gmanch94

Designs a Microsoft Foundry (formerly Azure AI Foundry) footprint on Azure — surface map, model catalog (1,900+ via Azure OpenAI + partners), Agent Service (GA Mar 16 2026), private networking (BYO VNet), Foundry IQ + Azure AI Search, safety stack (Prompt Shields + Groundedness), cost model (PTU / PAYG / Batch), lock-in posture. Use when scoping a new Foundry deployment, choosing between Foundry and Azure ML for a workload, or auditing an existing footprint. Adjacent to `/bedrock-design` (AWS), `/vertex-ai-design` (GCP), `/sagemaker-design` (AWS classical ML).

Designs an Amazon Bedrock footprint on AWS — service split (Models / AgentCore / Knowledge Bases / Guardrails / Flows / Prompt Mgmt / IPR / Eval / Custom Import), model selection (Claude / Nova 2 / Llama / Mistral / Cohere / AI21), inference pattern (on-demand / PT / batch / cross-region), agent runtime (AgentCore vs Bedrock Agents vs Flows), guardrails posture (incl. Automated Reasoning), routing + cost (IPR), MLOps wiring, and lock-in posture. Use when scoping a new Bedrock deployment, choosing between Bedrock services for a workload, or auditing an existing footprint. Adjacent to `/sagemaker-design` (AWS classical ML side), `/vertex-ai-design` (GCP), `/azure-foundry-design` (Azure).

Designs an OpenAI platform footprint — API surface (Responses API as default; Assistants sunset 2026-08-26; Chat Completions feature-frozen on GPT-5.4+ reasoning models), model catalog (GPT-5.5/5.4/4.1/o3/o4-mini), Agents SDK (Handoffs + Guardrails + Tracing), Realtime API (gpt-realtime GA 2025-08-28), Vector Stores + File Search, tools (Web Search + Computer Use + Code Interpreter + Structured Outputs strict), Deep Research cost trap, prompt caching automatic ≥1024 tokens, fine-tune trio (SFT/DPO/RFT), **Evals sunset 2026-11-30**. Use when building on OpenAI directly (not Azure OpenAI). Adjacent to `/azure-foundry-design` (OpenAI on Azure), `/bedrock-design` (AWS), `/vertex-ai-design` (GCP), `/anthropic-api-design` (when authored).

Designs a Vertex AI footprint on Google Cloud — service split (Workbench / Pipelines / Training / Endpoints / Feature Store / Model Garden / Model Monitoring), compute selection, MLOps wiring, deployment pattern (online vs batch vs streaming), cost guardrails, and observability. Use when scoping a new Vertex deployment, choosing between Vertex services for a workload, or auditing an existing Vertex footprint. Adjacent to `/databricks-asset-bundles` + `/databricks-model-serving` (Databricks side) and `/sagemaker-design` (AWS side).

Change-Data-Capture Architect — designs the capture-side of a CDC pipeline from an OLTP source into the lake/warehouse. Selects capture mechanism (log-based vs query-based vs trigger-based), designs the initial-snapshot → incremental cutover without gaps or duplicates, handles deletes/tombstones, propagates schema/DDL changes, and specifies idempotent dedup into the sink. Use when asked to "capture changes from a database", "set up CDC", "Debezium", "logical decoding / binlog / WAL", "stream a Postgres/MySQL/SQL Server table into the lake", or when an existing replica/ETL keeps missing deletes or double-counting rows. Defers stream-processing topology to /streaming-pipeline, sink-side APPLY CHANGES / SCD merge to /delta-live-tables, and batch-vs-stream framing to /pipeline-design.

Designs distribution-free uncertainty quantification via conformal prediction — prediction SETS for classification and prediction INTERVALS for regression with a finite-sample coverage guarantee at 1−alpha. Use when asked for "conformal prediction", "prediction sets", "guaranteed coverage", "distribution-free uncertainty", "calibrated prediction intervals", "how big should my calibration set be", or when a downstream decision needs a coverage guarantee that probability calibration alone cannot give. Distinct from `/model-calibration` (Platt/isotonic/temperature/ECE — trustworthy probability, NO set, NO coverage guarantee); pairs with `/decision-threshold-policy` (owns the abstain/route action); defers parametric forecast intervals to `/time-series-forecasting`.

Doc-CI gate for repos whose deliverable includes a document set. Scans for (1) count drift across README/CLAUDE.md/NEXT_SESSION.md/prompts indices, (2) broken relative links, (3) skill↔prompt↔CLAUDE.md↔README↔prompts/README parity, (4) ungraded external facts, (5) markdown table pipe-integrity (stray-pipe phantom tables). Severity-grouped report. Use BEFORE shipping any docs commit, AFTER adding a skill/prompt/hook, and as a pre-commit gate. Pair with `.github/workflows/doc-ci.yml` for CI enforcement.

Designs a Data Loss Prevention (DLP) system — data classification, egress-surface enumeration, detection technique per class, enforcement per (class × surface), policy engine, and response/audit. Use when asked to prevent data exfiltration/leakage, design DLP controls, stop secrets/PII/PHI/PCI from leaving a system, or gate data egress (prompts, model output, tool actions, logs, network, files, third-party APIs).

Audit a Google ADK tool file against the five known gotchas (DI params, thin wrappers, _j helper, async-wrap blocking calls, httpx context manager) before they bite in production

After creating an ADR, run the cross-referencing checklist — update README Artifacts table, add Related Decisions section to source proposal, cross-link sibling ADRs to each other

Mid-task durability — dump current state and a next-step file before context fills, so the next session resumes without re-deriving where you were

Generate and verify a pre-demo checklist for an ADK/agent project — env vars, GCP auth, embedding swap, ngrok/Slack wiring, dry-run, tests, real-vs-synthetic data

Scan a project's docs (README, CLAUDE.md, ADRs, runbooks) for inconsistent project naming, scope, or framing — catches the "README says retail, CLAUDE.md still says Kroger" class of bug

Refresh a project's status — derive current state from code/tests/git, regenerate the project's status memory entry and (if requested) a status section in the README

Generate a new Architecture Decision Record from a topic, decision description, or rough notes

Design a full agentic system — loop architecture, tool manifest, memory, guardrails, observability

Walk every doc surface (README, CLAUDE.md, docs/prd/, docs/adr/, docs/architecture.md, docs/runbook.md, docs/solution.md, docs/lessons.md) and surface drift against current code. Use after any sizeable change to src/agora/saga/, src/agora/api/, src/agora/agents/, src/agora/models/, src/agora/config.py, Makefile, alembic/versions/, or .github/workflows/ — or when the user asks "are the docs still accurate", "check for doc drift", "stale-check the PRDs", or before tagging a release. Outputs a punch list of file:line drift candidates rather than rewriting docs autonomously.

Add a new state or step to the Agora ILL lifecycle without breaking saga invariants. Use when the user asks to add a state (e.g. "Held", "Renewed", "Lost"), add a forward+compensator pair, or extend the state machine. Walks through every file that must change in lockstep and writes the skeletons.

Scaffold a new outbox target handler (NCIP, webhook, peer relay, etc.) following the commit-then-enqueue pattern from ADR-0011. Use when adding a new external system that saga steps need to dispatch to asynchronously, when the user asks to "wire up an outbox handler for X", or when extending the OutboxWorker registry. Walks the developer through the handler signature, idempotency-key contract, lifespan registration, and the test pattern.

Run a security audit pass over agora — Bandit on src/agora/, pip-audit on locked deps, detect-secrets sweep, plus agora-specific concerns (ReShare Basic auth, NCIP creds, OpenURL targets, saga-event payload sanitization). Use when reviewing security before a milestone, after touching auth/credentials, before opening agora to a real ReShare tenant, or when CLAUDE.md known-gaps lists an unverified surface that touches credentials.

Validate an ISO 18626 XML payload against the published XSD. Use when reviewing/generating peer-facing wire messages, before flipping `RESHARE_ENABLED=true`, or when a peer reports a schema rejection. Catches the common 2021-revision pitfalls (DeliveryMethod rename, namespace drift, missing required header fields).

Bootstrap a new Architecture Decision Record under `docs/adr/` with the project's standard template, the next sequential number, and consistent Status/Context/Decision/Consequences sections. Use when the user makes a non-trivial design decision worth locking in (anything that would be expensive to reverse later).

Add a new rule to `PolicyAgent` (CONTU-style copyright, patron eligibility, budget, ISO 18626 cost cap, etc.) with consistent code, tests, and rationale-string format. Use when extending `src/agora/agents/policy.py`.

Probe a running FOLIO/ReShare (mod-rs) instance to verify the actual endpoint paths, request/response shapes, and idempotency-header handling — then diff against `HttpReShareClient` in `src/agora/clients/reshare.py`. Use before flipping `reshare_enabled=true` against a real instance, or when an integration error suggests our endpoint guesses are wrong.