Database

Triggers when users need help with transfer learning, fine-tuning pretrained models, or parameter-efficient adaptation. Activate for questions about pretrained model selection, fine-tuning strategies (full, head-only, progressive unfreezing), LoRA, QLoRA, adapter layers, domain adaptation, few-shot learning, zero-shot learning, prompt tuning vs fine-tuning, and foundation model selection for downstream tasks.

Triggers when users need help with transformer model architectures, self-attention mechanisms, or positional encoding strategies. Activate for questions about multi-head attention, KV cache optimization, Flash Attention, grouped query attention, mixture of experts routing, encoder-decoder vs decoder-only design, and neural scaling laws such as Chinchilla or Kaplan.

Triggers when users need help with distributed ML training, including data parallelism (DDP, FSDP), model parallelism (tensor, pipeline), DeepSpeed ZeRO stages 1-3, Megatron-LM, 3D parallelism, communication backends (NCCL, Gloo), gradient compression, checkpoint strategies, fault tolerance, and elastic training.

Triggers when users need help with feature store architecture and implementation, including Feast, Tecton, and Hopsworks. Activate for questions about online vs offline feature serving, feature computation pipelines, point-in-time correctness, feature reuse, feature freshness, streaming features, and feature monitoring and drift detection.

Triggers when users need help with GPU infrastructure for ML workloads, including GPU cluster architecture (A100, H100, H200, B200), NVIDIA CUDA ecosystem, multi-GPU training setup, InfiniBand networking, NVLink, GPU memory management, spot instances for training, cloud GPU comparison across AWS, GCP, Azure, Lambda, and CoreWeave, and on-prem vs cloud cost analysis.

Triggers when users need help with ML inference optimization, including model quantization (INT8, INT4, GPTQ, AWQ, GGUF), pruning strategies, knowledge distillation, ONNX Runtime, TensorRT, operator fusion, batching strategies, speculative decoding, and KV cache optimization. Activate for questions about reducing model latency, improving throughput, or lowering inference costs.

Triggers when users need help with CI/CD for ML systems, including training pipelines, model validation, and deployment automation. Activate for questions about GitHub Actions or GitLab CI for ML, automated retraining triggers, model validation gates, deployment strategies (blue-green, canary, shadow), infrastructure as code for ML, and environment reproducibility with Docker, conda, and pip-tools.

Triggers when users need help with ML cost optimization, including compute cost management for training and inference, spot instance strategies, model size vs accuracy tradeoffs, right-sizing GPU instances, caching strategies, batch inference optimization, managed vs self-hosted infrastructure decisions, FinOps for ML teams, and cost attribution and chargeback models.

Triggers when users need help with ML experiment tracking, including Weights & Biases, MLflow, Neptune, or ClearML setup and configuration. Activate for questions about experiment organization, metric logging, artifact management, hyperparameter sweeps, team collaboration in experiment platforms, and cost tracking across training runs.

Triggers when users need help with ML model monitoring in production, including data drift detection (PSI, KL divergence, KS test), concept drift, model performance monitoring, prediction monitoring, alerting strategies, shadow mode deployment, ground truth collection, monitoring dashboards, and SLA management for ML systems.

Triggers when users need help with internal ML platform architecture and design, including self-serve ML infrastructure, platform team responsibilities, abstraction layers for data scientists, notebook-to-production workflows, multi-tenant ML platforms, platform metrics and adoption, and build vs buy decisions for ML tools.

Triggers when users need help with testing ML systems, including unit testing ML code, integration testing ML pipelines, data validation testing, model quality testing with regression tests and performance thresholds, training pipeline testing, serving endpoint testing, load testing for ML systems, test data management, and property-based testing for data transforms.

Triggers when users need help with model versioning and registry systems, including MLflow Model Registry, Weights & Biases, and SageMaker Model Registry. Activate for questions about model lifecycle management, staging and production transitions, approval workflows, model metadata and lineage, packaging formats, CI/CD integration, and model governance and compliance.

Triggers when users need help with model serving and deployment, including serving frameworks like TorchServe, Triton Inference Server, TensorFlow Serving, BentoML, or vLLM. Activate for questions about online vs batch vs streaming inference, REST and gRPC APIs, model warm-up, autoscaling, multi-model serving, A/B testing for models, and canary deployments.

Triggers when users need help with algorithm design, data structure selection, or complexity analysis. Activate for questions about Big-O notation, amortized analysis, sorting algorithms (quicksort, mergesort, radix sort, counting sort), search algorithms, hash tables, trees (BST, AVL, red-black, B-trees, tries), heaps, graph algorithms (DFS, BFS, Dijkstra, A*, topological sort, minimum spanning trees), dynamic programming patterns, greedy algorithms, or choosing the right data structure for a problem.

Triggers when users need help with compiler design, language implementation, or code generation. Activate for questions about lexical analysis, tokenization, regex engines, parsing (LL, LR, PEG), abstract syntax trees, semantic analysis, type checking, intermediate representations (SSA, three-address code), optimization passes (dead code elimination, loop unrolling, inlining), code generation, JIT compilation, garbage collection algorithms, or building interpreters and compilers.

Triggers when users need help with computational complexity theory or its practical implications. Activate for questions about P vs NP, complexity classes (P, NP, NP-complete, NP-hard, PSPACE, BPP), reductions, approximation algorithms, randomized algorithms, amortized analysis, space complexity, circuit complexity, decidability, the halting problem, or making engineering decisions based on problem hardness.

Triggers when users need help with computer architecture, hardware performance, or low-level optimization. Activate for questions about CPU pipeline stages, cache hierarchy (L1/L2/L3, cache coherence, MESI protocol), branch prediction, out-of-order execution, SIMD (SSE, AVX), memory hierarchy, NUMA architecture, GPU architecture (CUDA cores, warps, shared memory), DMA, storage hierarchy (NVMe, SSD internals), interconnects, or understanding how hardware affects software performance.

Triggers when users need help with computer networking concepts, protocols, or architecture. Activate for questions about TCP/IP, HTTP/1.1 vs HTTP/2 vs HTTP/3, QUIC, TLS handshake, DNS resolution, WebSockets, gRPC, load balancing (L4 vs L7), CDN architecture, network security, firewalls, DDoS mitigation, BGP, MTU, fragmentation, connection pooling, or debugging network issues.

Triggers when users need help with concurrent or parallel programming. Activate for questions about thread safety, mutexes, semaphores, condition variables, lock-free data structures, the actor model, CSP (communicating sequential processes), async/await patterns, coroutines, thread pools, parallel algorithms, memory models, happens-before relationships, deadlock prevention, work stealing, or reasoning about concurrent correctness and performance.

Triggers when users need help with cryptography concepts, protocols, or implementation decisions. Activate for questions about symmetric encryption (AES, ChaCha20), asymmetric encryption (RSA, elliptic curves), hash functions (SHA-256, BLAKE3), digital signatures, key exchange (Diffie-Hellman, ECDH), TLS/SSL, certificate chains, zero-knowledge proofs, homomorphic encryption, post-quantum cryptography, or choosing the right cryptographic primitives for a system.

Triggers when users need help with database internals, storage engines, or query optimization. Activate for questions about B-tree and LSM-tree storage engines, write-ahead logging (WAL), MVCC, query optimization (cost-based, rule-based), join algorithms (nested loop, hash join, sort-merge join), indexing strategies (B-tree, hash, GIN, GiST, BRIN), buffer pool management, transaction isolation levels, write amplification, or understanding how databases work under the hood.

Triggers when users need help with distributed systems design or debugging. Activate for questions about CAP theorem, consensus protocols (Paxos, Raft), distributed transactions (2PC, Saga pattern), replication strategies, consistent hashing, vector clocks, CRDTs, leader election, distributed locking, service mesh, circuit breakers, load balancing algorithms, backpressure, or reasoning about consistency and availability tradeoffs in multi-node systems.

Triggers when users need help with formal methods, formal verification, or rigorous specification. Activate for questions about model checking (TLA+, SPIN), property-based testing (QuickCheck, Hypothesis), theorem proving, invariant specification, temporal logic (LTL, CTL), design by contract, formal verification of concurrent systems, when to use formal methods vs testing, or applying lightweight formal methods in industry settings.

Triggers when users need help with information retrieval, search systems, or ranking algorithms. Activate for questions about inverted indexes, TF-IDF, BM25, vector search (approximate nearest neighbor, HNSW, IVF), embedding models for retrieval, hybrid search (lexical + semantic), relevance feedback, query understanding, faceted search, search ranking, evaluation metrics (NDCG, MRR, MAP), search infrastructure (Elasticsearch, Vespa), or building and optimizing search systems.

Triggers when users need help with operating system concepts, internals, or system-level programming. Activate for questions about process management, scheduling algorithms, IPC, signals, memory management, virtual memory, paging, TLB, file systems (ext4, ZFS, BTRFS), I/O models (blocking, non-blocking, async, epoll, kqueue), system calls, kernel architecture (monolithic vs microkernel), containers (cgroups, namespaces), or understanding how the OS manages hardware resources.

Triggers when users need help with programming language theory, type systems, or language design. Activate for questions about type systems (static vs dynamic, strong vs weak, gradual typing), type inference (Hindley-Milner), polymorphism (parametric, ad-hoc, subtyping), lambda calculus, functional programming principles (immutability, higher-order functions, monads), memory management models (garbage collection, ownership/borrowing, ARC), or understanding how language design choices affect program correctness and expressiveness.

Triggers when users need help with large-scale system design, architecture, or capacity planning. Activate for questions about system design methodology, capacity planning, back-of-envelope calculations, horizontal vs vertical scaling, caching strategies (CDN, application, database), message queues (Kafka, RabbitMQ, SQS), rate limiting, idempotency, eventual consistency patterns, observability (logs, metrics, traces), or designing systems that handle millions of users.

Triggers when users need help with LLM agent design, tool use, or multi-agent systems. Activate for questions about agent architectures (ReAct, plan-and-execute, reflexion), tool use and function calling, agent memory, multi-agent systems, agent evaluation, debugging, guardrails, safety for agents, agent frameworks (LangGraph, CrewAI, AutoGen), production agent deployment, and agent failure modes.

Triggers when users need help with LLM application design patterns and architectures. Activate for questions about classification with LLMs, extraction and structuring, summarization pipelines, code generation systems, chat application design, search augmented generation, document processing pipelines, multi-turn conversation management, LLM routing and model selection per query, and fallback strategies.

Triggers when users need help with LLM cost optimization, budgeting, or economic analysis. Activate for questions about token cost optimization, prompt compression, caching, model routing, API cost comparison across providers, self-hosted vs API tradeoffs, semantic caching, prompt deduplication, batch API usage, cost-per-task analysis, budget allocation across models, and cost monitoring and alerting.

Triggers when users need help with LLM evaluation, benchmarking, or assessment methodology. Activate for questions about MMLU, HumanEval, GSM8K, HellaSwag, ARC, TruthfulQA, MT-Bench, few-shot evaluation, zero-shot evaluation, chain-of-thought evaluation, LLM-as-judge, human evaluation protocols, contamination detection, evaluation harness setup, lm-eval-harness, and EleutherAI evaluation tools.

Triggers when users need help with LLM fine-tuning, adaptation, or specialization. Activate for questions about full fine-tuning, LoRA, QLoRA, prefix tuning, adapters, instruction tuning, dataset design, supervised fine-tuning pipelines, hyperparameter selection, catastrophic forgetting, domain adaptation, and continued pretraining vs fine-tuning decisions.

Triggers when users need help with LLM inference optimization, serving, or deployment performance. Activate for questions about KV cache management, continuous batching, speculative decoding, tensor parallelism, quantization (GPTQ, AWQ, GGUF, FP8), PagedAttention, vLLM, prefix caching, flash decoding, serving frameworks (TGI, TensorRT-LLM, SGLang), and throughput vs latency tradeoffs.

Triggers when users need help with LLM pretraining, data curation, or training infrastructure. Activate for questions about Common Crawl processing, deduplication, quality filtering, toxicity removal, tokenizer design (BPE, SentencePiece, Unigram), distributed training, checkpointing, scaling laws, Chinchilla, compute-optimal training, curriculum learning, data mixing ratios, training stability, loss spikes, and gradient norm monitoring.

Triggers when users need help with LLM safety, guardrails, or content moderation systems. Activate for questions about input/output guardrails, content filtering, PII detection and redaction, prompt injection defense, system prompt protection, input sanitization, jailbreak detection, toxicity classification, hallucination detection and mitigation, usage policies implementation, and safety evaluation benchmarks.

Triggers when users need help with advanced prompt engineering techniques for LLMs. Activate for questions about chain-of-thought prompting, few-shot example selection, system prompt design, structured output prompting (JSON mode, function calling), prompt chaining, self-consistency, tree-of-thought, meta-prompting, prompt optimization (DSPy, automatic prompt engineering), and adversarial prompt testing.

Triggers when users need help with RAG systems, retrieval-augmented generation, or knowledge-grounded LLM applications. Activate for questions about chunking strategies, embedding models, vector databases (Pinecone, Weaviate, Chroma, Qdrant, pgvector), retrieval methods (dense, sparse, hybrid, reranking), context window management, citation and attribution, RAG evaluation, context relevance, faithfulness, and answer relevance metrics.

Triggers when users need help with RLHF, alignment, or preference optimization for LLMs. Activate for questions about reward model training, PPO optimization, DPO, KTO, ORPO, preference data collection, human annotation, synthetic preferences, reward hacking, overoptimization, constitutional AI, debate, scalable oversight, and red teaming for aligned models.

Triggers when users need help with synthetic data generation using LLMs. Activate for questions about using LLMs for training data, self-instruct, Evol-Instruct, data augmentation with LLMs, quality filtering for synthetic data, constitutional AI data generation, preference pair generation, synthetic evaluation data, domain-specific synthetic data, and avoiding model collapse from synthetic data.

Triggers when users need help with aerospace engineering, including aerodynamics, propulsion, and orbital mechanics. Activate for questions about lift, drag, airfoil theory, jet engines, rockets, electric propulsion, spacecraft systems, flight dynamics and control, avionics, structural design for aerospace, re-entry physics, and UAV design.

Triggers when users need help with biomedical engineering, including biomechanics, biomaterials, medical imaging, and biosensors. Activate for questions about CT, MRI, ultrasound imaging, tissue engineering, neural engineering, prosthetics, orthotics, FDA regulatory pathways, clinical engineering, and rehabilitation engineering.

Triggers when users need help with chemical engineering, including mass and energy balances, fluid mechanics, heat exchanger design, and separation processes. Activate for questions about distillation, absorption, extraction, reactor design (CSTR, PFR, batch), process control, process safety, and plant design economics.

Triggers when users need help with civil engineering, including structural analysis, reinforced concrete design, steel design, and geotechnical engineering. Activate for questions about beams, trusses, frames, soil mechanics, foundations, transportation engineering, hydraulics, hydrology, construction management, and building codes.

Triggers when users need help with control systems engineering, including transfer functions, block diagrams, and stability analysis. Activate for questions about Routh-Hurwitz criterion, Nyquist plots, Bode plots, PID controllers, tuning methods, root locus, state-space representation, digital control, LQR, Kalman filter, and process control applications.

Triggers when users need help with electrical engineering concepts, including circuit analysis, semiconductor devices, signal processing, and power systems. Activate for questions about Kirchhoff's laws, Thevenin/Norton equivalents, transistors, MOSFETs, Fourier transforms, filtering, ADC/DAC conversion, AC/DC circuits, analog and digital electronics, control systems, and PCB design.

Triggers when users need help with energy engineering, including solar energy, wind energy, and energy storage. Activate for questions about photovoltaics, concentrated solar power, solar cell technologies, wind turbine design, wind farm layout, batteries, pumped hydro, hydrogen storage, nuclear energy, reactor types, fuel cycles, grid integration, smart grid, energy efficiency, and techno-economic analysis.

Triggers when users need help with environmental engineering, including water treatment, wastewater treatment, and air quality management. Activate for questions about coagulation, filtration, disinfection, activated sludge, MBR, solid waste management, site remediation, environmental impact assessment, sustainability metrics, Clean Water Act, and Clean Air Act.

Triggers when users need help with materials science and engineering, including crystal structures, phase diagrams, and mechanical properties. Activate for questions about tensile testing, hardness, fatigue, creep, metals and alloys, ceramics, polymers, composites, thin films, corrosion, and materials selection using Ashby charts.

Triggers when users need help with mechanical engineering, including statics, dynamics, strength of materials, machine design, and heat transfer. Activate for questions about stress and strain analysis, Mohr's circle, bearings, gears, shafts, conduction, convection, radiation, HVAC, manufacturing processes, CAD/CAM, and finite element analysis.

Triggers when users need help with robotics engineering, including robot kinematics, dynamics, actuators, and sensors. Activate for questions about forward and inverse kinematics, servo and stepper motors, encoders, IMU, lidar, cameras, path planning (RRT, A*), SLAM, ROS framework, industrial robotics, mobile robots, and human-robot interaction.

Triggers when users need help with systems engineering, including requirements engineering, system architecture, and V-model development. Activate for questions about model-based systems engineering (MBSE), SysML, trade studies, verification and validation, configuration management, reliability engineering, FMEA, fault trees, and lifecycle management.

The 3MF file format — the modern replacement for STL in 3D printing, supporting colors, materials, multi-object assemblies, and precise manufacturing data in a single package.

The 7z archive format — open-source high-ratio compression using LZMA2, with strong AES-256 encryption, solid archives, and multi-threading support.

A lossy audio codec standardized as part of MPEG-2 and MPEG-4, designed to supersede MP3 with better quality at equivalent or lower bitrates.

Dolby

AI is Adobe Illustrator's native vector graphics file format, used for creating logos, illustrations, typography, and print-ready vector artwork in professional design workflows.

Apple

Apple

A speech-optimized audio codec designed for mobile telephony, encoding voice efficiently at very low bitrates for GSM and 3G cellular networks.