Skip to content

Concept Index

All concept notes in this repo, alphabetical order.

Concept Tags
Acceptability-envelope evals llm, evaluation, testing, domain/llm, maturity/emerging, source-type/practitioner
Access control at the retrieval layer security, retrieval, rag, domain/security, maturity/emerging, source-type/practitioner
Actionable page criteria alerting, on-call, sre, domain/reliability, maturity/established, source-type/practitioner
Adaptive data analysis evaluation, statistics, methodology, domain/data, maturity/established, source-type/research
Agent archetypes agents, taxonomy, architecture, domain/ai-agents, maturity/emerging, source-type/practitioner
Agent harness ai-agents, architecture, context, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Agent instruction layering agents, prompting, context, domain/ai-agents, maturity/emerging, source-type/practitioner
Agent loop patterns ai-agents, design-patterns, architecture, domain/ai-agents, maturity/emerging, source-type/practitioner
Agent loop telemetry agents, observability, telemetry, domain/observability, maturity/emerging, source-type/practitioner
Agent security as OS security security, ai-agents, architecture, domain/security, maturity/emerging, source-type/research
Agent Skills format standards, ai-agents, context, domain/standards, maturity/emerging, source-type/vendor-doc
Agent state residence ai-agents, architecture, scaling, domain/ai-agents, maturity/emerging, source-type/practitioner
Agent tool ergonomics ai-agents, mcp, tool-design, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Agent-discovered weak-to-strong methods ai-safety, alignment, machine-learning, domain/ai-safety, maturity/emerging, source-type/research
Agent-led elicitation prompting, requirements, human-ai-interaction, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Agent-legible architecture architecture, agents, software-design, domain/software-engineering, maturity/emerging, source-type/practitioner
Agent-maintained knowledge bundle knowledge-management, provenance, standards, domain/standards, maturity/emerging, source-type/vendor-doc
Agentic artifacts as code agents, operations, versioning, domain/software-engineering, maturity/emerging, source-type/practitioner
AgentOps agent-ops, observability, multi-agent-systems, reliability, domain/observability, maturity/emerging, source-type/research, topic/multi-agent
Anatomy of a reliable agent loop ai-agents, reliability, architecture, domain/ai-agents, maturity/emerging, source-type/practitioner
Answer-layer interception search, content-distribution, user-behavior, domain/llm, maturity/emerging, source-type/practitioner
Associative trail knowledge-management, hypertext, linking, domain/knowledge-management, maturity/established, source-type/practitioner
Attacker-first forward analysis security, static-analysis, agents, domain/security, maturity/emerging, source-type/vendor-doc
Attested computation provenance, agents, data, domain/standards, maturity/emerging, source-type/vendor-doc
Attested per-agent identity security, identity, ai-agents, domain/security, maturity/emerging, source-type/vendor-doc
Authorization response issuer identification oauth, security, protocols, domain/standards, maturity/established, source-type/vendor-doc
Automated W2S research sandbox ai-safety, ai-agents, research-automation, domain/ai-safety, maturity/emerging, source-type/research
Automatic prefix caching (RadixAttention) llm-inference, caching, performance, domain/llm, maturity/established, source-type/research, topic/cost-control
Bell-LaPadula confidentiality model security, access-control, confidentiality, domain/security, maturity/established, source-type/research
Budget caps for autonomous agents agents, operations, cost-control, domain/ai-agents, maturity/emerging, source-type/practitioner
Build-time governance of generated code agents, architecture, ci, domain/software-engineering, maturity/emerging, source-type/practitioner
CFRG curves in JOSE (OKP key type) cryptography, standards, jose, domain/standards, maturity/established, source-type/vendor-doc
Chain-of-thought prompting llm, prompting, reasoning, domain/llm, maturity/emerging, source-type/practitioner
Checkpoint-and-resume agents ai-agents, architecture, reliability, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Classifier-mediated action approval ai-agents, security, autonomy, domain/security, maturity/emerging, source-type/vendor-doc
Closed-loop secure code generation security, ai-native-sdlc, agents, domain/security, maturity/emerging, source-type/vendor-doc
Code knowledge graph software-engineering, knowledge-graph, code-analysis, domain/software-engineering, maturity/established, source-type/vendor-doc
Code Mode for MCP infrastructure, ai-agents, cost, domain/infrastructure, maturity/emerging, source-type/vendor-doc
Cognitive debt cognition, learning, human-ai-interaction, domain/human-factors, maturity/emerging, source-type/research
Collector-side telemetry reduction observability, sampling, cost-control, domain/observability, maturity/emerging, source-type/vendor-doc
Compounding failure in agentic systems ai-agents, reliability, failure-modes, domain/reliability, maturity/emerging, source-type/practitioner
Comprehension gate code-review, human-ai-interaction, software-engineering, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Context drift in long-running agent tasks ai-agents, context, failure-modes, domain/ai-agents, maturity/emerging, source-type/practitioner
Context engineering agents, llm, prompting, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Context layer data, ai-agents, architecture, domain/data, maturity/emerging, source-type/practitioner
Context rot llm, long-context, evaluation, domain/llm, maturity/emerging, source-type/research
Continuous profiling observability, performance, profiling, domain/observability, maturity/emerging, source-type/practitioner
Contract-driven agent development agents, software-process, specification, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Cranfield paradigm evaluation, retrieval, history, domain/knowledge-management, maturity/established, source-type/research
Cross-run observational memory ai-agents, memory, observability, domain/ai-agents, maturity/emerging, source-type/practitioner
Cross-run result identity and baselining static-analysis, security, tooling, domain/standards, maturity/established, source-type/vendor-doc
CycloneDX object model security, supply-chain, standards, domain/standards, maturity/established, source-type/vendor-doc
DAMA-DMBOK Wheel data-management, governance, taxonomy, domain/data, maturity/established, source-type/vendor-doc
Datasheets for datasets data-governance, documentation, ml-datasets, domain/data, maturity/established, source-type/research
Debate-augmented weak supervision ai-safety, alignment, scalable-oversight, domain/ai-safety, maturity/emerging, source-type/research
Debate-gated decision pipeline ai-agents, multi-agent, design-patterns, domain/ai-agents, maturity/emerging, source-type/research, topic/multi-agent, topic/patterns
Decoupled policy decision engines security, agents, authorization, policy-as-code, domain/security, maturity/established, source-type/vendor-doc
Defense-in-depth for unsandboxed extension marketplaces security, supply-chain, extensibility, domain/security, maturity/established, source-type/vendor-doc, topic/supply-chain
Deletion confidence for dead code dead-code-detection, static-analysis, testing, domain/software-engineering, maturity/established, source-type/practitioner, topic/static-analysis
Deletion semantics in continuous sync data, distributed-systems, sync, domain/data, maturity/established, source-type/practitioner
Deterministic verification in agent loops ai-agents, verification, reliability, domain/reliability, maturity/emerging, source-type/practitioner
Deterministic-picker scoring agents, evaluation, llm-as-judge, domain/ai-agents, maturity/emerging, source-type/practitioner
Deterministic/agentic capability matrix agents, architecture, system-design, domain/ai-agents, maturity/emerging, source-type/practitioner
Deviation log ai-agents, software-engineering, observability, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Disposable artifacts as specification prototyping, requirements, human-ai-interaction, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Domain-anchored federated identifiers architecture, identity, distributed-systems, naming, domain/standards, maturity/emerging, source-type/vendor-doc
Ebbinghaus forgetting curve knowledge-management, memory, learning, domain/knowledge-management, maturity/established, source-type/research
eBPF zero-instrumentation observability observability, kubernetes, ebpf, domain/observability, maturity/emerging, source-type/practitioner
Emergent misalignment from reward hacking ai-safety, alignment, reinforcement-learning, domain/ai-safety, maturity/emerging, source-type/research
Evaluation rubric as training signal evaluation, post-training, fine-tuning, domain/llm, maturity/emerging, source-type/vendor-doc
Event-driven knowledge maintenance knowledge-management, ai-agents, automation, domain/knowledge-management, maturity/emerging, source-type/practitioner
Evolved lightweight LLM coordinator multi-agent, orchestration, evolutionary-optimization, domain/ai-agents, maturity/emerging, source-type/research
Exploitability versus reliability in attack evidence security, evaluation, research-methods, domain/security, maturity/emerging, source-type/research
Exposure-first supply chain defense security, supply-chain, ci-cd, domain/security, maturity/emerging, source-type/vendor-doc
Extension registry trust model security, supply-chain, extensibility, domain/security, maturity/emerging, source-type/practitioner
Fable 5 export-control directive governance, ai-safety, policy, domain/governance, maturity/emerging, source-type/announcement
First-pass acceptance as a productivity measure metrics, ai-assisted-development, delivery, domain/software-engineering, maturity/emerging, source-type/practitioner
Fitness-driven agent tuning ai-agents, evaluation, optimization, domain/ai-agents, maturity/emerging, source-type/practitioner
Fitted spaced-repetition scheduling learning, spaced-repetition, memory, domain/knowledge-management, maturity/emerging, source-type/practitioner
Frontier model as callable advisor ai-agents, orchestration, inference-cost, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Gateway-owned channel architecture architecture, agents, messaging, protocol-design, domain/ai-agents, maturity/emerging, source-type/vendor-doc, topic/protocols
Golden trajectory regression testing agents, testing, observability, domain/ai-agents, maturity/emerging, source-type/practitioner
Golden-dataset retrieval evals llm, evaluation, retrieval, domain/llm, maturity/emerging, source-type/practitioner
Goodhart's law variants evaluation, governance, metrics, domain/governance, maturity/established, source-type/research
Governing the automation loop security, governance, ai-native-sdlc, domain/security, maturity/emerging, source-type/vendor-doc
Graph vs vector retrieval for code llm, retrieval, code-analysis, domain/llm, maturity/emerging, source-type/vendor-doc
Grounding agents in current state agents, retrieval, tooling, domain/ai-agents, maturity/emerging, source-type/practitioner
Harness-determined injection resistance security, ai-agents, agent-harness, prompt-injection, domain/security, maturity/emerging, source-type/research
Harness-memory lock-in ai-agents, memory, lock-in, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Hybrid search with rank fusion retrieval, search, knowledge-management, domain/knowledge-management, maturity/emerging, source-type/practitioner
Hypothetical document embeddings (HyDE) retrieval, rag, embeddings, domain/knowledge-management, maturity/emerging, source-type/practitioner
Immutable reference pinning against mutable-name substitution security, supply-chain, ci-cd, domain/security, maturity/established, source-type/vendor-doc, topic/supply-chain
Independent fix verification security, agents, remediation, domain/security, maturity/emerging, source-type/vendor-doc
Instruction and data boundary collapse security, llm, prompt-injection, domain/security, maturity/emerging, source-type/practitioner
Interchangeable agentic architectures agents, architecture, patterns, domain/ai-agents, maturity/emerging, source-type/practitioner
Internet-facing MCP servers are exposed by design security, mcp, measurement, domain/security, maturity/emerging, source-type/research, topic/mcp
JSON Web Encryption (JWE) cryptography, standards, jose, domain/standards, maturity/established, source-type/vendor-doc
JSON Web Token (JWT) jose, claims-based-authentication, offline-verification, licensing, domain/standards, maturity/established, source-type/vendor-doc, topic/licensing
Kernel-enforced agent sandbox security, agents, sandboxing, domain/security, maturity/emerging, source-type/vendor-doc
Knowledge lifecycle management knowledge-management, memory, ai-agents, domain/knowledge-management, maturity/emerging, source-type/practitioner
Language-agnostic code graph code-intelligence, static-analysis, graphs, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Layered agent guardrails agents, security, guardrails, domain/security, maturity/emerging, source-type/practitioner
Layered agent memory ai-agents, memory, architecture, domain/ai-agents, maturity/emerging, source-type/practitioner
Layered testing of agentic systems agents, testing, architecture, domain/software-engineering, maturity/emerging, source-type/practitioner
LLM wiki architecture knowledge-management, ai-agents, memory, domain/knowledge-management, maturity/emerging, source-type/practitioner
LLM-maintained wiki knowledge-management, ai-agents, memory, domain/knowledge-management, maturity/emerging, source-type/practitioner
LLMOps maturity gates llmops, platform-engineering, governance, domain/governance, maturity/emerging, source-type/vendor-doc
Loop engineering ai-agents, agentic-coding, automation, domain/ai-agents, maturity/emerging, source-type/practitioner
macOS Gatekeeper code-signing, app-notarization, desktop-app-distribution, licensing, domain/software-distribution, maturity/established, source-type/vendor-doc, topic/licensing
Matryoshka embeddings embeddings, machine-learning, retrieval, domain/llm, maturity/emerging, source-type/research
MCP abstraction tax ai-agents, integration, mcp, domain/ai-agents, maturity/emerging, source-type/practitioner
MCP attack surface taxonomy security, mcp, threat-modeling, domain/security, maturity/emerging, source-type/vendor-doc
MCP authorization hardening standards, security, oauth, domain/standards, maturity/emerging, source-type/vendor-doc
MCP confused-deputy and token-passthrough risk security, mcp, oauth, proxy, domain/security, maturity/emerging, source-type/vendor-doc, topic/mcp
MCP control-plane layers security, mcp, architecture, domain/security, maturity/emerging, source-type/practitioner
MCP extensions framework standards, mcp, governance, domain/standards, maturity/emerging, source-type/vendor-doc
MCP Registry federation model mcp, registries, governance, discovery, domain/standards, maturity/emerging, source-type/announcement, topic/mcp
MCP stateless protocol core standards, mcp, protocols, domain/standards, maturity/emerging, source-type/vendor-doc
MCP tool poisoning security, mcp, ai-agents, domain/security, maturity/emerging, source-type/research
Memex knowledge-management, personal-knowledge, history, domain/knowledge-management, maturity/established, source-type/practitioner
Memory as a harness capability agents, memory, context-management, domain/ai-agents, maturity/emerging, source-type/practitioner
Metrics, logs and traces as wide-event projections observability, telemetry, instrumentation, domain/observability, maturity/emerging, source-type/practitioner
Microcopy doubt injection ux-writing, conversion, product-design, domain/human-factors, maturity/emerging, source-type/practitioner
Model provenance over inspection security, supply-chain, ai-governance, domain/security, maturity/emerging, source-type/vendor-doc
Model-harness co-evolution ai-agents, training, evaluation, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Multi-agent orchestration topologies agents, architecture, multi-agent, domain/ai-agents, maturity/emerging, source-type/practitioner
Multi-agent token economics ai-agents, orchestration, inference-cost, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Mutation testing testing, quality, verification, domain/software-engineering, maturity/established, source-type/practitioner
Narrow reviewer ensembles code-review, agents, security, domain/security, maturity/emerging, source-type/vendor-doc
Natural-language-to-Cypher querying llm, knowledge-graph, interfaces, domain/llm, maturity/emerging, source-type/vendor-doc
Non-text channel injection security, ai-agents, prompt-injection, code-review, domain/security, maturity/emerging, source-type/research
Observability generations (1.0 vs 2.0) observability, telemetry, cost-model, domain/observability, maturity/emerging, source-type/vendor-doc
Observability pipeline as a control point observability, data-pipeline, architecture, vendor-strategy, domain/observability, maturity/emerging, source-type/vendor-doc
Observe-and-confine sandboxing agents, security, observability, domain/security, maturity/emerging, source-type/practitioner
Okapi BM25 retrieval, ranking, lexical-search, domain/llm, maturity/established, source-type/research
Opaque agent interoperability ai-agents, protocols, interoperability, domain/standards, maturity/emerging, source-type/vendor-doc
Orchestration as a provider hedge orchestration, vendor-risk, ai-strategy, domain/ai-agents, maturity/emerging, source-type/practitioner
OSV format security, supply-chain, standards, domain/security, maturity/established, source-type/practitioner
Outcome versus proxy metrics for agents agents, observability, evaluation, domain/ai-agents, maturity/emerging, source-type/practitioner
Outcome-based agent evaluation evaluation, ai-agents, llm-as-judge, domain/ai-agents, maturity/emerging, source-type/vendor-doc
PageRank ranking, graphs, algorithms, domain/llm, maturity/established, source-type/research
Parallel automated researchers ai-agents, research-automation, ai-safety, domain/ai-safety, maturity/emerging, source-type/research
Partitioned-edit consistency debt ai-agents, software-maintenance, correctness, domain/software-engineering, maturity/emerging, source-type/practitioner
Passkeys security, authentication, identity, domain/security, maturity/emerging, source-type/practitioner
Paved-road MCP platform infrastructure, governance, platform-engineering, domain/infrastructure, maturity/established, source-type/vendor-doc
Per-product agent runtime isolation platform-engineering, ai-agents, reliability, domain/infrastructure, maturity/emerging, source-type/vendor-doc
Perpetual fallback access licensing, software-business, desktop-software, domain/software-distribution, maturity/emerging, source-type/vendor-doc
Pre-seeded-state agent evals ai-agents, evaluation, testing, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Premature multi-agent architecture ai-agents, architecture, anti-patterns, domain/ai-agents, maturity/emerging, source-type/practitioner
Principle of least agency security, agents, identity, domain/security, maturity/emerging, source-type/vendor-doc
Production reliability for stateful agents ai-agents, reliability, operations, domain/reliability, maturity/emerging, source-type/vendor-doc
Prompt, context, harness and loop layers ai-agents, abstraction, engineering-practice, domain/ai-agents, maturity/emerging, source-type/practitioner
Protocol feature lifecycle policy standards, governance, protocols, domain/standards, maturity/emerging, source-type/vendor-doc
Proxy-boundary session capture observability, ai-agents, reliability, domain/observability, maturity/emerging, source-type/practitioner
Purpose-built agent hierarchies agents, architecture, evaluation, domain/ai-agents, maturity/emerging, source-type/practitioner
Rare context agents, knowledge, operations, domain/knowledge-management, maturity/emerging, source-type/practitioner
Reachability-based dead code detection static-analysis, dead-code-detection, dependency-graph, domain/software-engineering, maturity/established, source-type/vendor-doc, topic/static-analysis
ReAct pattern ai-agents, prompting, reasoning, domain/ai-agents, maturity/established, source-type/research
Read and write permission separation for agents ai-agents, security, guardrails, domain/security, maturity/emerging, source-type/practitioner
Remocal development developer-experience, kubernetes, tooling, domain/infrastructure, maturity/emerging, source-type/vendor-doc
Remote-first MCP governance infrastructure, security, mcp, domain/infrastructure, maturity/emerging, source-type/vendor-doc
Request-level sandbox isolation developer-experience, kubernetes, testing, domain/infrastructure, maturity/emerging, source-type/vendor-doc, topic/devops
Retrieval as composition llm, retrieval, orchestration, domain/llm, maturity/emerging, source-type/practitioner
Retrieval-Augmented Generation (RAG) llm, retrieval, architecture, domain/llm, maturity/established, source-type/research
Retry escalation ladder ai-agents, reliability, orchestration, domain/reliability, maturity/emerging, source-type/practitioner
Reward hacking of evaluation APIs ai-safety, evaluation, ai-agents, domain/ai-safety, maturity/emerging, source-type/research
Risk-tiered control of agent-authored change security, agents, software-process, domain/security, maturity/emerging, source-type/vendor-doc
RL-learned agent orchestration multi-agent, orchestration, reinforcement-learning, domain/ai-agents, maturity/emerging, source-type/research
SARIF format security, static-analysis, standards, domain/standards, maturity/established, source-type/practitioner
Search-first discovery for agentic resources ai-agents, mcp, architecture, discovery, domain/ai-agents, maturity/emerging, source-type/vendor-doc, topic/mcp
Selection as the bottleneck of the record knowledge-management, information-retrieval, history, domain/knowledge-management, maturity/established, source-type/practitioner
Self-falsification as a finding filter security, agents, verification, domain/security, maturity/emerging, source-type/vendor-doc
Semantic layer data, analytics, architecture, domain/data, maturity/emerging, source-type/practitioner
Server-driven UI mobile, architecture, frontend, domain/software-distribution, maturity/emerging, source-type/practitioner
Server-sent events web-platform, protocols, streaming, domain/standards, maturity/established, source-type/vendor-doc
Shadow MCP detection infrastructure, security, observability, domain/infrastructure, maturity/emerging, source-type/vendor-doc
Shared mental-model erosion software-engineering, cognition, engineering-management, domain/software-engineering, maturity/emerging, source-type/practitioner
SIEM visibility gap for agentic AI observability, security, ai-agents, domain/observability, maturity/emerging, source-type/vendor-doc
Six-part agentic AI architecture taxonomy agents, architecture, taxonomy, llm, domain/ai-agents, maturity/emerging, source-type/research
Skill-enforced development workflow ai-agents, software-process, tdd, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Sleeper agent backdoors ai-safety, alignment, security, domain/ai-safety, maturity/emerging, source-type/research
SLO burn-rate alerting observability, reliability, sre, domain/reliability, maturity/established, source-type/practitioner
SLSA build provenance levels security, supply-chain, ci-cd, standards, domain/standards, maturity/established, source-type/vendor-doc, topic/supply-chain
Snapshot-backed agent sandboxes infrastructure, virtualization, ai-agents, domain/infrastructure, maturity/emerging, source-type/research
Spec-driven SLO rule generation reliability, observability, sre, domain/reliability, maturity/emerging, source-type/practitioner
Specification gaming to reward tampering ai-safety, alignment, reinforcement-learning, domain/ai-safety, maturity/emerging, source-type/research
Split-payload prompt injection security, prompt-injection, supply-chain, domain/security, maturity/emerging, source-type/practitioner
Spreading activation retrieval, graphs, cognitive-science, domain/llm, maturity/established, source-type/research
SSRF via MCP OAuth discovery security, mcp, oauth, ssrf, domain/security, maturity/emerging, source-type/vendor-doc, topic/mcp
Stacked production agent loops ai-agents, architecture, continuous-improvement, domain/ai-agents, maturity/emerging, source-type/practitioner
State-authoritative agent interface agents, interface-design, state-management, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Stateless worker fan-out ai-agents, orchestration, parallelism, domain/ai-agents, maturity/emerging, source-type/practitioner
Structural linting for agent-written code agents, code-quality, static-analysis, domain/software-engineering, maturity/emerging, source-type/practitioner
Sub-agent delegation ai-agents, architecture, orchestration, domain/ai-agents, maturity/emerging, source-type/vendor-doc
Symptom-based alerting observability, alerting, sre, domain/reliability, maturity/established, source-type/practitioner
Tail latency histograms observability, monitoring, latency, domain/observability, maturity/established, source-type/practitioner
Targeted profiling rollout observability, performance, operations, domain/observability, maturity/emerging, source-type/practitioner
Telemetry collector pipeline observability, telemetry, architecture, domain/observability, maturity/established, source-type/vendor-doc
Temporal fakes testing, simulation, observability, domain/software-engineering, maturity/emerging, source-type/practitioner
The AI coding maintainability gap ai-coding, code-quality, technical-debt, software-engineering, domain/software-engineering, maturity/emerging, source-type/research, topic/agentic-coding
The four golden signals observability, monitoring, sre, domain/observability, maturity/established, source-type/practitioner
The Ladder mechanism evaluation, statistics, leaderboards, domain/data, maturity/established, source-type/research
Three loops of agentic development agentic-coding, product-development, feedback-loops, domain/software-engineering, maturity/emerging, source-type/practitioner
Threshold-signed software update security security, supply-chain, cryptography, software-distribution, domain/standards, maturity/established, source-type/vendor-doc, topic/supply-chain
Tiered execution gating for AI agents security, ai-agents, agent-harness, domain/security, maturity/emerging, source-type/vendor-doc
Tool surface minimalism ai-agents, tool-design, context, domain/ai-agents, maturity/emerging, source-type/practitioner
Tools for certainty, agents for discovery agents, architecture, reliability, domain/ai-agents, maturity/emerging, source-type/practitioner
Trace-to-dataset evaluation loop llmops, observability, evaluation, domain/observability, maturity/emerging, source-type/practitioner
Trading short-term availability for long-term health reliability, on-call, sre, domain/reliability, maturity/established, source-type/practitioner
Transformer architecture machine-learning, neural-networks, attention, domain/llm, maturity/established, source-type/research
TREC (Text REtrieval Conference) evaluation, retrieval, institutions, domain/knowledge-management, maturity/established, source-type/research
Triage as a separate evidence pass agents, security, verification, domain/security, maturity/emerging, source-type/practitioner
Typed knowledge graph layer knowledge-management, knowledge-graph, ai-agents, domain/knowledge-management, maturity/emerging, source-type/practitioner
Unknowns inventory in prompting prompting, human-ai-interaction, software-engineering, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Vision-language document parsing machine-learning, document-processing, ocr, domain/llm, maturity/emerging, source-type/practitioner
Vocabulary mismatch retrieval, language, evaluation, domain/llm, maturity/established, source-type/research
Vulnerability range events security, supply-chain, standards, domain/standards, maturity/established, source-type/vendor-doc
Wave-based parallel agent execution agents, software-process, parallelism, domain/software-engineering, maturity/emerging, source-type/vendor-doc
Weak-to-strong generalization ai-safety, alignment, evaluation, domain/ai-safety, maturity/established, source-type/research
Wide events as a single source of truth observability, telemetry, instrumentation, domain/observability, maturity/emerging, source-type/vendor-doc
Workflows versus agents ai-agents, design-patterns, architecture, domain/ai-agents, maturity/established, source-type/vendor-doc