标签：#p

While other humanoid startups chase sky-high valuations, Agility Robotics is betting its future on execution — and a SPAC.

Open-source alternative to Storylane, Navattic, and Arcade Discussion | Link

The Problem Nobody Talks About Everyone's posting AI-generated videos — characters speaking with lip-sync, manga panels coming alive, virtual idols dancing. The pitch: "just describe what you want." I tried. For months. Here's what I got: Character's face morphed by frame 2 "Slowly looks up" became "violent head shake" Voice-over sounded like Google Translate Same prompt, 3 runs, 3 completely different results No idea what to include or how long the prompt should be Tutorials were either too vague ("be detailed") or too technical (parameter tuning from line 1). The real issue: video prompts are structurally different from text/image prompts. You need to simultaneously control visuals, motion, audio, camera, and consistency constraints — in the right order, at the right length. What I Found A Skill in the Model Studio official repo called happyhorse-prompt-studio . It doesn't teach you theory — it asks you questions and assembles the prompt for you . 4-phase flow: 1. Inspiration Menu Shows you 4 "flavors" of what HappyHorse can do: Flavor What it does A · Voiced Manga Drama Characters talk to each other, with voice + lip-sync B · Character Voice PV Single character self-introduction, 8-10 sec C · Manga Panel Motion Static manga panel starts breathing D · Virtual Idol MV Idol performance with choreography 2. Discovery Asks you conversationally: character appearance, scene, emotion, dialogue, voice type, art style, camera. 3. Prompt Assembly Assembles using the HappyHorse Formula : Scene + Subject + Motion + Audio + Quality Key techniques: @「Image n」 syntax locks character identity across shots Dialogue ≤15 characters (split shots if longer) Japanese prompts work best (HappyHorse is JP-optimized) Always end with キャラの顔・髪・衣装が変わらない (face/hair/outfit stays unchanged) 4. Quality Check Auto-reviews: completeness, compliance, cost estimate, optimization tips. Before vs. After Dimension Writing myself With Prompt Studio Attempts needed 10-20 before one usable 2-3 to satisfacti

A month ago we added a card_token column to the users table so a background job could retry failed Pro charges. It lasted about two days. Storing card data in your own database drops you into PCI-DSS (the compliance standard that kicks in the moment card data touches your systems), so we pulled it and moved to Stripe-managed payment methods. Last week the charges started failing again. New Claude Code session, no memory of any of that. Its plan? Add a card_token column to users and retry. I don't really blame the agent. It had the context the first time and it was right. The problem is that context died when the session closed. That's the part I never see mentioned about building with agents: the code sticks around, the reasoning doesn't. People leave a trail without trying. A commit message, a PR comment, the Slack thread before it. Agents don't, and the prompt that explained everything is gone by morning. So I built Selvedge to hold onto the reasoning. What happened the second time Selvedge is a local MCP server the agent calls as it works. There's a four-line block in our CLAUDE.md that says, roughly: before you touch an entity, check if we've been here before. $ selvedge prior-attempts users.card_token users.card_token Prior attempt 28 days ago ( reverted after 2 days ) Reasoning Added to store card tokens for one-click retries. Outcome REVERTED — kept card data out of our own DB to stay clear of PCI-DSS scope ; moved to Stripe-managed methods. So it didn't add the column. It charged off_session against the saved Stripe PaymentMethod instead. Charge retried, no card data in our database, done. We paid for that lesson once. How it works The agent writes down why live, in the moment, from the same context that made the change. That's the whole trick. A lot of the "git blame for AI" tools take your diff afterward and ask a second model to explain it. That's a guess. It reads well, but you can't really build on it. Selvedge stores what the agent actually meant, in i

In Part 1 , we introduced the idea that meaningful product design isn't about adding more — it's about knowing what to remove. Now let's examine this principle through a specific lens: meditation and mindfulness products. The Paradox of "More Mindfulness" Walk through any app store's health & wellness category and you'll find a strange contradiction: apps that promise to reduce your mental clutter by adding more things to your daily routine. Daily meditation streaks Guided breathing exercises (14 varieties) Sleep stories narrated by celebrities Mood tracking with 47 emotion labels Community challenges, leaderboards, badges AI-generated personalized recommendations The message is clear: "To feel less overwhelmed, here are 12 more things to do every day." This isn't just ironic — it's counterproductive. The cognitive load of managing a wellness routine can itself become a source of stress. The Feature Ceiling I've been studying meditation products for the past few months, and a pattern emerges across the market: Product Core Feature Total Features After 2 Years Calm Guided meditation ~40+ (stories, music, masterclasses) Headspace Guided meditation ~35+ (focus music, move, sleep casts) Balance Personalized meditation ~15 (singles, plans, skills) The most interesting case is Balance, which has fewer features but higher per-session engagement. Users spend more time meditating, not more time navigating. This isn't accidental. There's a cognitive principle at work: decision fatigue applies to self-care too. Every additional feature is another decision the user has to make before they can simply be still . What OneZen Gets Right OneZen takes the subtraction principle to its logical endpoint. Instead of asking "What can we add?" the product asks "What can we remove while still delivering value?" The result is a meditation tool that doesn't feel like a tool at all. It feels like breathing room. Three design choices worth studying: 1. No onboarding questionnaire. Most apps ask

This post was originally published on MatrixTrak.com — the production reliability toolkit for trading bot operators and .NET engineers. Complete WebSocket auto-reconnect guide for trading bots. Implement automatic reconnection with exponential backoff, heartbeat ping-pong, message gap detection, and state recovery. WebSocket connections drop. Not maybe. Definitely. Exchanges reset connections every 24 hours. Networks glitch. Load balancers rotate. HTTP proxies timeout. Your trading bot will experience disconnects. The question isn't whether you'll disconnect—it's whether your bot recovers correctly when you do. If you only do three things Implement automatic reconnection with exponential backoff and jitter. Track sequence numbers to detect missed messages. Always verify state via REST after reconnect. Never trust WebSocket alone. WebSocket Auto-Reconnect Quick Start If you just need a working auto-reconnect loop right now, here's the minimum viable implementation: class AutoReconnectWebSocket { private ws : WebSocket | null = null ; private reconnectAttempts = 0 ; private maxRetries = 10 ; private shouldReconnect = true ; async connect ( url : string ): Promise < void > { return new Promise (( resolve , reject ) => { this . ws = new WebSocket ( url ); this . ws . onopen = () => { this . reconnectAttempts = 0 ; resolve (); }; this . ws . onclose = ( event ) => { if ( this . shouldReconnect ) { const delay = this . backoff (); console . log ( `[AutoReconnect] Closed ${ event . code } . Reconnecting in ${ delay } ms` ); setTimeout (() => this . connect ( url ), delay ); } }; this . ws . onerror = () => { /* onclose fires next */ }; }); } private backoff (): number { const base = 1000 ; const max = 30000 ; const delay = Math . min ( base * Math . pow ( 2 , this . reconnectAttempts ++ ), max ); return delay + delay * 0.2 * ( Math . random () * 2 - 1 ); // +20% jitter } close (): void { this . shouldReconnect = false ; this . ws ?. close (); } } This handles the core auto

これは、Apidog が API テストおよび API ライフサイクル管理のためのコマンドラインツールである Apidog CLI をどのように開発したかを共有する全10回のシリーズです。順番に読むか、必要なテーマから直接参照してください。 今すぐApidogを試す タイトル 焦点 1 当社は126のMCPツールを構築しました。しかし、それはAgentにとって最良の解決策ではありません 問題の発見 2 なぜ当社は全く新しいApidog CLIを開発したのか アーキテクチャ開発 3 黄金律：CLIは事実を生成し、モデルは事実に従って行動する 核となる哲学 4 agentHints : CLIにAgentとの会話を教える 構造化出力 5 SKILL：運用経験をコードとして出荷する 運用経験 6 数字は嘘をつかない：ツール呼び出しは30%減、トークンは25%減 定量的結果 7 PRDからテストループまで：Apidog CLIによる完全なAgentワークフロー 実践的なチュートリアル 8 なぜCI/CD互換性がAgentツールにとって不可欠なのか DevOpsの視点 9 AIブランチ：AI Agentによるより安全なプロジェクト変更 セキュリティレイヤー 10 Spec-Firstは昨日。Skill-Firstへようこそ。 ビジョンと未来 当社は、MCPが最適化しない複雑なワークフロー、つまり検証ゲートと構造化された実行を伴うワークフローを処理するために、CLI + SKILLを構築しました。 MCPはその目的を果たし続けています CLI + SKILLに入る前に、前提を明確にします。 Apidog MCPは現在も利用可能で、メンテナンスされています。 MCPは、プロトコルに従って標準化されたツール接続を提供します。特に以下の用途に適しています。 シンプルで明確に定義された操作 MCPベースのワークフローを好むユーザー MCP準拠クライアントとのエコシステム統合 当社はMCPを置き換えたわけではありません。CLI + SKILLはMCPを補完するために構築されました。 MCPは ツール接続 に優れています。一方で、検証、読み戻し、実行確認を伴う多段階のR&Dワークフローでは、Agentに対して 実行可能なエンジニアリングプロセス を提供するほうが安定します。そこにCLI + SKILLが適合します。 タスクごとに使い分けると、次のようになります。 タスクタイプ 推奨されるアプローチ シンプルなツール呼び出し（例：エンドポイントの取得） MCPまたはCLI。どちらも機能します 多段階ワークフロー（例：テストの作成、検証、実行） CLI + SKILL。より良い体験になります CI/CD統合 CLI。ネイティブに適合します MCPエコシステム統合 MCP。プロトコル標準に適合します 古いCLI：最後にテストを実行する Apidog CLIは長年、APIテストを実行するためのコマンドラインのエントリポイントでした。 apidog run --project <projectId> --test-scenario <scenarioId> --environment <environmentId> この基盤は今も重要です。チームには以下を行うための信頼できる方法が必要です。 ターミナルからAPIテストを実行する CIパイプラインでレポートを生成する 自動化ワークフロー内で品質ゲートを維持する ただし、古いCLIの主な役割は テスト実行 でした。つまり、ワークフローの終盤で使われます。 設計 → ドキュメント化 → モック → デバッグ → テスト → [CLIがテストを実行] CLIは最後のステップでした。他の作業が完了したあとに、既存のテストを実行するためのものだったのです。 新しい要件：Agentにはより多くの操作が必要 API開発は変化しています。 AI Agentは現在、APIライフサイクルの複数段階に参加します。 段階 Agentの活動 API設計 PRDからエンドポイント定義を生成する テスト生成 API仕様からテストケースを作成する デバッグ 障害を分析し、修正案を提示する 移行 プロジェクト間でAPIを移動する メンテナンス API変更時にテストを更新する このようなワークフローでは、CLIは既存テストを最後に実行するだけでは不十分です。 Agentが安定して作業するには、CLI側で次の操作を提供する必要があります。 APIアセット（エンドポイント、スキーマ、環境）を読み取る テストアセット（テストケース、テストシナリオ）を作成または更新する 書き込み前に構造化された変更を検証する 変更をプロジェクトに書き戻す 実行結果を検証

The AI video editor you hire that edits like a human Discussion | Link

It Started With a Simple Misunderstanding I was spelling something over a phone call. I said: "B" The other person heard: "D" So I repeated it. Still wrong. Then I remembered something I'd heard before: "B as in Bravo." Instantly... There was no confusion. That's When I Realized Some letters sound almost identical. Especially over: Phone calls Weak connections Noisy environments Different accents And repeating the same letter five times doesn't always help. Why I Built This Tool So I built something simple: 👉 https://allinonetools.net/phonetic-alphabet-converter/ A tool that instantly converts normal text into the NATO phonetic alphabet. For example: CHAT Becomes: Charlie Hotel Alpha Tango No signup. No setup. Just: Paste → Convert → Read What I Learned Before building this, I thought the phonetic alphabet was mostly for pilots or the military. Turns out it's useful for anyone who needs to spell things clearly. Like: Email addresses Usernames License keys Customer support Phone conversations The Small Problem It Solves Have you ever said: "M" And someone replied: "N?" Or: "P?" 😅 That's exactly the kind of confusion this avoids. Why It Works So Well Instead of similar-sounding letters... You use unique words. Like: A → Alpha B → Bravo C → Charlie D → Delta It's much harder to misunderstand. What Surprised Me I expected only developers or IT people to use it. But it also makes sense for: Customer support Call centers Students Remote workers Anyone spelling things over the phone What I Focused On I wanted the tool to be: Fast Simple Easy to copy Beginner-friendly Because if you're already on a call... You don't want extra steps. The Real Insight Good communication isn't always about saying more. Sometimes it's about making sure the first attempt is understood. Simple Rule I Follow Now If people keep repeating themselves... 👉 There's probably a simpler way to communicate. Final Thought The NATO phonetic alphabet has been around for decades. But after using it once... Yo

The obvious fix for "my projects all look similar" is a better README — more screenshots, clearer descriptions, maybe a comparison table. I considered that for about five minutes and decided it was still just a nicer list of links. What actually made a portfolio project feel different was making it something you could talk to instead of read. That's what MCP (Model Context Protocol) is built for — it's the standard that lets AI clients like Claude Desktop call external tools directly, not just process text. So I built a server that exposes my 9 projects as queryable tools instead of static entries. What is MCP, and why does it matter here Almost every AI-developer portfolio I've seen is a list of links. Mine now includes something you can actually talk to . Open Claude Desktop, connect my server, and ask "what has Ayush built with FastAPI?" — it doesn't guess from a cached README, it calls a real tool and answers from structured, live data. What I built A Python MCP server ( FastMCP , stdio transport) exposing five tools: list_projects — short summary of all 9 projects get_project_details(project_name) — full stack, GitHub link, demo URL for one project, fuzzy-matched by name search_projects_by_stack(technology) — "show me everything using Groq" or "LangGraph" or "React" get_flagship_project — the single best project to look at first get_resume_summary — background, target role, core stack The data itself lives in plain Python dictionaries right now — no database needed for something this size. Each tool is a thin function around that data, decorated with @mcp.tool() . @mcp.tool () def search_projects_by_stack ( technology : str ) -> list [ dict ]: """ Find all projects that use a given technology or tool. """ query = technology . lower (). strip () matches = [ { " name " : p [ " name " ], " stack " : p [ " stack " ], " github " : p [ " github " ]} for p in PROJECTS if any ( query in tech . lower () for tech in p [ " stack " ]) ] return matches or [{ " message " : f

FROST 的治理哲学：为什么每个 Agent 系统都需要一部宪法 "细胞会死，但谱系会存续。Agent 会消亡，但宪法会传承。资产会永存。" 在 AI Agent 框架百花齐放的 2026 年，我们见证了一个有趣的现象：框架越来越多，治理却越来越缺失。LangChain 给了你工具链，CrewAI 给了你角色扮演，AutoGen 给了你对话——但没有人回答一个关键问题： 当你的 Agent 家族有十代、百代，谁来保证它们的行为不越界？ 这就是 FROST 要解决的问题。 一、一个被忽视的问题：Agent 治理真空 想象这样一个场景：你构建了一个 Agent 系统，它帮你处理客户咨询、自动写报告、管理财务。一开始只有 3 个 Agent，你都能监控。三个月后，Agent 数量变成了 30 个——有些是你创建的，有些是 Agent 自己创建的。 问题来了： 某个 Agent 开始访问不该访问的数据 某个 Agent 创建的子 Agent 继承了一份不该继承的权限 某个 SOP 工作流在运行中被人悄悄修改了 这不是科幻场景，这是今天 Agent 系统正在发生的事。 根本原因 ：现有框架的"治理"要么是提示词级别的软约束（"请你不要访问这些数据"），要么是事后的日志审计。没有一个是代码级别、架构级别的硬约束。 FROST 的设计哲学是： 治理必须是架构的一部分，而不是补丁。 二、FROST 的宪法模型：四层治理 FROST 把治理拆解为四个层次，每一层都有对应的代码实现： 第一层：只读继承——权限的代码级强制 在大多数框架中，Agent 之间的数据共享靠的是"约定"。FROST 用的是 HierarchicalStore ——一种层级化记忆容器： class HierarchicalStore : """ 层级化记忆存储。 祖先 Store 对后代只读——后代可以继承，但不能篡改。 """ def __init__ ( self , data = None , parent = None , readonly = False ): self . _data = data or {} self . _parent = parent self . _readonly = readonly # 关键：只读标记 def save ( self , key , value ): if self . _readonly : raise PermissionError ( " 只读 Store 禁止写入 " ) self . _data [ key ] = value def load ( self , key , default = None ): if key in self . _data : return self . _data [ key ] if self . _parent : return self . _parent . load ( key , default ) return default 注意 readonly 参数。当一个 Agent 创建子 Agent 时，子 Agent 对父 Agent 的 Store 是 只读的 。这不是提示词告诉 Agent "请你不要修改"，而是代码直接抛出异常。 这意味着 ：即使 LLM 产生了幻觉，试图越权写入，代码层面也会拒绝执行。 第二层：SOP 宪法校验——工作流的可审计性 在 FROST 中，SOP 不是随便定义的步骤列表，而是经过祖辈审核的"宪法文本"： def validate_sop ( ancestor_sop , descendant_sop ): """ 祖辈验证后代的 SOP 是否合规。 检查点： 1. 后代 SOP 的步骤不能超出祖辈定义的边界 2. 后代 SOP 不能调用未授权的 Skill 3. 后代 SOP 的数据访问不能超出权限范围 """ # 检查 1：步骤边界 for step in descendant_sop . steps : if step not in ancestor_sop . allowed_steps : raise SOPValidationError ( f " 步骤 { step } 超出祖辈定义的边界 " ) # 检查 2：Skill 授权 for skill in descendant_sop . required_skills : if skill not in ancestor_sop . authorized_skills : raise SOPValidationError ( f " Skill { skill } 未获授权 " ) return True 这意味着 ：任何后代 Agent 想要执行的工作流，都必

A friend messaged me a photo of a sealed booster box last month with one question: "worth it?" He'd already decided, really. The chase card in that set was all over his feed, so the box felt like a good deal. I asked him to send me the pull rates instead of the hype, and we spent twenty minutes turning "worth it?" into something we could actually compute. That exercise is a small, self-contained data problem. It's also a good example of how a clean-looking model can hand you a confident number that doesn't survive contact with reality. If you like building little estimators, this one is worth doing carefully, because the interesting part isn't the formula. It's everything the formula assumes. The formula is the easy part Expected value of a box is a weighted sum. Each card you can pull has a probability and a market value, and you multiply the two across every slot the box gives you. That's it. Undergrad probability. Here's a stripped-down version for a hypothetical set. I'm using made-up numbers so nobody mistakes this for real pull data — the point is the shape of the computation, not the specific set. # One "hit slot" in a box: probabilities cover the full outcome space. # Values are illustrative market estimates in USD. hit_table = [ { " name " : " Alt-art chase " , " p " : 0.0125 , " value " : 180.00 }, { " name " : " Secret rare " , " p " : 0.030 , " value " : 45.00 }, { " name " : " Full-art rare " , " p " : 0.100 , " value " : 8.00 }, { " name " : " Standard hit " , " p " : 0.400 , " value " : 0.55 }, { " name " : " No notable hit " , " p " : 0.4575 , " value " : 0.06 }, ] assert abs ( sum ( row [ " p " ] for row in hit_table ) - 1.0 ) < 1e-9 ev_per_slot = sum ( row [ " p " ] * row [ " value " ] for row in hit_table ) hit_slots_per_box = 36 # e.g. one meaningful slot per pack ev_box = ev_per_slot * hit_slots_per_box print ( f " EV per slot: $ { ev_per_slot : . 2 f } " ) # $4.65 print ( f " EV per box: $ { ev_box : . 2 f } " ) # $167.31 The box costs $150 sea

Last week, I asked my AI agent to scrape 300 job listings from a recruiting site. It broke at row...

Everyone talks about AI speeding up coding. Nobody talks about debugging AI-generated code. Last month, I spent three hours hunting down a bug in a 20-line function that an LLM wrote in thirty seconds. That's not a productivity gain—that's a productivity swap. You trade typing speed for debugging speed, and most of the time the trade is terrible. I've been using AI assistants for about a year now, mostly Claude and GPT-4, and I've noticed a pattern. The first version of any moderately complex piece of code always has at least one subtle mistake. Not syntax errors—those are easy. I'm talking about logical off-by-ones, missing edge cases, or completely hallucinated API calls. And the worst part? The AI writes the code with such confidence that you assume it's correct. You run it, it crashes, and you spend ten minutes thinking you misused the function before you finally look at the generated code with a suspicious eye. Let me show you a concrete example. I was building a small Node.js service that fetches data from a paginated REST API and merges the results. I asked the AI to write a function that handles pagination with a while loop and an offset parameter. Here's what it gave me: async function fetchAllPages ( baseUrl , limit = 100 ) { let offset = 0 ; let allData = []; let hasMore = true ; while ( hasMore ) { const response = await fetch ( ` ${ baseUrl } ?limit= ${ limit } &offset= ${ offset } ` ); const data = await response . json (); allData = allData . concat ( data . results ); hasMore = data . results . length === limit ; offset += limit ; } return allData ; } Looks clean, right? I pasted it in, ran my test, and got an infinite loop. The server returned a 400 error after a few requests, but the function kept going because response.ok was never checked. The AI assumed every call succeeds. I spent forty-five minutes debugging that—not because the bug was hard, but because I trusted the output. I added a try/catch and a status check, and then I found the real is

Before adopting DSPy, prove the LM program has a contract DSPy is easy to undersell. If you describe it as "a nicer way to write prompts", you will probably test the wrong thing. The better first test is this: can your language-model workflow be expressed as a small program with declared inputs, declared outputs, measurable examples, and an optimizer that is allowed to change prompts without changing the business boundary? That is the point where DSPy starts to make sense. The upstream README positions DSPy as a framework for programming, rather than prompting, foundation models. The current Doramagic project pack for stanfordnlp/dspy also points at the same starting command: pip install dspy . The package metadata I checked today declares name="dspy" , version 3.3.0b1 , and Python >=3.10,<3.15 . The GitHub API snapshot showed the repository was still active, with a push on 2026-07-05 and recent pull requests around empty evaluation sets, document formatting, and GEPA trace attribution. That activity is useful, but it is not the adoption proof. The proof is whether your own task can survive three separations. 1. Separate the task contract from the prompt In DSPy terms, the first artifact worth reading is not a clever prompt. It is the Signature. A Signature says what goes in and what must come out. A Module wraps that contract into something callable. An Adapter turns the contract into the provider-facing prompt format and parses the model response back into fields. That gives you a practical review question: Can the team name the output fields before anyone starts tuning wording? If the answer is no, DSPy will not rescue the workflow. You are still negotiating the task itself. The first pass should be a tiny contract: input text, retrieved context if needed, answer, citations, confidence, or whatever fields the product actually needs. Do not start with agents, tools, or multi-stage pipelines. 2. Separate compilation from runtime correctness DSPy optimizers can impr

Introduction: When Does On-Premises Outpace the Cloud? For small businesses like ComputeLabs , the decision between on-premises servers and cloud services isn’t just about cost—it’s about predictable stability versus elastic flexibility. With stable workloads (websites, email, file storage, backups, internal apps), the question narrows: Does a one-time server purchase amortized over 5–7 years beat monthly cloud bills? The answer hinges on a total cost of ownership (TCO) analysis , where upfront CAPEX collides with recurring OPEX , and hidden costs lurk in both models. The CAPEX vs. OPEX Tug-of-War On-premises servers demand a high initial investment —hardware, software licenses, setup. For a small business, this could mean $5,000–$15,000 upfront , depending on specs. Cloud services, in contrast, operate on a pay-as-you-go model , with monthly costs averaging $100–$500 for similar workloads. But here’s the catch: Cloud costs compound. Over 5 years, that’s $6,000–$30,000 —potentially double the on-premises CAPEX. The break-even point? When the cumulative cloud spend exceeds the depreciated server cost , typically 3–4 years in , assuming no major upgrades. Hidden Costs: The Silent Budget Killers On-premises servers aren’t just a one-time buy. Electricity (a 2U server consumes ~ 500W/hour , costing ~ $400/year ), cooling (fans degrade, heat expands components, shortening lifespan), and maintenance (disk failures, OS patches) add $500–$1,000/year. Cloud services mask these costs but introduce their own: data egress fees (AWS charges $0.09/GB for outbound transfers), premium support ( $100+/month ), and vendor lock-in (migrating data is costly). The edge case? Regulatory compliance —if data must stay on-premises, cloud costs become irrelevant, but self-managed security (firewalls, patches) becomes a non-negotiable expense. Scalability vs. Stability: The Workload Paradox Cloud’s elasticity is its strength—but for stable workloads, it’s overkill. An on-premises server sized

If someone compromised one of your project's dependencies today, would they be able to steal your...

Most SaaS backends were built around a simple assumption: The user pays a subscription, then uses the product. That assumption breaks down for AI apps. An AI app does not just serve screens. It spends money while it works. A user searches the web. A model summarizes a report. An image model generates a draft. An agent calls an MCP tool. A workflow buys data from an API. A future x402 endpoint charges for a capability call. Every one of those actions can have a marginal cost. That means the backend for an AI app is no longer just a place to store users, projects, and settings. Increasingly, it is a system of record for economic activity. In other words: AI app backends are becoming accounting systems. The old SaaS model was simpler Traditional SaaS could survive with coarse billing. You had: monthly subscriptions seats tiers maybe a usage limit somewhere That worked because the marginal cost of most product actions was close enough to zero. If a user clicked a button, edited a document, opened a dashboard, or created a project, the backend cost was usually small compared with the subscription price. The business could average it out. AI apps are different. The product may call paid APIs on almost every useful action. Search once. Summarize once. Generate once. Transcribe once. Call an agent tool once. The unit economics are inside the interaction loop. If the product cannot see who spent what, when, and why, the business is flying blind. Usage billing is not an add-on For AI apps, usage billing is often treated like a pricing feature. I think that is too narrow. Usage billing is really a cost ledger. It answers: which user triggered the cost? which project or app did it belong to? which capability was called? what did it quote before execution? what did it actually cost? was it retried? was it idempotent? did the end user pay for it? is there a payment or checkout record attached? If you cannot answer those questions, you do not have a reliable production backend for

TL;DR 23 commits across 4 repos, one theme: opening apps to the outside world, safely. Public: kickoff v1.32.0 ships SDK-free support-widget integration stubs. Private: external intake channels (token-authed API, cookie-free widget, signed webhooks) on a helpdesk product; signed public API + rebuild webhooks on an event platform. Everything today was about external surfaces — letting the outside in without leaving the door unlocked. What shipped Where What kickoff v1.32.0 (public) SDK-free support-widget integration stubs: settings class + migration, Livewire admin settings page, Blade component, docs, Pest coverage Helpdesk product (private) External intake channels: token-authed API, magic-link requester view, cookie-free embeddable widget, signed outbound webhooks, hardening pass from an adversarial review Event platform (private) Signed public event API + landing-page rebuild webhooks, persona nav overhaul, 15 new MCP tools, offline PWA check-in, plan-limit enforcement Event platform docs (private) Tracker updates + before/after UX screenshots Stubs, not SDKs kickoff now ships a support-widget integration as stubs — settings class, migration, admin page, Blade component — copied into your app. No composer dependency for glue code: you own it, you can read it, you can change it. For ~100 lines of integration code, a stub beats a package. Intake is three problems The helpdesk work was the day's core: letting outside systems and end users create tickets. Every inbound surface splits into the same three problems — who gets in (token auth, magic links), what they can do (rate limits, severity clamps, single-use entry), and what you send back out (signed, idempotent webhooks). An adversarial review caught four real issues before launch; that story gets its own post, next. Static pages, fresh data The event platform got a signed public API plus webhooks that fire on content changes — so landing pages can be static builds that rebuild themselves when an event changes. C

We’ve all been there: it’s 7:00 PM, you’re exhausted after a long sprint, and you open a food delivery app. Your brain screams "Double Cheeseburger," but your body is still recovering from that mid-afternoon sugar spike. What if your phone was smart enough to say, "Hey, your blood sugar is currently 160 mg/dL and rising—maybe skip the extra fries?" In this tutorial, we are building a Chief Health Officer (CHO) Agent . This isn't just a simple chatbot; it’s a sophisticated AI Agent using LangGraph to bridge the gap between real-time medical data (CGM) and real-world actions (Food Delivery APIs). By leveraging automation , function calling , and state machines , we’ll create a system that actively protects your metabolic health. The Architecture: How the CHO Agent Thinks To build a reliable agent, we need a "stateful" workflow. We aren't just sending a prompt to an LLM; we are creating a loop that monitors glucose levels, analyzes food options, and interacts with the browser. graph TD A[Start: Hunger Trigger] --> B{Fetch CGM Data} B -->|Sugar High/Unstable| C[Constraint: Low GI Only] B -->|Sugar Stable| D[Constraint: Balanced Meal] C --> E[Scrape Delivery App Menu] D --> E E --> F[Agent: Analyze Ingredients & GI Index] F --> G[Selenium: Mark/Filter Non-Compliant Items] G --> H[End: Safe Ordering] subgraph "The LangGraph Loop" C D E F end Prerequisites Before we dive into the code, ensure you have the following: LangGraph & LangChain : For the agent's cognitive architecture. Dexcom API Credentials : To fetch real-time Continuous Glucose Monitor (CGM) data. Selenium : For interacting with food delivery web interfaces (Meituan/Ele.me). OpenAI API Key : Specifically for GPT-4o’s reasoning and function-calling capabilities. Step 1: Defining the Agent State In LangGraph, everything revolves around the State . Our CHO agent needs to track the current glucose level, the user's health constraints, and the list of available food items. from typing import TypedDict , List , Anno