devices or a large shot count. Spending limits may already exist in the customer's account. In general, enforce QPU spend caps with spending limits.",{"type":40,"tag":415,"props":1525,"children":1526},{},[1527,1532],{"type":40,"tag":105,"props":1528,"children":1529},{},[1530],{"type":45,"value":1531},"Secrets.",{"type":45,"value":1533}," Hyperparameters are stored in job metadata and echoed into the job's\nCloudWatch log stream at container boot, so never pass a secret as a hyperparameter —\nfetch it from Secrets Manager or SSM Parameter Store inside the algorithm script.\nRestrict read access to the job log groups accordingly.",{"type":40,"tag":55,"props":1535,"children":1536},{},[1537,1539,1546],{"type":45,"value":1538},"For details, see the ",{"type":40,"tag":119,"props":1540,"children":1543},{"href":1541,"rel":1542},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fsecurity.html",[221],[1544],{"type":45,"value":1545},"Amazon Braket security documentation",{"type":45,"value":455},{"type":40,"tag":48,"props":1548,"children":1550},{"id":1549},"reference-links",[1551],{"type":45,"value":1552},"Reference links",{"type":40,"tag":55,"props":1554,"children":1555},{},[1556],{"type":45,"value":1557},"Authoritative sources — prefer these over recalled details, since device ARNs, quotas, prices, and supported features change.",{"type":40,"tag":55,"props":1559,"children":1560},{},[1561,1566],{"type":40,"tag":105,"props":1562,"children":1563},{},[1564],{"type":45,"value":1565},"Official documentation",{"type":45,"value":1567}," (stable entry points — navigate\u002Fsearch from here)",{"type":40,"tag":411,"props":1569,"children":1570},{},[1571,1582,1593,1604,1615,1625,1636,1647,1657,1668,1686],{"type":40,"tag":415,"props":1572,"children":1573},{},[1574,1576],{"type":45,"value":1575},"Developer Guide — ",{"type":40,"tag":119,"props":1577,"children":1580},{"href":1578,"rel":1579},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fwhat-is-braket.html",[221],[1581],{"type":45,"value":1578},{"type":40,"tag":415,"props":1583,"children":1584},{},[1585,1587],{"type":45,"value":1586},"Prerequisites & account setup — ",{"type":40,"tag":119,"props":1588,"children":1591},{"href":1589,"rel":1590},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-get-started.html",[221],[1592],{"type":45,"value":1589},{"type":40,"tag":415,"props":1594,"children":1595},{},[1596,1598],{"type":45,"value":1597},"How Amazon Braket works — ",{"type":40,"tag":119,"props":1599,"children":1602},{"href":1600,"rel":1601},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-how-it-works.html",[221],[1603],{"type":45,"value":1600},{"type":40,"tag":415,"props":1605,"children":1606},{},[1607,1609],{"type":45,"value":1608},"API Reference — ",{"type":40,"tag":119,"props":1610,"children":1613},{"href":1611,"rel":1612},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002FAPIReference\u002FWelcome.html",[221],[1614],{"type":45,"value":1611},{"type":40,"tag":415,"props":1616,"children":1617},{},[1618,1620],{"type":45,"value":1619},"Python SDK API docs — ",{"type":40,"tag":119,"props":1621,"children":1623},{"href":669,"rel":1622},[221],[1624],{"type":45,"value":669},{"type":40,"tag":415,"props":1626,"children":1627},{},[1628,1630],{"type":45,"value":1629},"Getting started — ",{"type":40,"tag":119,"props":1631,"children":1634},{"href":1632,"rel":1633},"https:\u002F\u002Faws.amazon.com\u002Fbraket\u002Fgetting-started\u002F",[221],[1635],{"type":45,"value":1632},{"type":40,"tag":415,"props":1637,"children":1638},{},[1639,1641],{"type":45,"value":1640},"OpenQASM 3.0 spec — ",{"type":40,"tag":119,"props":1642,"children":1645},{"href":1643,"rel":1644},"https:\u002F\u002Fopenqasm.com\u002Fversions\u002F3.0\u002Findex.html",[221],[1646],{"type":45,"value":1643},{"type":40,"tag":415,"props":1648,"children":1649},{},[1650,1652],{"type":45,"value":1651},"OpenQASM on Braket — ",{"type":40,"tag":119,"props":1653,"children":1655},{"href":1229,"rel":1654},[221],[1656],{"type":45,"value":1229},{"type":40,"tag":415,"props":1658,"children":1659},{},[1660,1662],{"type":45,"value":1661},"Supported OpenQASM features (pragmas, verbatim rules, dynamic circuits) — ",{"type":40,"tag":119,"props":1663,"children":1666},{"href":1664,"rel":1665},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fbraket\u002Flatest\u002Fdeveloperguide\u002Fbraket-openqasm-supported-features.html",[221],[1667],{"type":45,"value":1664},{"type":40,"tag":415,"props":1669,"children":1670},{},[1671,1673,1678,1680],{"type":45,"value":1672},"boto3 ",{"type":40,"tag":261,"props":1674,"children":1676},{"className":1675},[],[1677],{"type":45,"value":517},{"type":45,"value":1679}," client — ",{"type":40,"tag":119,"props":1681,"children":1684},{"href":1682,"rel":1683},"https:\u002F\u002Fdocs.aws.amazon.com\u002Fboto3\u002Flatest\u002Freference\u002Fservices\u002Fbraket.html",[221],[1685],{"type":45,"value":1682},{"type":40,"tag":415,"props":1687,"children":1688},{},[1689,1691],{"type":45,"value":1690},"Security — ",{"type":40,"tag":119,"props":1692,"children":1694},{"href":1541,"rel":1693},[221],[1695],{"type":45,"value":1541},{"type":40,"tag":55,"props":1697,"children":1698},{},[1699,1701,1706,1708,1714],{"type":45,"value":1700},"For anything not covered here, ",{"type":40,"tag":105,"props":1702,"children":1703},{},[1704],{"type":45,"value":1705},"search the documentation",{"type":45,"value":1707}," rather than guessing page slugs or recalling details: if the AWS MCP server is available, its ",{"type":40,"tag":261,"props":1709,"children":1711},{"className":1710},[],[1712],{"type":45,"value":1713},"aws___search_documentation",{"type":45,"value":1715}," tool can help; otherwise start from the Developer Guide or API Reference above and navigate.",{"type":40,"tag":55,"props":1717,"children":1718},{},[1719],{"type":40,"tag":105,"props":1720,"children":1721},{},[1722],{"type":45,"value":1723},"GitHub",{"type":40,"tag":411,"props":1725,"children":1726},{},[1727,1744,1761],{"type":40,"tag":415,"props":1728,"children":1729},{},[1730,1736,1738],{"type":40,"tag":261,"props":1731,"children":1733},{"className":1732},[],[1734],{"type":45,"value":1735},"amazon-braket-sdk-python",{"type":45,"value":1737}," (core SDK) — ",{"type":40,"tag":119,"props":1739,"children":1742},{"href":1740,"rel":1741},"https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-sdk-python",[221],[1743],{"type":45,"value":1740},{"type":40,"tag":415,"props":1745,"children":1746},{},[1747,1753,1755],{"type":40,"tag":261,"props":1748,"children":1750},{"className":1749},[],[1751],{"type":45,"value":1752},"amazon-braket-schemas-python",{"type":45,"value":1754}," (schemas and models for public Braket data) — ",{"type":40,"tag":119,"props":1756,"children":1759},{"href":1757,"rel":1758},"https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-schemas-python",[221],[1760],{"type":45,"value":1757},{"type":40,"tag":415,"props":1762,"children":1763},{},[1764,1770,1772],{"type":40,"tag":261,"props":1765,"children":1767},{"className":1766},[],[1768],{"type":45,"value":1769},"amazon-braket-examples",{"type":45,"value":1771}," — ",{"type":40,"tag":119,"props":1773,"children":1776},{"href":1774,"rel":1775},"https:\u002F\u002Fgithub.com\u002Famazon-braket\u002Famazon-braket-examples",[221],[1777],{"type":45,"value":1774},{"type":40,"tag":1779,"props":1780,"children":1781},"style",{},[1782],{"type":45,"value":1783},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1785,"total":1889},[1786,1803,1818,1833,1848,1858,1873],{"slug":1787,"name":1787,"fn":1788,"description":1789,"org":1790,"tags":1791,"stars":21,"repoUrl":22,"updatedAt":1802},"agents-build","add capabilities to existing agent projects","Use to extend an existing agent project with memory, app integration, VPC, multi-agent, migration, model, browser, code interpreter, payments, or resource removal. Triggers: \"add memory\", \"remember across sessions\", \"call agent from app\", \"invoke agent from code\", \"agent auth\", \"streaming\", \"VPC\", \"VPC connectivity\", \"can't reach from VPC\", \"multi-agent\", \"A2A\", \"A2A auth\", \"orchestrator not delegating\", \"specialist not called\", \"migrate Bedrock Agent\", \"migration issue\", \"change model\", \"browser tool\", \"code interpreter\", \"delete agent\", \"tear down\", \"agentcore remove\", \"cross-account memory\", \"add payments capability to my agent\", \"wire payments plugin\", \"integrate x402 payments with the agent I'm building\", \"add MPP payments\", \"Machine Payments Protocol\". External APIs via Gateway: use agents-connect. New project: use agents-get-started. CLI\u002Fdev-server errors: use agents-debug. Runtime x402\u002FMPP payments: use agents-pay. Migration-specific Strands vs LangGraph routes here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1792,1795,1798,1799],{"name":1793,"slug":1794,"type":15},"Agents","agents",{"name":1796,"slug":1797,"type":15},"Automation","automation",{"name":17,"slug":8,"type":15},{"name":1800,"slug":1801,"type":15},"Engineering","engineering","2026-08-20T03:27:06.137661",{"slug":1804,"name":1804,"fn":1805,"description":1806,"org":1807,"tags":1808,"stars":21,"repoUrl":22,"updatedAt":1817},"agents-connect","connect agents to external services","Use when connecting your agent to external APIs, tools, or services via Gateway, or restricting tool access with Cedar policies. Handles gateway setup, target types, outbound auth (OAuth, API key, IAM), credentials, and Cedar policy authoring. Triggers on: \"connect to API\", \"add gateway\", \"connect to MCP server\", \"Lambda tools\", \"OpenAPI\", \"gateway target\", \"Cedar policy\", \"restrict tools\", \"policy engine\", \"gateway auth error\", \"store API key\", \"outbound credential\", \"env var API key\", \"API key None after deploy\", \"credential not available after deploy\", \"should this be a gateway target\", \"give my agent tools\", \"add tools to agent\". Not for inbound auth (who can call your agent) — use agents-harden. Not for debugging agent behavior — use agents-debug. Not for VPC networking errors (agent can't reach APIs due to VPC) — use agents-build. Not for creating or hosting a new MCP server project — use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1809,1810,1813,1816],{"name":1793,"slug":1794,"type":15},{"name":1811,"slug":1812,"type":15},"API Development","api-development",{"name":1814,"slug":1815,"type":15},"Authentication","authentication",{"name":17,"slug":8,"type":15},"2026-07-16T06:00:38.866147",{"slug":1819,"name":1819,"fn":1820,"description":1821,"org":1822,"tags":1823,"stars":21,"repoUrl":22,"updatedAt":1832},"agents-debug","debug agent and environment issues","Use when your agent or environment is broken — wrong answers, errors, timeouts, tool failures, or CLI issues. Reads traces and logs to diagnose root causes. Also checks prerequisites when the CLI itself isn't working. Triggers on: \"agent not working\", \"wrong answer\", \"agent error\", \"tool call failing\", \"debug agent\", \"check logs\", \"read traces\", \"broken\", \"500 error\", \"424 error\", \"model access denied\", \"command not found\", \"stuck in DELETING\", \"maxVms exceeded\", \"cold start diagnosis\", \"cold start slow\", \"agentcore create error\", \"create failed\", \"exit code 7\", \"connection refused local dev\". Not for deploy failures — use agents-deploy. Not for performance tuning without errors — use agents-optimize. Not for VPC configuration — use agents-build. Not for observability setup or missing logs — use agents-optimize.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1824,1825,1826,1829],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1827,"slug":1828,"type":15},"Debugging","debugging",{"name":1830,"slug":1831,"type":15},"Observability","observability","2026-07-16T06:00:44.679093",{"slug":1834,"name":1834,"fn":1835,"description":1836,"org":1837,"tags":1838,"stars":21,"repoUrl":22,"updatedAt":1847},"agents-deploy","deploy AI agents to AWS","Use when deploying your agent to AWS, or when a deploy has failed. Handles pre-flight validation, CDK\u002FIAM\u002Fquota error diagnosis, version management, rollback, and canary deployments. Triggers on: \"deploy my agent\", \"agentcore deploy\", \"deploy failed\", \"CDK error\", \"rollback\", \"canary deploy\", \"pin version\", \"redeploy\", \"deploy stuck\". Not for production hardening — use agents-harden. Not for adding capabilities before deploy — use agents-build or agents-connect. Not for VPC configuration errors — use agents-build.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1839,1840,1841,1844],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1842,"slug":1843,"type":15},"CI\u002FCD","ci-cd",{"name":1845,"slug":1846,"type":15},"Deployment","deployment","2026-07-12T08:42:55.059577",{"slug":1849,"name":1849,"fn":1850,"description":1851,"org":1852,"tags":1853,"stars":21,"repoUrl":22,"updatedAt":1857},"agents-get-started","scaffold and deploy new agent projects","Use when a developer wants to create a new agent project or get started with AgentCore. Handles framework selection, project scaffolding, first deploy, and first invocation. Triggers on: \"build an agent\", \"create an agent\", \"get started\", \"new project\", \"agentcore create\", \"which framework\", \"Strands vs LangGraph\", \"hello world agent\", \"first agent\", \"create MCP server\", \"host MCP server\", \"agentcore dev\", \"dev server\", \"what port\", \"local development\". Not for adding capabilities to existing projects — use agents-build or agents-connect. Strands vs LangGraph in a migration context routes to agents-build, not here. Connecting to an existing MCP server routes to agents-connect, not here.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1854,1855,1856],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1845,"slug":1846,"type":15},"2026-07-12T08:42:51.963247",{"slug":1859,"name":1859,"fn":1860,"description":1861,"org":1862,"tags":1863,"stars":21,"repoUrl":22,"updatedAt":1872},"agents-harden","harden agents for production","Use when preparing your agent for production — IAM scoping, inbound auth (JWT, SigV4), secrets management, cold start optimization, session lifecycle, rate limiting, input validation, and quota guidance. Triggers on: \"production checklist\", \"harden agent\", \"production ready\", \"secure agent\", \"inbound auth\", \"going live\", \"cold start optimization\", \"session lifecycle\", \"StopRuntimeSession\", \"quota\", \"throttling\", \"maxVms\", \"rate limit\", \"security audit of outbound API calls\", \"gateway target audit for production\", \"restrict who can call\", \"lock down endpoint\", \"only our app can call\". Not for Cedar tool-restriction policies — use agents-connect. Not for quality measurement — use agents-optimize. Not for outbound credential storage or API key wiring — use agents-connect. Not for A2A agent-to-agent auth — use agents-build. Cold start observation and diagnosis (not optimization) routes to agents-debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1864,1865,1866,1869],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1867,"slug":1868,"type":15},"Best Practices","best-practices",{"name":1870,"slug":1871,"type":15},"Security","security","2026-07-16T06:00:42.174705",{"slug":1874,"name":1874,"fn":1875,"description":1876,"org":1877,"tags":1878,"stars":21,"repoUrl":22,"updatedAt":1888},"agents-optimize","optimize agent quality and performance","Use when measuring or improving agent quality and performance — set up evaluators, online monitoring, CI\u002FCD quality gates, observability, or cost optimization. Triggers on: \"evaluate my agent\", \"add evaluator\", \"measure quality\", \"quality gate\", \"run evals\", \"agent too slow\", \"why is it slow\", \"reduce latency\", \"set up observability\", \"CloudWatch dashboard\", \"how much does my agent cost\", \"cost optimization\", \"logs not showing up\", \"logs missing\", \"spans not found\", \"eval failing\", \"eval error\", \"dev traces\", \"local traces\", \"agentcore dev traces\", \"traces to CloudWatch\". Not for debugging errors or crashes — use agents-debug. Slow but correct routes here; broken routes to debug.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1879,1880,1881,1884,1885],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1882,"slug":1883,"type":15},"Evals","evals",{"name":1830,"slug":1831,"type":15},{"name":1886,"slug":1887,"type":15},"Performance","performance","2026-07-12T08:42:56.488105",122,{"items":1891,"total":2003},[1892,1899,1906,1913,1920,1926,1933,1941,1955,1972,1985,1997],{"slug":1787,"name":1787,"fn":1788,"description":1789,"org":1893,"tags":1894,"stars":21,"repoUrl":22,"updatedAt":1802},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1895,1896,1897,1898],{"name":1793,"slug":1794,"type":15},{"name":1796,"slug":1797,"type":15},{"name":17,"slug":8,"type":15},{"name":1800,"slug":1801,"type":15},{"slug":1804,"name":1804,"fn":1805,"description":1806,"org":1900,"tags":1901,"stars":21,"repoUrl":22,"updatedAt":1817},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1902,1903,1904,1905],{"name":1793,"slug":1794,"type":15},{"name":1811,"slug":1812,"type":15},{"name":1814,"slug":1815,"type":15},{"name":17,"slug":8,"type":15},{"slug":1819,"name":1819,"fn":1820,"description":1821,"org":1907,"tags":1908,"stars":21,"repoUrl":22,"updatedAt":1832},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1909,1910,1911,1912],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1827,"slug":1828,"type":15},{"name":1830,"slug":1831,"type":15},{"slug":1834,"name":1834,"fn":1835,"description":1836,"org":1914,"tags":1915,"stars":21,"repoUrl":22,"updatedAt":1847},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1916,1917,1918,1919],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1842,"slug":1843,"type":15},{"name":1845,"slug":1846,"type":15},{"slug":1849,"name":1849,"fn":1850,"description":1851,"org":1921,"tags":1922,"stars":21,"repoUrl":22,"updatedAt":1857},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1923,1924,1925],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1845,"slug":1846,"type":15},{"slug":1859,"name":1859,"fn":1860,"description":1861,"org":1927,"tags":1928,"stars":21,"repoUrl":22,"updatedAt":1872},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1929,1930,1931,1932],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1867,"slug":1868,"type":15},{"name":1870,"slug":1871,"type":15},{"slug":1874,"name":1874,"fn":1875,"description":1876,"org":1934,"tags":1935,"stars":21,"repoUrl":22,"updatedAt":1888},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1936,1937,1938,1939,1940],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1882,"slug":1883,"type":15},{"name":1830,"slug":1831,"type":15},{"name":1886,"slug":1887,"type":15},{"slug":1942,"name":1942,"fn":1943,"description":1944,"org":1945,"tags":1946,"stars":21,"repoUrl":22,"updatedAt":1954},"agents-pay","handle x402 payments for agent tasks","Use when THIS agent needs to pay for x402-protected content at runtime: hitting a paywall mid-task, settling it via AgentCore Payments, and applying operator-defined spend limits. Covers payment setup, policy, session budgets, and troubleshooting. Triggers on: \"my agent hit a 402 while calling an API\", \"a tool call returned 402 Payment Required\", \"my agent needs to pay for x402-protected content\", \"let the agent pay for content, capped at $5 per session\", \"set a spend limit for the agent\", \"ProcessPayment failed\", or \"why did my agent refuse to pay\". Not for BUILDING payment capability for end users, including wallets and framework middleware; use agents-build and references\u002Fpayments.md. For non-paid APIs via Gateway use agents-connect. For inbound auth use agents-harden. For project scaffolding use agents-get-started.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1947,1948,1949,1952],{"name":1793,"slug":1794,"type":15},{"name":1796,"slug":1797,"type":15},{"name":1950,"slug":1951,"type":15},"Payments","payments",{"name":1953,"slug":1953,"type":15},"x402","2026-08-10T04:16:31.844309",{"slug":1956,"name":1956,"fn":1957,"description":1958,"org":1959,"tags":1960,"stars":21,"repoUrl":22,"updatedAt":1971},"amazon-aurora-mysql","manage Amazon Aurora MySQL clusters","Amazon Aurora MySQL — creates, modifies, and advises on Aurora MySQL clusters specifically (MySQL-compatible engine, Aurora serverless, parallel query). Trigger for Aurora MySQL cluster operations, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or MySQL upgrade planning. Aurora MySQL uses full (VPC-based) configuration — express configuration is PostgreSQL-only. For Aurora PostgreSQL, use amazon-aurora-postgresql instead. Contains safety guardrails and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1961,1962,1965,1968],{"name":17,"slug":8,"type":15},{"name":1963,"slug":1964,"type":15},"Database","database",{"name":1966,"slug":1967,"type":15},"MySQL","mysql",{"name":1969,"slug":1970,"type":15},"Serverless","serverless","2026-07-12T08:43:13.27939",{"slug":1973,"name":1973,"fn":1974,"description":1975,"org":1976,"tags":1977,"stars":21,"repoUrl":22,"updatedAt":1984},"amazon-aurora-postgresql","configure Amazon Aurora PostgreSQL clusters","Amazon Aurora PostgreSQL — creates, modifies, and advises on Aurora PostgreSQL clusters specifically (PostgreSQL-compatible engine, Aurora serverless, express configuration, pgvector, Babelfish). Trigger for Aurora PostgreSQL cluster operations, express-configuration quick-start, ACU sizing, I\u002FO-Optimized storage, commitment pricing, or PostgreSQL upgrade planning. For Aurora MySQL, use amazon-aurora-mysql instead. Contains safety guardrails, express-first routing, and response templates that override defaults.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1978,1979,1980,1983],{"name":17,"slug":8,"type":15},{"name":1963,"slug":1964,"type":15},{"name":1981,"slug":1982,"type":15},"PostgreSQL","postgresql",{"name":1969,"slug":1970,"type":15},"2026-07-16T06:00:34.789624",{"slug":1986,"name":1986,"fn":1987,"description":1988,"org":1989,"tags":1990,"stars":21,"repoUrl":22,"updatedAt":1996},"amazon-bedrock","build generative AI apps with Amazon Bedrock","Builds generative AI applications on Amazon Bedrock. Covers model invocation (Converse API, InvokeModel), RAG with Knowledge Bases, Bedrock Agents, Guardrails, and AgentCore (including the Harness managed agent loop). Use when invoking models, setting up Knowledge Bases, creating agents, applying guardrails, deploying to AgentCore, migrating\u002Fporting\u002Fconverting a Bedrock Agent (including inline agents) to an AgentCore Harness, troubleshooting Bedrock errors (ThrottlingException, AccessDeniedException), or choosing models (Claude, Llama, Nova, Titan). ALSO USE for prompt caching, quota health checks and throttling diagnosis, cost attribution, migrating between Claude model generations, chunking strategies, API selection (Converse vs InvokeModel), and model selection. Also covers AgentCore Payments setup (x402, microtransactions, Payment Manager, Coinbase CDP, Stripe Privy, 402 Payment Required, paid endpoint). NOT for custom model training, Rekognition, or Comprehend.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1991,1992,1993],{"name":1793,"slug":1794,"type":15},{"name":17,"slug":8,"type":15},{"name":1994,"slug":1995,"type":15},"LLM","llm","2026-08-07T04:38:13.03499",{"slug":4,"name":4,"fn":5,"description":6,"org":1998,"tags":1999,"stars":21,"repoUrl":22,"updatedAt":23},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[2000,2001,2002],{"name":17,"slug":8,"type":15},{"name":19,"slug":20,"type":15},{"name":13,"slug":14,"type":15},139]