<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><channel><title>The Archive of — English</title><description>Understand uncertainty. Make better decisions.</description><link>https://thearchiveof.com/</link><language>en</language><item><title>Bloom Energy Valuation Lab: How Many Gigawatts Must Bloom Deliver to Justify Today’s Price?</title><link>https://thearchiveof.com/en/coding/experiments/bloom-energy-valuation-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/bloom-energy-valuation-lab/</guid><description>An interactive FCFF model that separates Bloom Energy’s announced contracts and financing frameworks from common-equity value.</description><pubDate>Fri, 16 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>portfolio</category><category>supply-chain</category><category>enterprise-ai</category></item><item><title>Bloom Energy: An AI Power Bottleneck Winner, but How Much Success Is Already Priced In?</title><link>https://thearchiveof.com/en/investing/markets/bloom-energy-ai-power-valuation/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/bloom-energy-ai-power-valuation/</guid><description>Bloom Energy’s AI-power opportunity is real. We test contracts, cash flow, dilution, and the value that can reach common shareholders.</description><pubDate>Fri, 16 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>portfolio</category><category>supply-chain</category><category>enterprise-ai</category></item><item><title>The Future of AX: When Domain Experts Become Software Owners</title><link>https://thearchiveof.com/en/ai/ax/the-future-of-ax-domain-experts-software-owners/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/the-future-of-ax-domain-experts-software-owners/</guid><description>If AI changes the economics of software and technical debt, how might domain expertise, organizational design, mid-market firms, and private-equity value creation change with it?</description><pubDate>Wed, 14 Oct 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>perspective</category><category>ax</category><category>enterprise-ai</category><category>ai-agents</category><category>evaluation</category></item><item><title>Applied Digital Corporation Valuation Lab: What Is 1.41GW of Contracted Capacity Worth Per Share?</title><link>https://thearchiveof.com/en/coding/experiments/applied-digital-corporation-valuation-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/applied-digital-corporation-valuation-lab/</guid><description>An interactive sensitivity tool connecting Applied Digital Corporation&apos;s contracted capacity, development cost, and capital claims to common-equity value.</description><pubDate>Tue, 13 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>portfolio</category><category>enterprise-ai</category></item><item><title>Applied Digital Corporation: $36 Billion in AI Data Center Leases, but How Much Value Reaches Shareholders?</title><link>https://thearchiveof.com/en/investing/markets/applied-digital-corporation-ai-data-center-value/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/applied-digital-corporation-ai-data-center-value/</guid><description>A contract-to-common-equity analysis of Applied Digital Corporation&apos;s AI data-center portfolio.</description><pubDate>Tue, 13 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>portfolio</category><category>enterprise-ai</category></item><item><title>Build with Gemini Notes: Google Cloud Is Taking the Agent Era Seriously</title><link>https://thearchiveof.com/en/misc/notes/build-with-gemini-gcp-agent-era/</link><guid isPermaLink="true">https://thearchiveof.com/en/misc/notes/build-with-gemini-gcp-agent-era/</guid><description>Notes from Build with Gemini on Google Cloud&apos;s agent governance, Gemini Enterprise as a sticky entry point, and its distribution challenge in Korea.</description><pubDate>Tue, 13 Oct 2026 00:00:00 GMT</pubDate><category>Perspectives</category><category>Short Notes</category><category>perspective</category><category>enterprise-ai</category><category>ai-agents</category></item><item><title>Multi-Agent Is Not Multiple Agents: Parent Runs, Fan-out, and Fan-in</title><link>https://thearchiveof.com/en/ai/agents/multi-agent-parent-run-fan-out-fan-in/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/multi-agent-parent-run-fan-out-fan-in/</guid><description>Model multi-agent execution as a durable parent-child run hierarchy with bounded fan-out, deterministic fan-in, isolated context, and propagated budgets and cancellation.</description><pubDate>Sun, 11 Oct 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>Salesforce Valuation Lab: The FCF Growth Implied by Today’s Price</title><link>https://thearchiveof.com/en/coding/experiments/salesforce-agentforce-fcf-valuation-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/salesforce-agentforce-fcf-valuation-lab/</guid><description>Change Salesforce FCF growth, the SBC adjustment, the discount rate, and terminal growth to calculate five-year fair value and the growth implied by today’s price.</description><pubDate>Fri, 09 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>portfolio</category><category>enterprise-ai</category></item><item><title>Salesforce, Inc.: Can Agentforce Reaccelerate CRM Growth?</title><link>https://thearchiveof.com/en/investing/markets/salesforce-agentforce-fcf-valuation/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/salesforce-agentforce-fcf-valuation/</guid><description>A Salesforce reverse DCF testing organic growth, cRPO, Agentforce economics, SBC, buybacks, and the FCF growth embedded in today’s CRM price.</description><pubDate>Fri, 09 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>portfolio</category><category>enterprise-ai</category></item><item><title>Huntington Ingalls Industries Valuation Lab: Stress-Test the 7.5% Margin</title><link>https://thearchiveof.com/en/coding/experiments/huntington-ingalls-industries-valuation-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/huntington-ingalls-industries-valuation-lab/</guid><description>Change Huntington Ingalls Industries&apos; shipbuilding margin, growth, exit P/E, and required return to recalculate 2030 EPS and present fair value.</description><pubDate>Thu, 08 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>portfolio</category><category>supply-chain</category></item><item><title>Huntington Ingalls Industries: Why Does a Monopoly Shipbuilder With $57 Billion of Orders Trade at 14×?</title><link>https://thearchiveof.com/en/investing/markets/huntington-ingalls-industries-valuation/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/huntington-ingalls-industries-valuation/</guid><description>A valuation of Huntington Ingalls Industries through backlog conversion, shipbuilding productivity, normalized margin, and 2030 scenarios.</description><pubDate>Thu, 08 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>portfolio</category><category>supply-chain</category></item><item><title>Sterling Infrastructure Valuation Lab: The Growth Implied by Today’s Price</title><link>https://thearchiveof.com/en/coding/experiments/sterling-infrastructure-valuation-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/sterling-infrastructure-valuation-lab/</guid><description>Change Sterling Infrastructure growth, EBITDA margin, and exit multiple to calculate 2030 fair value and the growth implied by today’s price.</description><pubDate>Wed, 07 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>portfolio</category><category>supply-chain</category></item><item><title>Sterling Infrastructure: Time to Sell? A Good Company, but About Fair Value Now</title><link>https://thearchiveof.com/en/investing/markets/sterling-infrastructure-fair-value/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/sterling-infrastructure-fair-value/</guid><description>Sterling&apos;s edge is the capacity to build when customers need it. The October 6 close of $564 is about the base case discounted at 10%.</description><pubDate>Wed, 07 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>portfolio</category><category>supply-chain</category></item><item><title>From Retrieval Engineering to Task Engineering</title><link>https://thearchiveof.com/en/ai/ax/from-retrieval-engineering-to-task-engineering/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/from-retrieval-engineering-to-task-engineering/</guid><description>AI engineering is moving from optimizing retrieval pipelines to specifying, constraining, and evaluating end-to-end enterprise tasks.</description><pubDate>Mon, 05 Oct 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>research</category><category>ai-agents</category><category>rag</category><category>evaluation</category><category>enterprise-ai</category></item><item><title>Will Rogo Eat the Financial Intelligence Stack? Two Years with AlphaSense Changed My Answer</title><link>https://thearchiveof.com/en/investing/markets/will-rogo-eat-financial-ai/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/will-rogo-eat-financial-ai/</guid><description>A financial AI market map that separates banking value creation from vendor revenue and a seat-based SAM, then asks where AlphaSense and Rogo can build lasting moats.</description><pubDate>Mon, 05 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>enterprise-ai</category><category>portfolio</category></item><item><title>AI Handoff Queue Simulator</title><link>https://thearchiveof.com/en/coding/experiments/ai-handoff-queue-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/ai-handoff-queue-lab/</guid><description>Change an AI contact center&apos;s human handoff rate, average handle time, and staffing to compare wait times and service levels in an M/M/c queue.</description><pubDate>Sun, 04 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>enterprise-ai</category><category>optimization</category></item><item><title>AWS Is Hiring FDEs. But Can You Hire Your Way Into an FDE Organization?</title><link>https://thearchiveof.com/en/investing/research/fde-loop-hyperscalers-palantir/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/research/fde-loop-hyperscalers-palantir/</guid><description>A framework for evaluating whether hyperscaler FDE teams can turn field discoveries into reusable products, with Palantir as the counterexample that makes the thesis testable.</description><pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Research</category><category>research</category><category>enterprise-ai</category><category>ax</category><category>portfolio</category></item><item><title>What Is the Exponential Distribution?</title><link>https://thearchiveof.com/en/math/statistics/exponential-distribution-ai-handoff/</link><guid isPermaLink="true">https://thearchiveof.com/en/math/statistics/exponential-distribution-ai-handoff/</guid><description>Use contacts an AI cannot resolve—or that require human judgment—to understand exponential waiting times, memorylessness, Poisson thinning, queues, and their limits in crises.</description><pubDate>Sat, 03 Oct 2026 00:00:00 GMT</pubDate><category>Mathematics</category><category>Statistics</category><category>foundation</category><category>enterprise-ai</category><category>optimization</category></item><item><title>FDE Economics: What Wonderful and Reflection Need to Prove</title><link>https://thearchiveof.com/en/investing/research/fde-economics-wonderful-reflection/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/research/fde-economics-wonderful-reflection/</guid><description>A private-market analysis of Wonderful&apos;s labor leverage and Reflection&apos;s challenge of turning open intelligence into capital and distribution leverage.</description><pubDate>Fri, 02 Oct 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Research</category><category>research</category><category>enterprise-ai</category><category>ax</category><category>portfolio</category></item><item><title>LangGraph Is Not Architecture: Where the Runtime Actually Belongs</title><link>https://thearchiveof.com/en/ai/agents/langgraph-runtime-not-architecture/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/langgraph-runtime-not-architecture/</guid><description>A close look at LangGraph&apos;s graph.astream(), updates, custom streams, reducers, and checkpoints—and the boundary between an agent runtime and backend architecture.</description><pubDate>Thu, 01 Oct 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category><category>langgraph</category></item><item><title>Poisson Demand and Inventory Simulator</title><link>https://thearchiveof.com/en/coding/experiments/poisson-demand-inventory-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/poisson-demand-inventory-lab/</guid><description>Change Poisson demand, inventory, service level, and shortage-versus-leftover costs to compare stockout risk and inventory rules.</description><pubDate>Thu, 01 Oct 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>implementation</category><category>supply-chain</category><category>optimization</category></item><item><title>What Is the Poisson Distribution?</title><link>https://thearchiveof.com/en/math/statistics/poisson-demand-inventory/</link><guid isPermaLink="true">https://thearchiveof.com/en/math/statistics/poisson-demand-inventory/</guid><description>A café queue and a Chuseok chicken stockout explain Poisson demand, stockout probability, expected lost sales, and inventory decisions.</description><pubDate>Thu, 01 Oct 2026 00:00:00 GMT</pubDate><category>Mathematics</category><category>Statistics</category><category>foundation</category><category>supply-chain</category><category>optimization</category></item><item><title>Let the Agent Speak While It Works: SSE, Generators, and Redis Streams</title><link>https://thearchiveof.com/en/ai/agents/agent-sse-streaming/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/agent-sse-streaming/</guid><description>Build an agent streaming endpoint from iterators and async generators through SSE framing, Redis Stream replay, heartbeats, disconnects, and backpressure.</description><pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>Why Our Agent Platform Got Off to a Rocky Start</title><link>https://thearchiveof.com/en/ai/ax/we-built-the-agent-platform-too-early/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/we-built-the-agent-platform-too-early/</guid><description>Our agent platform worked in demos but stumbled in production. A retrospective on predictability, trust debt, and earning abstractions through deployment.</description><pubDate>Tue, 29 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>perspective</category><category>ai-agents</category><category>enterprise-ai</category><category>ax</category><category>evaluation</category></item><item><title>Can an Agent Tool Execute Exactly Once? Approval, Idempotency, and Retries</title><link>https://thearchiveof.com/en/ai/agents/agent-tool-idempotency-approval-retry/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/agent-tool-idempotency-approval-retry/</guid><description>For side-effecting agent tools such as transfers and payments: human approval, action fingerprints, idempotency keys, queue redelivery, and unknown outcomes.</description><pubDate>Mon, 28 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>State Is Not an Event: Designing Real-Time Agent UIs</title><link>https://thearchiveof.com/en/ai/agents/state-is-not-event/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/state-is-not-event/</guid><description>Lay out current state and an event timeline in an agent run screen, then implement bootstrap, SSE cursor replay, and snapshot resync for safe reconnects.</description><pubDate>Sun, 27 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>A Profit Beat, a Falling Stock: What Can the Data Tell Us?</title><link>https://thearchiveof.com/en/coding/experiments/samsung-earnings-event-lab/</link><guid isPermaLink="true">https://thearchiveof.com/en/coding/experiments/samsung-earnings-event-lab/</guid><description>Explore Samsung&apos;s pre-announcement price over different windows, compare peers, and separate a quarterly profit surprise from a one-day stock return.</description><pubDate>Sun, 27 Sep 2026 00:00:00 GMT</pubDate><category>Lab</category><category>Experiments</category><category>research</category><category>bayesian-inference</category><category>portfolio</category></item><item><title>Efficient Markets Through a Bayesian Lens: Why Does Everything Seem Priced In?</title><link>https://thearchiveof.com/en/investing/markets/efficient-markets-bayesian-lens/</link><guid isPermaLink="true">https://thearchiveof.com/en/investing/markets/efficient-markets-bayesian-lens/</guid><description>Samsung earnings, a Fed cut, and CPI surprises lead to a Bayesian view of how investors update beliefs, place orders, and shape prices.</description><pubDate>Sun, 27 Sep 2026 00:00:00 GMT</pubDate><category>Investing</category><category>Markets</category><category>research</category><category>bayesian-inference</category><category>inflation</category></item><item><title>Who Disappears First: The AI Team or the Business Teams?</title><link>https://thearchiveof.com/en/ai/ax/who-disappears-first-ai-or-business-teams/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/who-disappears-first-ai-or-business-teams/</guid><description>As agents take on more work, which team changes first? A task-level view of how enterprise AI may reshape both builders and business practitioners.</description><pubDate>Sat, 26 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>research</category><category>ax</category><category>enterprise-ai</category><category>ai-agents</category></item><item><title>Do Agents Have to Be Graphs? Why I Am Removing LangGraph from My Default Stack</title><link>https://thearchiveof.com/en/ai/ax/why-i-am-removing-langgraph-from-agent-building/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/why-i-am-removing-langgraph-from-agent-building/</guid><description>After building a multi-agent research system with LangGraph, I am rethinking where explicit graphs belong as models choose more of their own execution paths.</description><pubDate>Sat, 26 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>perspective</category><category>ai-agents</category><category>langgraph</category><category>ax</category></item><item><title>What Is Bayesian Statistics?</title><link>https://thearchiveof.com/en/math/statistics/bayesian-statistics-dog-walk/</link><guid isPermaLink="true">https://thearchiveof.com/en/math/statistics/bayesian-statistics-dog-walk/</guid><description>A dog&apos;s evening walk routine and a hypothetical Samsung Electronics price move explain priors, likelihoods, posteriors, sequential updating, and Bayesian statistics.</description><pubDate>Sat, 26 Sep 2026 00:00:00 GMT</pubDate><category>Mathematics</category><category>Statistics</category><category>foundation</category><category>bayesian-inference</category></item><item><title>Where Does Agent State Live? Redis, PostgreSQL, and Checkpoints</title><link>https://thearchiveof.com/en/ai/agents/where-agent-state-lives/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/where-agent-state-lives/</guid><description>Separate agent state into durable run records, hot projections, execution checkpoints, and process-local state, then place each by its failure and recovery requirements.</description><pubDate>Fri, 25 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>Why Is vLLM Slow?</title><link>https://thearchiveof.com/en/ai/ai-engineering/vllm-troubleshooting-metrics/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ai-engineering/vllm-troubleshooting-metrics/</guid><description>A practical guide to diagnosing vLLM serving bottlenecks by reading TTFT, TPOT, queue, prefill, KV-cache, and preemption signals together.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AI Engineering</category><category>implementation</category><category>enterprise-ai</category><category>evaluation</category><category>ai-agents</category></item><item><title>What is multi-objective optimization?</title><link>https://thearchiveof.com/en/math/optimization/multi-objective-optimization-battery-supply-chain/</link><guid isPermaLink="true">https://thearchiveof.com/en/math/optimization/multi-objective-optimization-battery-supply-chain/</guid><description>When cost, carbon, recycled content, and supply reliability collide, how do you decide? An EV battery procurement case I worked through.</description><pubDate>Thu, 24 Sep 2026 00:00:00 GMT</pubDate><category>Mathematics</category><category>Optimization</category><category>foundation</category><category>optimization</category><category>multi-objective-optimization</category><category>pareto-optimization</category><category>supply-chain</category><category>carbon-footprint</category></item><item><title>A Worker Is Not a Thread: Why Agent Execution Should Leave the API Server</title><link>https://thearchiveof.com/en/ai/agents/worker-is-not-thread/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/worker-is-not-thread/</guid><description>Why a worker is not another name for a thread or process, and when a long-running agent run should move from an API request to a queue and worker.</description><pubDate>Wed, 23 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>What is vLLM tuning?</title><link>https://thearchiveof.com/en/ai/ai-engineering/vllm-tuning-limited-gpus/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ai-engineering/vllm-tuning-limited-gpus/</guid><description>A practical guide to serving LLMs on limited on-premises GPUs: diagnose prefill, decode, KV cache, queues, and tail latency to tune vLLM for sustainable throughput.</description><pubDate>Tue, 22 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AI Engineering</category><category>implementation</category><category>enterprise-ai</category><category>ai-agents</category><category>evaluation</category></item><item><title>Async, Threads, and Processes: What to Know Before Agent Workers</title><link>https://thearchiveof.com/en/ai/agents/async-thread-process-agent-backends/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/async-thread-process-agent-backends/</guid><description>Classify agent-backend work as non-blocking I/O, blocking I/O, or CPU-bound computation, then choose among async, threads, and processes.</description><pubDate>Mon, 21 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>Why Enterprise AI Transformation Should Start Narrow</title><link>https://thearchiveof.com/en/ai/ax/ax-should-start-narrow/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/ax-should-start-narrow/</guid><description>General-purpose AI is a Swiss Army knife; enterprise AX is a purpose-built blade. A Market Intelligence case shows why transformation means redesigning work, not automating it.</description><pubDate>Mon, 21 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>research</category><category>ax</category><category>enterprise-ai</category><category>ai-agents</category><category>evaluation</category></item><item><title>The Point of AX Is Transformation, Not AI</title><link>https://thearchiveof.com/en/ai/ax/ax-is-transformation/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ax/ax-is-transformation/</guid><description>Why enterprise AX stalls, what practitioners actually need, and why organizational context matters more than another model.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AX</category><category>research</category><category>ax</category><category>enterprise-ai</category><category>ai-agents</category></item><item><title>Why Agent Systems Need Async: Making Waiting Time Useful</title><link>https://thearchiveof.com/en/ai/agents/why-agent-systems-need-async/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/why-agent-systems-need-async/</guid><description>Why agent backends need async, explained through blocking, coroutines, tasks, the event loop, await, and structured concurrency.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>Why Serve Open-Source LLMs with vLLM on Internal GPUs?</title><link>https://thearchiveof.com/en/ai/ai-engineering/why-vllm-for-internal-llm-serving/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/ai-engineering/why-vllm-for-internal-llm-serving/</guid><description>When internal GPU serving and vLLM make sense: compare external APIs, adoption trade-offs, batching and prefix caching in plain terms, and a pre-flight checklist.</description><pubDate>Sat, 19 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>AI Engineering</category><category>foundation</category><category>enterprise-ai</category><category>ai-agents</category><category>evaluation</category></item><item><title>Agent Backend Architecture at a Glance: How APIs, Queues, Workers, State, and SSE Fit Together</title><link>https://thearchiveof.com/en/ai/agents/agent-backend-architecture-map/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/agent-backend-architecture-map/</guid><description>How API, queue, worker, PostgreSQL, Redis, and SSE divide responsibility in an agent backend. Implementation detail lives in follow-up articles.</description><pubDate>Fri, 18 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category></item><item><title>Agent Pattern Design: From Tool Use to Planning, Parallelism, HITL, and Reflection</title><link>https://thearchiveof.com/en/ai/agents/agent-pattern-design/</link><guid isPermaLink="true">https://thearchiveof.com/en/ai/agents/agent-pattern-design/</guid><description>A plain-Python guide to tool use, parallel orchestration, planning, HITL, retry, and reflection—and to the boundary between LLM judgment and deterministic code.</description><pubDate>Thu, 17 Sep 2026 00:00:00 GMT</pubDate><category>AI &amp; AX</category><category>Agents</category><category>foundation</category><category>ai-agents</category><category>langgraph</category><category>evaluation</category></item><item><title>What is Pareto optimization?</title><link>https://thearchiveof.com/en/math/optimization/pareto-optimization-dinner-with-friends/</link><guid isPermaLink="true">https://thearchiveof.com/en/math/optimization/pareto-optimization-dinner-with-friends/</guid><description>An intuitive introduction to Pareto dominance, Pareto-optimal solutions, and the Pareto frontier through a New York dinner decision.</description><pubDate>Sat, 12 Sep 2026 00:00:00 GMT</pubDate><category>Mathematics</category><category>Optimization</category><category>foundation</category><category>optimization</category><category>pareto-optimization</category><category>multi-objective-optimization</category></item><item><title>What is optimization?</title><link>https://thearchiveof.com/en/math/optimization/what-is-optimization-dinner-with-friends/</link><guid isPermaLink="true">https://thearchiveof.com/en/math/optimization/what-is-optimization-dinner-with-friends/</guid><description>Optimization explained through a New York dinner plan: decision variables, objective functions, constraints, and why choosing one restaurant needs a binary decision.</description><pubDate>Tue, 01 Sep 2026 00:00:00 GMT</pubDate><category>Mathematics</category><category>Optimization</category><category>foundation</category><category>optimization</category><category>linear-programming</category><category>integer-programming</category></item><item><title>Why I Keep Research as an Archive, Not a Feed</title><link>https://thearchiveof.com/en/misc/essays/why-this-archive-is-open/</link><guid isPermaLink="true">https://thearchiveof.com/en/misc/essays/why-this-archive-is-open/</guid><description>Why I keep questions, evidence, assumptions, and revision conditions with the conclusion, so research can be revisited and reused.</description><pubDate>Mon, 31 Aug 2026 00:00:00 GMT</pubDate><category>Perspectives</category><category>Essays</category><category>foundation</category><category>ai-agents</category></item></channel></rss>