59 side-by-side comparison tables across 51 ChangeGamer resources — frameworks, models, protocols, vector databases, and more — each linked to the exact section that contains it.
Cross-vendor, threat-surface-organized security checklist for building and operating AI agents — synthesizing OWASP, NIST, Anthropic, OpenAI, Google SAIF, and MITRE ATLAS.
Compact comparison of the Model Context Protocol (agent↔tool) and the Agent2Agent Protocol (agent↔agent): purpose, topology, transport, discovery, auth, governance, and when to use each.
Canonical reference table of major AI crawler user-agent tokens, their purpose, robots.txt semantics, and the WAF/edge layer that sits above robots.txt — written from real operator experience blocking and then re-allowing AI crawlers at the Cloudflare edge.
Cross-vendor comparison table of major open-weight LLM families — license, tool-calling support, context window, and agent-builder notes — as of July 2026.
What the Agentic Commerce Protocol (ACP) is and how it differs from AP2, plus an implementor's comparison of the three live content-payment mechanisms — self-hosted HTTP 402 gates, Cloudflare Pay Per Crawl, and the x402 open standard — and how RSL fits as the licensing layer, not the settlement layer.
Vendor-neutral comparison table of the major agent-orchestration frameworks — language, license, multi-agent model, MCP/A2A support — plus a how-to-choose guide for agent builders.
Compares: Hallucinated tool name — model calls a tool not in the declared set · Missing required arguments — model omits a field the schema marks required · Extra / unexpected arguments — model adds fields not in schema · Malformed JSON — output is not parseable · Wrong types — string where int expected, etc. · Over-calling — model calls tools unnecessarily · Under-calling — model answers in text when a tool call was required · Parallel tool calls in wrong order — parallel calls with dependencies · Chat-template mismatch — open model's tool schema injected with wrong template
End-to-end practitioner reference for Retrieval-Augmented Generation: pipeline stages, chunking strategies, dense/sparse/hybrid retrieval, reranking, agentic retrieval patterns, quality failure modes, and evaluation — with verified sources for every named technique.
Isolation spectrum from language sandboxes to microVMs, WebAssembly as a portable sandbox, and a verified comparison of hosted agent-sandbox APIs — for agents that need to run model-generated code safely.
How to pick an embedding model, understand distance metrics, choose an ANN index type, and operate a vector store reliably in agent retrieval pipelines.
Architectures, vendor APIs, and open frameworks for real-time speech-to-speech AI agents — cascaded pipeline vs. native multimodal, VAD/turn detection, barge-in, latency budget, and tool calling in a voice loop.
Serving-stack reference for teams self-hosting open-weight models for agents: production inference servers, local/dev runtimes, managed GPU endpoints, and key serving concepts — with decision guidance by load profile and verified sources.
From crafting a single prompt to managing everything an agent sees across a trajectory: system-prompt design, context-window management, failure modes, and a high-leverage checklist.
Compares: Already on AWS; need durable multi-step agent workflows · Already on Azure · Already on GCP · Already on Cloudflare Workers · Need portable, code-first durability; want to self-host · Managed serverless, code-first, TypeScript/JavaScript-first · Already using LangGraph; need HITL and checkpoint-based fault tolerance within a graph · Using OpenAI Agents SDK; need memory continuity across sessions but not crash-resume semantics
Deep reference on the six MCP capability primitives beyond tools — who controls each, the exact JSON-RPC method names, and when to use Resources vs Tools — verified against the 2025-06-18 and 2025-11-25 spec revisions.
Compares: The data is read-only context the app injects · The app (not the model) decides what to include · The content is stable or subscribable · Example: open file, DB row, live feed
How agents perceive and reason over images: VLM mechanics, image-input APIs across major providers, open-weight VLM families, grounding/pointing, failure modes, and practical guidance for agent builders.
How credential authority flows when one agent spawns another — the multi-hop delegation problem, RFC 8693 token exchange, the act/may_act claims, audience binding across hops, and the IETF drafts standardizing verifiable actor chains in 2026.
Implementation guide for MCP servers: architecture roles, the three server primitives, stdio vs Streamable HTTP transports, official SDKs, server lifecycle, remote-server concerns, testing with MCP Inspector, and publishing to the official registry.
Decision guide for agent builders: when to use prompting, RAG, or fine-tuning — and how they combine. Covers SFT, LoRA/QLoRA, DPO, distillation, and a symptom-to-fix table.
Compares: Model lacks current or proprietary facts · Output format or schema is unreliable · Tone or style is wrong · Model too slow or expensive at scale · Model makes tool-calling mistakes · Need model to follow complex instructions reliably · Behavior must reflect human ranking preferences
How to build agentic training corpora without human annotation at scale: the three generation patterns (distillation, self-play, environment rollout), open pipelines (distilabel, AgentInstruct, APIGen-MT, TOUCAN), quality filtering, and the model-collapse risk.
Cross-provider prompt caching reference: how to activate it, minimum token thresholds, TTLs, read-vs-write pricing, and when it pays off for agentic workloads.
A practical reference for agent builders: what a 429 means, how to read provider rate-limit headers, exponential backoff with jitter, client-side throttling, and when to use a batch API.
Second-stage retrieval step that re-scores bi-encoder candidates with full query-document attention, boosting precision without sacrificing recall; covers cross-encoder, LLM, and late-interaction reranking, hosted APIs, sizing heuristics, and evaluation.
Practitioner reference for chunking documents before embedding: fixed-size, recursive, semantic, late chunking, and contextual retrieval — with a strategy comparison table, chunk-size and overlap tradeoffs, code/table/Markdown handling, embedding model context limits, and evaluation methods.
A criteria-based decision framework for selecting an LLM for agent use: tool-calling reliability, long-context behavior, structured output, cost per task, latency, and a step-by-step selection procedure.
How to force schema-valid JSON from OpenAI, Anthropic, and Gemini — parameter names, strict-mode requirements, schema-subset limits, and self-hosted constrained decoding.
How to implement exact-match and semantic caching in your agent application to eliminate redundant LLM calls, with threshold guidance, invalidation strategies, and a decision matrix for when semantic caching is unsafe.
How to combine lexical (BM25/SPLADE) and dense vector retrieval with Reciprocal Rank Fusion for higher first-stage recall in RAG pipelines — with the RRF formula, a sparse-method comparison table, and verified DB support.
Treating prompts as deployable artifacts: versioning, external registries, A/B and canary testing, eval-gated promotion, rollback, and the composite-version problem.
Criteria-based decision guide: dedicated vs. add-on vector stores, scale thresholds, hybrid search support, self-host vs. managed, and a start-here recommendation.
Buyer-side guide to giving an AI agent a wallet: how the x402 payment loop works, the client libraries that automate it, spend controls, and what 20,000+ Apify Actors on x402 mean for agent tool budgets.
Seller-side guide to monetizing agent traffic: self-hosted HTTP 402 gates, native x402 with automatic Bazaar listing, marketplace publishing, and crawl licensing — with an honest status ledger from a site that runs these rails in production.
How to bound what an autonomous agent can spend — per-transaction caps, session/daily ceilings, human-in-the-loop approval thresholds, and kill switches — across the three layers agents now spend money on: LLM API cost, on-chain wallet payments, and card-network agent tokens.
What agentic browsers (Perplexity Comet, ChatGPT Atlas (stop date Aug 9, 2026), Microsoft Edge Copilot Mode (reported retired as a separate mode in May 2026; search-reported), Opera Neon) are, how they differ from developer-facing computer-use APIs, and the documented prompt-injection attacks — CometJacking, indirect injection, hidden-text/screenshot instructions — that target the whole product category.
Six named architectural patterns — Action-Selector, Plan-Then-Execute, LLM Map-Reduce, Dual LLM, Code-Then-Execute, Context-Minimization — plus Google DeepMind's CaMeL, that structurally constrain what an agent can do with untrusted data instead of just filtering it.
How the general IETF Sunset/Deprecation HTTP headers work, why none of the three major LLM APIs actually send them, and each vendor's real notice periods and retirement mechanics — plus detection and fallback patterns for agents that pin a model ID today.
What changes in MCP's largest revision since launch: SEP-2575/SEP-2567 remove the session handshake and Mcp-Session-Id header for explicit state handles, new Mcp-Method/Mcp-Name routing headers, full JSON Schema 2020-12 tool schemas, and six authorization-hardening SEPs — shipped as final, on schedule, on 2026-07-28.
How CycloneDX AI/ML-BOM, SPDX AI profiles, SLSA build levels, and in-toto/Sigstore signing let an agent check what is actually inside a model, package, or MCP server — and how it was built — before trusting it.
Decision rule for choosing an open-source AI red-teaming tool — garak (probe/detector scanner), PyRIT (Microsoft, attack orchestration), promptfoo (config-driven, CI-friendly) — plus the OWASP GenAI Red Teaming Guide and what automated scanning does not prove.
Compares: Baseline a model or endpoint against known failure classes (jailbreaks, encoding tricks, leakage) · Scripted multi-turn or multi-step attacks, custom scorers, research-style experiments · Regression-test attacks on every pull request; app-level tests defined in YAML · Need a scoping and reporting framework for a human-led exercise
Decision rule for counting LLM tokens: bill from the response usage fields, gate requests with the provider's token-counting endpoint, estimate offline with a tokenizer library such as tiktoken, and never reuse a count across models. Includes pitfalls and budgeting rules.
Compares: What you were actually billed or rate-limited on · Gate or route a request before sending, on a hosted provider · Fast offline estimate, no network call · Model with no published tokenizer or counting endpoint
MCP tool poisoning is an attack where the tool metadata an agent reads (descriptions, schemas) carries hostile instructions or altered contracts. Definition, OWASP MCP03 mapping, what the MCP spec requires of clients, and a pin-scan-confirm defense checklist.
Wire-level reference for the A2A (Agent2Agent) protocol v1.0: the Agent Card at /.well-known/agent-card.json, the 11 operations, the 8 task states, three protocol bindings, security schemes, version negotiation, and what changed from v0.3.
Reference for the Agent Client Protocol (ACP), the open protocol that connects code editors and IDEs to coding agents over JSON-RPC: session lifecycle, MCP server hand-off, transports, tool calls, permissions, and how ACP differs from MCP and A2A.