A dialogue system that helps a user get something done is traditionally split into four modules: understand the utterance, track the state so far, decide the next action, and write the action as a sentence. A language model can act out all four in one go, and without external tools its "let me check" checks nothing. The first half of this lecture therefore covers representative systems that let a model use tools: LaMDA drafts first and then verifies and revises, BlenderBot adds search and long-term memory, WebGPT learns to search from records of human actions, and Toolformer has the model generate and filter its own training data. The second half moves from a single reply to multiple turns: the model can ask the user, learn an expert's strategy, and guess what the other party is thinking. It ends with how conversations are evaluated.
Agent Memory is a Cloudflare private beta service for letting agents remember users, teams, projects, and task context across conversations. It fits facts, events, instructions, and tasks; RAG documents, product data, files, and audit logs should still live in AI Search, Vectorize, D1, or R2.
Cloudflare Agents turns an agent session into a durable runtime: each agent instance has stable identity, local SQLite, WebSockets, scheduled work, recoverable execution, and tools. It is not just a chat example; it composes Workers, Durable Objects, AI models, Browser, Sandbox, AI Search, and MCP into a deployable agent app.
An AI app should not put conversations, artifacts, memory, retrieval documents, locks, and eval traces into one store. D1 fits queryable product data, R2 fits large files and artifacts, Durable Objects fit named coordination and per-session state, and Agent Memory / AI Search / Vectorize handle memory and retrieval.
The Cloudflare AI Stack series covers the infrastructure around AI apps: where models run, how gateway control works, how RAG is built, how agents keep running, how memory is governed, and how browser, sandbox, secrets, data, and observability fit into a product.
Browser Run gives Workers access to Cloudflare-managed headless Chrome. Quick Actions fit one-shot tasks such as screenshots, PDFs, HTML, JSON, and crawls; Browser Sessions fit Puppeteer, Playwright, CDP, and Stagehand automation where you need full control.
Lecture 12 moves from perplexity to exams, chat preferences, agents, reasoning, and safety. Every benchmark changes the capability definition, scaffold, judge, and contamination risk, so evaluation must first say whether it compares a method, model, or complete system.
Across Microsoft's four AI/agent certifications there are two hard prerequisites: AI-500 requires AI-103, and AB-100 requires any one associate on its list. The rest is positioning. Three forks decide it: whether you write Python (AI-103/AI-500 vs AB-620), whether you build or judge (AB-100 vs the rest), and whether you can actually start today — AI-500's four official learning paths currently 404, AB-620 has no practice test, AB-100 has a free one. For readers who prefer Chinese there is a fourth fork: AI-103, AB-620, and AB-100 offer Traditional Chinese, and only AI-500 is English only. All four cost $165 in the US ($83 in Taiwan), expire after one year, and renew free but only inside a six-month window.
NVIDIA's generative AI line has four exams: NCA-GENL and NCA-GENM ($125 each, associate), NCP-GENL and NCP-AAI ($200 each, professional). Three decision inputs no other vendor forces on you. One: both professional exams still show 'Coming soon' next to Register, so any near-term plan is down to the two associates. Two: the cost of the official recommended training differs sharply by level. In autumn 2026 the two associate exams switched to one free open-source set of materials plus one course, while the two professional exams still list five paid courses, $1,620 at list price for NCP-GENL. Three: the official web pages and PDFs differ in a few places — two NCP-AAI weights do not match, and two cells of NCP-GENL's web table carry misplaced text — so for those two exams follow the PDF or budget a range. Lock-in also varies sharply: NCP-AAI is 7% NVIDIA-specific, NCP-GENL is 31% GPU and model-compression work.
AIP-C01 tests integrating foundation models into production AWS applications: RAG, agents, security, cost, and evaluation. This guide follows the five official domains with a prerequisite self-check, four-step preparation plan, resource choices, and hands-on checkpoints, plus a ten-week schedule, an AI study prompt, and exam-day guidance. Start with a diagnostic, then close gaps through one RAG-and-agent project.
CCDV-F is the engineer's exam among Anthropic's four certifications. The official blueprint has eight domains, and the heaviest — Applications and Integration at 33.1% — is led by Claude Application Design (8.6%) and Software Engineering Foundations (7.4%), meaning a third of the exam is API mechanics and ordinary software engineering. The counterintuitive part: Claude Code is only 3.1% and Eval only 2.6%, while the sibling Architect exam gives Claude Code 20%. Official specs: $125, 53 items, 120 minutes, pass at 720, valid 12 months, registration limited to Claude Partner Network organizations.
AB-100 is the architect tier of Microsoft's agent line, weighted 25-30 / 25-30 / 40-45 with deployment and governance heaviest. Its outline runs on verbs like design, recommend, and propose — it tests judgment, not configuration. Three things to know first: it has a prerequisite — besides passing AB-100 you must hold one of the associate certifications on the official list (AI-103, AB-620, and AI-300 are all on it); it has a free practice assessment, the only one of Microsoft's three agent credentials that does; and one blurb on the exam page describes a compliance exam instead, so prepare from the study guide. Official specs: $165 in the US, 13 languages including Traditional Chinese, pass at 700, one-year validity.
AB-620 is the low-code branch of Microsoft's agent certification line — it tests agent flows, adaptive cards, computer use, MCP tools, A2A, and Fabric data agents in Copilot Studio, not Python. The three skill areas weigh 30-35 / 40-45 / 20-25, with integration the heaviest. Official specs: $165, 120 minutes, pass at 700, one-year validity, and 13 languages including Traditional Chinese. It is generally available, but the practice assessment is not out yet.
AI-103 replaces AI-102, retired June 30, 2026, and the objectives were rewritten around Microsoft Foundry — prompt flow, Azure AI Studio, Azure OpenAI Service, and Azure AI Agent Service appear nowhere in them. The five skill areas weigh 25-30 / 30-35 / 10-15 / 10-15 / 10-15, with generative AI and agents the largest. Official specs: $165, 120 minutes, pass at 700, offered in Traditional Chinese, may include interactive components — and it is valid for only one year, though renewal is a free, open-book, unproctored online assessment.
AI-500 is a rare thing among the major clouds — an expert-level certification dedicated to multi-agent systems, weighted 15-20 / 30-35 / 20-25 / 20-25, naming Agent Framework, LangGraph, Hugging Face Transformers, MCP servers on Azure Functions / Logic Apps / API Management, A2A, Key Vault, and the AI Red Teaming Agent. Two constraints come first: it requires AI-103 before you can take it, and neither the official learning paths nor a practice assessment is live yet. Microsoft removed the beta label from its pages at the end of September 2026.
NCP-AAI is NVIDIA's professional-level agentic AI credential — $200, 120 minutes, 60–70 items, two-year validity. Of its ten areas the heaviest are Agent Architecture and Design at 15% and Agent Development at 15%; only NVIDIA Platform Implementation at 7% is explicitly tied to NVIDIA products, and the rest is general agentic engineering. Two things to know first: registration is not open (the Register button carries a 'Coming soon' label), and the web page and the PDF study guide differ on two weights (Deployment and Scaling 13% versus 5%, Run/Monitor/Maintain 5% versus 7%), so budget those as a range.
The hard part of LLM agents is not building function calling, skills, code interpreter, and document tools individually -- it is assembling them into a system that selects the right tool, writes code when needed, decomposes tasks, verifies results, and resists prompt injection. This post organizes the key papers into six engineering decisions: function calling reliability, tool/skill selection, code-as-action, multi-step planning, skill systems, and safety plus document generation.
Anthropic open-sourced 12 financial-industry Agents and 11 MCP connectors. The real takeaway isn't the Agents themselves but the layered design of 'one prompt, two runtimes' and 'pure-file extensibility.'