Use when writing Java code with `dev.axllm:ax` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.
Use when writing Java code with `dev.axllm:ax` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
Use when ALM, DevOps, pipelines, releases, builds, deployments, rollback, branch strategy, or environment release governance.
Use when setting up, checking, explaining, or troubleshooting AX SQL, Azure DevOps, LCS, D365FO OData/metadata, usage telemetry, GitHub export, or connector environment variables…
Use when enterprise architects, portfolio architects, capability owners, platform architects, or architecture boards need AX to D365FO capability maps, application portfolio…
Use when regression testing, end-to-end testing, retesting, risk-based regression suite, or repeat validation needs.
Use when writing Python code with `axllm` for agents, child delegation, tools, MCP, clarification, runtime state, final typed responses, and direct-respond executor skipping.
Use when writing Python code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.
Use when writing Python code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
Use when writing Python code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
Use when writing Python code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.
Use when writing Python code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.
Use when writing Python code with `axllm` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers,…
Use when writing Python code with `axllm` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.
Use when writing Python code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
Use when writing Python code with `axllm` for AxGen programs, forward calls, indexed multi-sampling, result pickers, streaming, tools, assertions, traces, usage, and output…
Use when writing Python code with `axllm` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.
Use when writing Python code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.
Use when writing Python code with `axllm` for the playbook() context-engineering surface, evolving task knowledge, online updates, and rendering a playbook into a program.
Use when writing Python code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.
Use when writing Python code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
Use when writing Rust code with `axllm` for agents, child delegation, tools, MCP, citations, persistent playbook learning, stage instructions, runtime state, final typed…
Use when writing Rust code with `axllm` for deciding between context maps, trajectory context policy, offline optimization (ACE/GEPA), and memory recall for long-context agents.
Use when writing Rust code with `axllm` for agent memory, recall callbacks, dynamic skill discovery, loaded-skill state, and used-skill tracking.
Use when writing Rust code with `axllm` for agent tracing, centralized and multi-tenant usage accounting, action logs, runtime diagnostics, replay, and production debugging.
Use when writing Rust code with `axllm` for agent optimization, verified agent-playbook evolution, evaluators, judges, optimizer artifacts, BootstrapFewShot, and GEPA.
Use when writing Rust code with `axllm` for RLM executor loops, AxCodeRuntime sessions, runtime envelopes, process runtimes, and optional runtime profiles.
Use when writing Rust code with `axllm` for named deployment profiles, generic provider clients, model selection, OpenAI-compatible calls, Responses, Gemini, Anthropic, routers,…
Use when writing Rust code with `axllm` for audio input/output, OpenAI Responses audio mapping, realtime event folding, and generated package audio examples.
Use when writing Rust code with `axllm` for flows, nodes, program graphs, nested programs, dynamic options, caching, and optimizer components.
Use when writing Rust code with `axllm` for AxGen programs, forward calls, streaming, tools, assertions, traces, usage, and output parsing.
Use when writing Rust code with `axllm` for GEPA, Pareto tradeoffs, reflection clients, metric budgets, optimizer state, and artifacts.
Use when writing Rust code with `axllm` for using the generated Ax package, factory functions, package docs, examples, and API reference.
Use when writing Rust code with `axllm` for the playbook() context-engineering surface, agent-bound verified evolution, run-end learning, online updates, and rendering a playbook…
Use when writing Rust code with `axllm` for reward-scored generation, iterative candidate improvement, evaluator feedback, and optimizer-backed refinement patterns.
Use when writing Rust code with `axllm` for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.
First-principles assumption auditor. Classifies each hidden assumption (fact / convention / belief / interest-driven), ranks by fragility × impact, and rebuilds conclusio — from…
Use when the user mentions Swift performance audit, code optimization, or performance review.
Use when the user mentions flaky tests, tests that pass locally but fail in CI, race conditions in tests, or needs to diagnose WHY a specific test fails.
Use when integrating App Intents for Siri, Apple Intelligence, Shortcuts, Spotlight, or system experiences - covers AppIntent, AppEntity, parameter handling, entity queries,…
Use when implementing App Shortcuts for instant Siri/Spotlight availability, configuring AppShortcutsProvider, adding suggested phrases, or debugging shortcuts not appearing -…
Use when the user mentions SwiftUI architecture review, separation of concerns, testability issues, or "logic in view" problems.
Use when the user mentions SwiftUI navigation issues, deep linking problems, state restoration bugs, or navigation architecture review.
Use when the user wants to audit test quality, find flaky test patterns, speed up test execution, or prepare for Swift Testing migration.
Use when encountering "Unable to simultaneously satisfy constraints" errors, constraint conflicts, ambiguous layout warnings, or views positioned incorrectly - systematic…
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
Use when encountering dependency conflicts, CocoaPods/SPM resolution failures, "Multiple commands produce" errors, or framework version mismatches - systematic dependency and…
Use when build times are slow, investigating build performance, analyzing Build Timeline, identifying type checking bottlenecks, enabling compilation caching, or optimizing…
Use when choosing between CloudKit vs iCloud Drive, implementing reliable sync, handling offline-first patterns, or designing sync architecture - prevents common sync mistakes…
Use when debugging 'file not syncing', 'CloudKit error', 'sync conflict', 'iCloud upload failed', 'ubiquitous item error', 'data not appearing on other devices', 'CKError', 'quota…
Use when profiling async/await performance, diagnosing actor contention, or investigating thread pool exhaustion.
Use when debugging schema migration crashes, concurrency thread-confinement errors, N+1 query performance, SwiftData to Core Data bridging, or testing migrations without data loss…
Use this agent for closed-loop test debugging - automatically analyzes test failures, suggests fixes, and re-runs tests until passing.
Use when adding debug-only deep links for testing, enabling simulator navigation to specific screens, or integrating with automated testing workflows - enables closed-loop…
Use when debugging Foundation Models issues — context exceeded, guardrail violations, slow generation, availability problems, unsupported language, or unexpected output — from…
Use when debugging Foundation Models issues — context exceeded, guardrail violations, slow generation, availability problems, unsupported language, or unexpected output — from…
Use when implementing in-app purchases, StoreKit 2, subscriptions, or transaction handling - testing-first workflow with .storekit configuration, StoreManager architecture,…
Use when ANY iOS build fails, test crashes, Xcode misbehaves, or environment issue occurs before debugging code.
Use when implementing or debugging ANY network connection, API call, or socket. Covers URLSession, Network.framework, NetworkConnection, deprecated APIs, connection diagn — from…
Use when writing ANY test, debugging flaky tests, making tests faster, or asking about Swift Testing vs XCTest.