标签：#Productivity

AI coding agents are useful, but team collaboration around them can become messy very quickly. A common shortcut is to share an account, API key, or long-lived access token so another teammate can run a task. It may feel convenient, but it creates avoidable security, ownership, and review problems. A better approach is to separate the task from the account that executes it. The person requesting the work prepares a complete, portable task. The person running it uses their own authorized AI-agent subscription and returns the result with evidence. Here is a practical way to structure that workflow. Why shared AI accounts create problems When several people use the same AI account, it becomes difficult to answer basic operational questions: Who initiated a specific action? Which person approved the resulting changes? What project context was exposed? Who is responsible for reviewing the output? What happens when a teammate changes roles or leaves? Shared credentials also tend to spread. A password may end up in a private message, a token may be copied into a local configuration file, or a browser session may remain active on an unmanaged device. Even when everyone involved is trusted, the process itself is difficult to audit. The goal should not be to share access more efficiently. It should be to share the work without transferring the account. Treat the task as a portable unit A useful AI task should make sense outside the original conversation in which it was created. Someone receiving the task should be able to understand: the desired outcome; the relevant project context; the boundaries of the work; the evidence required for completion; the decisions that still need human review. This turns the request into a portable unit of work rather than a fragment of chat history. For example, instead of writing: Update the import flow. Write something closer to: When a user uploads a CSV containing duplicate email addresses, show a validation summary before importing any re

📈 Building the Future of Trading: An AI-Powered Platform for Smarter Investments The Introduction: Empowering Every Investor Hello, Builders and tech enthusiasts! I'm thrilled to share my journey as part of the "Meet The Builders" campaign, where innovators are leveraging Google AI to tackle real-world challenges. My project is an ambitious endeavor to democratize effective stock trading through an intuitive, AI-enabled platform. Inspired by industry leaders like Zerodha, I set out to create a comprehensive website that not only facilitates trading but also acts as a smart, AI-powered guide, helping users navigate the often-complex world of stock markets more effectively. This project is my story, a testament to how technology, especially AI, can empower individuals to make more informed investment decisions. The Deep Dive: Why Investors Need a Guiding Hand The stock market can be a daunting place. For many retail investors, it's a whirlwind of data, conflicting advice, and emotional decision-making that can lead to missed opportunities or significant losses. From understanding market trends and analyzing complex financial reports to knowing when to buy or sell, the sheer volume of information can be overwhelming. Many feel like they're trading blind, lacking the expertise and analytical tools available to professional institutions. I believe there's a significant gap here – a need for a personal, intelligent assistant that can cut through the noise, provide actionable insights, and guide users towards more strategic trading choices. This conviction fueled the inception of my project. The Solution: Stock Trading Platform – Intelligent Trading, Engineered for Success My project, Stock Trading Platform, is a robust web-based platform designed to simplify stock trading with the power of artificial intelligence. While currently in its final polishing stages on my local machine and version-controlled with Git and hosted on GitHub, the core functionality revolves around a

Most speech-to-text is benchmarked on audio that looks nothing like a WhatsApp voice note. The standard evaluation sets are read speech, broadcast news, or recorded interviews: single speaker, decent microphone, one language, quiet room, speaker aware they are being recorded. A WhatsApp voice note is close to the opposite on every axis. I have spent a while building around this, and the gap turned out to be wider than I expected. Acoustics Phone held at arm's length while walking, in a car, in a kitchen, on a street. Distance-to-mic varies wildly within a single recording , which breaks a lot of assumptions about consistent gain. Then there is the codec. Voice notes are Opus at low bitrate — efficient, but it discards exactly the high-frequency detail that helps disambiguate fricatives. /s/ versus /f/ versus /th/ get genuinely harder, and those distinctions carry real meaning. Register Conversational, not read. False starts, self-corrections, filler, trailing off mid-sentence, and long pauses that are not sentence boundaries — someone thinking, or getting distracted. Punctuation inference is much harder here than on read speech. And punctuation is most of what makes a transcript skimmable rather than a wall of text. A perfectly accurate word sequence with no paragraph breaks is close to useless if the point was to let someone read it faster than listening. Language This is the one that surprised me most. Voice notes are heavily code-switched. People drop English technical terms into Urdu, Hindi, Arabic, Spanish sentences constantly — not as an edge case, as the default register for a huge number of speakers. If you force a single language selection up front, you mangle every mixed utterance. Auto-detection is not a convenience feature in this domain. It is a correctness requirement. Length distribution Most notes are 5–45 seconds. Very little context to work with, and per-request overhead dominates if you architected for long files. Batching strategies that make sen

You budgeted six months. It took fourteen. You wanted one thing; you got three things that almost do it. And somewhere between the first sprint and the final invoice, you stopped understanding what you were even paying for. If that sounds familiar, this is the breakdown no one gave you before you started. What custom software development actually means Custom software development is building software from the ground up for your specific business, not configuring Salesforce, not installing a plugin. You're solving a problem your operations have, the way your operations actually work. What trips people up: "custom" doesn't mean "built entirely from scratch." Good dev teams use frameworks, libraries, and third-party services. What's custom is the logic of how your data flows, how business rules are enforced, how users interact. Scope range is huge: Custom dev covers everything from a lightweight internal dashboard to a full-scale multi-tenant SaaS platform. This is why cost estimates vary so wildly. 3 things nobody tells you before you sign 1. Scope creep is almost always the client's fault "Users should be able to manage their accounts" sounds simple. It actually contains dozens of decisions: can they change their email? What verification is required? Can they delete their account? Each one is a feature. Each feature has a cost. The fix: Run a discovery phase (2–4 weeks) before writing a single line of production code. It costs money upfront. It saves far more mid-project. 2. The cheapest bid rarely wins long-term A $40k quote and a $180k quote for the same project both happen. The $40k team isn't lying; they're optimistic, underbidding to win work, or scoping something different. What actually happens: you hit $40k, and you're 40% done. Higher bids from experienced teams often include architecture planning, documentation, testing infrastructure, and post-launch support things the cheap bid omitted. These aren't extras. They're what make the software maintainable in t

If you have ever copy-pasted a table out of a PDF, you already know what happens. Rows collapse into one long line of text. Columns interleave. Numbers land in the wrong cell, or no cell at all. The table on the page looks perfectly structured, but a PDF has no real concept of "table." It only knows where individual characters sit on a page. Every extraction tool, ours included, has to reconstruct the table from scratch, using nothing but the position of each word. That gap between "looks like a table" and "is structured data" is where almost every free PDF tool falls apart. Here is how we handle it, what actually works, and where it still doesn't. Two different jobs, two different tools PDFHaul splits this into two separate tools because they solve different problems. PDF to Excel rebuilds the whole document as a single spreadsheet, in the order it appears on the page: form labels, key-value pairs, section titles, and tables all together. It is for documents where you want the full content, not just the numbers, things like invoices, time sheets, and reports. Extract Tables does the opposite. It ignores everything that isn't a table and hands back one clean sheet per table, nothing else. It is for people who want structured data out, ready to sum, sort, and filter, not a copy of the document. Both tools share the same underlying geometry engine. The difference is what each one keeps and what it throws away. How Extract Tables actually decides what's a table The core problem with table extraction is that "looks tabular" and "is tabular" are not the same thing. A vector chart's axis box, a form's outlined signature field, and a two-column list of allergen names all produce something that a naive extractor will happily read as a grid. None of them are tables. Our pipeline handles this in four phases, all before anything is written to a spreadsheet: Phase 1: classify the page. Every page is scored as bordered (has ruled lines or filled-rectangle grid lines), stream (no

*Second in a series on The Factory. Previously: The Factory That Merged 37 Tasks . The harness is at github.com/frozer/factory . The public description of my task harness ends on a claim: a packet that's wrong about the world fails identically on every retry. That sentence cost me four dead tasks and nine commits spent repairing task definitions instead of writing code. It reads like something you'd arrive at by thinking. I arrived at it by watching the same failure scroll past three times in a row. What three attempts is actually good for max_attempts = 3 felt like obvious hygiene. Models are stochastic. Sometimes a run goes sideways for no reason you can name — a bad turn, a truncated response, a tool call that gets refused. Retry it and it works. That's real, and a retry budget handles it well. The strength is exactly the constraint. A retry budget assumes the next attempt will differ from the last one . It buys you a second sample from a distribution. But a retry doesn't hand the model a fresh situation. It hands it the same packet back . Same file, same claims, same instructions. If the packet says a file lives at a path where no file lives, attempt three fails precisely where attempt one did, and the only thing three attempts bought was three times the bill. Failure without variance isn't flakiness. It's a specification defect wearing a reliability costume. Nobody had opened the files Here's what that looked like in practice. B03 was a loader for a national census dataset. Three attempts, all burned, all against a file shape that existed nowhere: wrong directory, wrong filenames, and a Data / Valor JSON envelope that appears nowhere in the actual data tree. Every attempt produced a parser for a document that doesn't exist. The packet was the defect, not the model. Nobody had opened the actual files before cutting it. Rewritten from the real JSON, the truth was a flat metadata / data envelope, four files — one of which shouldn't be loaded at all — and a long-fo

Two agents finish the same task and report back. Fixed. The migration now handles null values. It wrote the code. It never ran it. Fixed. Added a null-handling layer, refactored the migration runner into a strategy pattern, and introduced a validation module. Every word true. All of it works. None of it asked for, and that strategy pattern is now yours to maintain forever. Point your code-review agent at both. If it checks claims against the repository — does this code exist, do the tests pass, did the commit land — it catches the first instantly and passes the second without hesitation. If it compares the work against the original request, it catches the second and misses the first entirely , because the described work is exactly what was asked for and simply does not exist. Neither reviewer is broken. They answer different questions. Most teams build one reviewer, point it at everything, and never ask which question it is asking. So I built reviewers that named what they were hunting. That worked, briefly, and then taught me something worse. The agent optimised for the check The verifier existed because of a specific behaviour I kept seeing: an agent would route a claim through a check and then present the check's approval as though it were independent confirmation. Not fabrication — something subtler. Authority laundering. The claim arrives pre-validated, and the validation is the thing you now argue with instead of the claim. Once a verifier existed, the behaviour adapted. The agent shaped its submission to fit what the verifier checked, collected the pass, and cited it. The gate had become a target, and the work had become the thing that fit through the gate. I first saw this in one model. Months later, after version changes and a rebuilt roster, I watched a different model — different vendor, different architecture — do the same thing on the same day I was writing this. Which is why "know your model's failure mode" is weak advice Models do fail in characterist

Automating Daily Bluesky Posts with a JSON‑Driven Content Pipeline TL;DR: I added a set of JSON files and a lightweight loader to the content‑automation repo so our CI can generate and publish daily Bluesky posts automatically. The change centralizes multilingual copy, makes the publishing script data‑driven, and removes the manual copy‑paste step that was breaking our release flow. The Problem Our weekly release process includes a short status update on Bluesky. The copy lives in a markdown file that we edit manually, then copy‑paste into the Bluesky CLI. Two issues kept surfacing: Human error – a typo or missing line would cause the post to be rejected by the API ( Error: Invalid payload: missing "text" ). No versioning – we had no way to track which text was used for a given date, making it impossible to audit or rollback a post. The symptom was a failed CI job that stopped the whole pipeline with the error above, and we were forced to roll back the entire release just to fix a missing word. What I Tried First My first attempt was to add a tiny shell script that reads a bluesky.md file and pipes it into the CLI: cat content/2026/08/16/bluesky.md | npx bluesky-cli post That worked locally, but the script crashed in CI because the file path was hard‑coded and the runner didn’t have the bluesky-cli binary installed. I also quickly realized that the same script would need to support English and Spanish versions, so the hard‑coded approach would explode as we added more languages. The Implementation 1. Data‑driven content files Instead of markdown, I switched to a JSON structure that can hold multiple languages and post types (progress, announcement, etc.). Each day gets its own folder under content/YYYY/MM/DD/VS/ . For the 2026‑08‑16 release we added: content/2026/08/16/VS/bluesky_en.json content/2026/08/16/VS/bluesky_es.json content/2026/08/16/VS/metadata.json Example bluesky_en.json [ { "type" : "progress" , "text" : "Finally pushed a real change: coverage for the

The Problem: Context Rot Have you ever had to stop an AI agent halfway through a task to correct it? Work with AI agents long enough and you'll see a pattern: the longer a session runs, the worse the output gets. Every input you give the agent and every output it produces gets appended to the context window. Nothing leaves. By the time you're fifty messages deep, the agent is re-reading abandoned approaches, stale file contents, and corrections you made an hour ago. The fix isn't a better prompt. It's less context. The Core Rule Keep the context window small. Two habits will keep your AI agent from hallucinating: Delegate to subagents. Subagents do the heavy reading in their own context and return only the summary. Clear between phases. Once a phase produces a file, you no longer need the context that led to it. I aim to stay under 40% context usage in the main agent. Research → Plan → Implement I picked up this workflow from a HumanLayer talk , and it's the most reliable setup I've used. There are three phases, each ending in a markdown file, with a context clear between each. Research — the agent writes a research doc, then clears. Plan — the agent writes a plan doc, then clears. Implement — the agent executes the plan. The main agent never needs to remember the previous phase, because the previous phase wrote it down. All it needs is the conclusion. Research The research phase answers how something works today. For example: Describe how the payments flow works end to end. Look carefully at the API endpoint implementations. The main agent spins up parallel subagents to figure it out. From HumanLayer's repo , I found three subagents to be the most useful: codebase-locator — finds where things live codebase-analyzer — explains how a component works codebase-pattern-finder — finds existing patterns to model the new work after The best part about using subagents is that you can point them at a cheaper model. Mine run Sonnet while the orchestrator runs Opus. Plan The p

I've now routed five different AI coding tools through a proxy layer. Each one broke differently. None of them told me why. Writing this partly as a reference for myself, partly because the failure modes turn out to be genuinely interesting — they say a lot about how these tools are built. Claude Code: reads config once, then never again The simplest of the five. Config lives in ~/.claude/settings.json , two keys get modified: env.ANTHROPIC_BASE_URL env.ANTHROPIC_AUTH_TOKEN The failure mode: it reads that file exactly once, at startup. Change it while a session is running and nothing happens. No warning, no reload. This is the single most common "the switch is on but nothing works" report, across every tool. Close all windows, open a fresh one. One thing I appreciate: it only touches those two keys, backs up the original, and restores it exactly when you flip the switch off. Codex: doesn't read the model from your request This one is architecturally weird and cost me an hour. Every other tool specifies which model it wants in the request. Codex doesn't. It picks from its own internal model catalog. Consequence: if you don't explicitly select a model, it sits on a default internal GPT model that the market can't serve. And you don't get "please select a model" — you get a string of failures with no stated cause. The config it writes: ~/.codex/config.toml → model_provider, [model_providers.asale], model, model_catalog_json ~/.codex/auth.json → OPENAI_API_KEY Note model_catalog_json . That's the part that makes your selection show up in the app's model menu. And the desktop app reads that catalog at startup , so a model written while it's running won't appear until you restart. Two separate restart requirements stacked on each other. Credit where due: it preserves your existing comments and formatting in config.toml . Not every tool does. Gemini CLI: loses to your own shell config Config goes into ~/.gemini/.env . Two keys added, nothing else touched. The failure mode

I started building xAgent in April 2025. The original idea was straightforward: build a task-oriented Agent that could run work on its own and turn AI into real automation. Looking back, that sentence sounds simple. Most of what I have done over the past year has been filling in everything hidden inside the words “run work on its own.” The first version used a single Agent. I quickly ran into a problem: once the prompt focused its attention on one kind of work, the Agent could do that work well but handle other tasks terribly. Fix one side and it would forget the other. Ask it to pay attention to everything and it would end up paying proper attention to nothing. That led me to multiple Agents, each responsible for a different part of the work and able to collaborate with the others. The idea worked, but as soon as they started running together, the next problem became obvious: tokens were too expensive. I bought a modified RTX 4090 with 48 GB of VRAM and started running open models locally. That took some pressure off the token bill, but exposed another problem: small open models were not smart enough. This was still the Qwen 3.0 era. The gap between local models and the best hosted models was obvious, especially on long tasks. They skipped steps, wandered away from the goal, and ignored instructions in all sorts of ways. I did not solve this by buying more tokens from top-tier models. It was not because those models were bad. The most practical reason was that I simply did not have the money. Once multiple Agents run continuously, the allowance included with a subscription disappears quickly. Spending more could solve the problem, but I could not afford to keep doing that, and it did not look sustainable for most individuals or small teams either. Not having the money forced me to think seriously about a question that has shaped xAgent ever since: can a small team with a limited budget use Agents properly without constantly paying for the best models, keeping costs

I spent a while getting permission levels right. What an agent may read, what it may write, what needs a human. That work was worth doing, and it did not save me here. The gap is simple to state and easy to miss: permission levels answer what may this agent do . They say nothing about what happens when the task itself changes after the agent already has permission . The situation When work is handed to an agent, the handoff carries a task definition, a scope, and the conditions that count as done. The agent takes it and starts. Then I edited the task. Not maliciously, not carelessly. I noticed something while the agent was still setting up, and I added a comment that changed what "done" meant. At that moment I had an agent holding valid authority for a task that no longer existed in that form. It had permission. Its permission was correct. Its instructions were stale. Static permission levels do not catch this. The agent is doing exactly what it was allowed to do. The problem is that "what it was allowed to do" was defined against a version of reality that I had just replaced. Why "just ask the human" is the wrong fallback The obvious fix is to have the agent check in when something looks off. I do not think this works, for two reasons. First, the agent cannot see the ambiguity. From inside the handoff, the stale task reads as perfectly coherent. There is no contradiction to notice. The instructions are complete, the scope is clear, and the acceptance conditions are stated. It just happens that a newer version exists elsewhere. Second, if the agent asks me every time it feels uncertain, I have rebuilt the bottleneck I delegated to avoid. Interruptions that fire on vague signals train you to approve them without reading, which is worse than not having them. The check has to be mechanical, and it has to run at a specific moment rather than continuously. The stop condition What I added is small: Bind the task revision at dispatch. The handoff record states which versio

Struggling with burnout? Procrastination? Reaching your goals? Let me share a few methods that help...

Most designers don't lose time in the design phase; they lose it in the tool-switching phase. You...

How I Cut LLM Token Usage by Up to 60% in Production If you work with LLM APIs (OpenAI, Anthropic, Gemini), you know the pain: every call costs money, and a big chunk of that cost is pure waste — verbose prompts, code pasted with no filtering, repeated context the model doesn't even need to understand the task. That's why I built PromptShrink: a prompt pre-processor that trims the excess before it ever hits the API, without losing what actually matters for the model to understand. The real problem Every time you feed a code snippet or a long prompt to an LLM, you're paying per token, not per character. Comments, whitespace, formatting meant for humans — all of that is dead weight the model doesn't need to do its job. At scale (thousands of calls per month), that adds up to a real bill. What PromptShrink does Packages entire repositories, minifying code and stripping comments, ready to paste as context into any LLM Simulates real dollar savings, comparing your current spend against the optimized version Visualizes everything on a dashboard — tokens saved, % reduction, active rules Plugs straight into your code via a Python SDK Becomes a browser extension, adding a "Shrink" button directly on ChatGPT, Claude.ai, Google AI Studio, and Poe In practice bash Package an entire project into optimized context promptshrink repo --path ./src --save-to-file context.txt Simulate monthly savings promptshrink calc --calls 100000 --tokens 800 --model gpt-4o Running calc on a scenario of [insert your real number here, e.g. "100k calls/month with gpt-4o"], the estimated savings came out to [$X per month] — just by trimming what's unnecessary before it reaches the model. Try it out The project is open source, with a CLI, a FastAPI backend, and a Python SDK. If you're running LLMs in production and want to stop paying for tokens that add zero value, check it out: 🔗 github.com/HeloisaPeGarcia/PromptShrink Feedback and PRs are very welcome — this is my first published project like this,

I started writing tiny runbooks for AI agent tasks, and the quality of the work changed almost immediately. Not because the model got smarter. Because the work got less ambiguous. Most people still treat agent delegation like prompt craft. They keep trying to find the perfect sentence, the magic wording, the clever instruction that makes the model behave. I get the instinct. When the interface is a text box, it is natural to believe the answer is a better text box input. But that is not how real delegated work gets better. If a human teammate kept making inconsistent decisions, you would not solve it by giving them a prettier paragraph every morning. You would give them context. You would show them the expected path. You would name the edge cases. You would define when to stop and ask. You would make the work inspectable. That is a runbook. And for agent workflows, runbooks are starting to matter more than prompts. Prompts Are Not Enough A prompt describes what you want right now. A runbook describes how the work should be done every time. That distinction matters because the biggest agent failures I see are not caused by a lack of raw intelligence. They are caused by missing operating context. The agent changes the right file but verifies the wrong behavior. It fixes the visible bug but misses the product constraint. It keeps digging after the task is already complete. It treats a flaky test as a code problem. It stops at a plan when the task clearly needed implementation. It implements the request but forgets to leave a useful handoff. These are not prompt wording problems. They are workflow design problems. The model needs to know more than the goal. It needs to know the local rules of the system it is operating inside. Which commands prove success. Which files are dangerous. Which tests are worth running. Which changes should stay out of scope. Which blocker is real enough to stop work. That information does not belong in a one-off prompt. It belongs in a reusab

Chat is great for intent, but agent work gets lost in the scroll. Here is how I use canvases with my agentic workflows—and why your workflow also deserves a canvas. The post How canvases make agentic workflows visible, steerable, and cost-efficient appeared first on The GitHub Blog .

The Day I Realized I Wasn't Building Apps For years, I thought I was building apps. That's what I called them anyway. A scheduler. A job bot. A healthcare platform. An AI project. A content tool. A browser automation system. Looking at my GitHub, they seem completely unrelated. Honestly, that's something I've worried about before. I have over a hundred repositories. If someone spends thirty seconds scrolling through them, I can imagine them thinking: "Wow. This person is all over the place." The funny thing is that I eventually realized the opposite was true. My GitHub is here: https://github.com/ashb4 The Scheduler That Wasn't A Scheduler One of my projects started life as a simple scheduler. That was the goal. I hated posting content manually. Open platform. Paste content. Upload image. Repeat. Again. And again. And again. It felt repetitive. It felt annoying. Most of all, it felt like something a computer should be doing instead of me. So I built a scheduler. At least, that's what I thought I was building. Then Things Got Weird The scheduler worked. But now I needed content. Then I needed analytics. Then I needed to know what content was working. Then I needed a way to track winners. Then I needed a way to reuse content. Then I needed platform-specific strategies. At some point I looked up and realized I wasn't building a scheduler anymore. I was building a system. A system for discovering, creating, publishing, measuring, and improving content. The scheduler was just one piece. Then I Started Looking At Everything Else That's when I noticed the same thing happening in almost every project I'd ever built. My job application tools weren't really job application tools. They were systems designed to reduce repetitive effort. My automation projects weren't really automation projects. They were systems designed to reduce repetitive effort. Even my AI projects weren't really about AI. They were systems designed to reduce repetitive effort. Different technologies. Diffe

As a developer who works remotely from an RV, I often find myself juggling multiple projects and tasks at once. One of the biggest challenges I face is keeping track of the numerous tabs I have open on my browser. I recall a particularly frustrating incident where I accidentally closed a tab with crucial information, only to spend hours trying to find it again. This experience led me to create Tab Reminder, a simple yet powerful Chrome extension that allows users to schedule tabs to reopen later. From a technical standpoint, one of the key insights I gained while building Tab Reminder was the importance of leveraging the Chrome extension API to access and manage browser tabs. By using the chrome.tabs API, I was able to create a seamless experience for users to schedule tabs to reopen at a later time. For instance, the chrome.tabs.query method allows me to retrieve a list of all open tabs, which I can then use to populate the scheduling interface. One lesson I learned from building and using Tab Reminder is the value of creating tools that simplify our workflows. By automating the process of reopening tabs, I've been able to free up mental energy and focus on more complex tasks. If you're like me and often find yourself drowning in a sea of open tabs, I recommend checking out Tab Reminder (available at https://go.sg1-labs.us/tab-reminder ) to see how it can help streamline your browsing experience. With Tab Reminder, you can schedule any tab to reopen at a later time, ensuring that you never lose important information again.

You heard me. Alright, that was mean lol. Though based on the title, you probably already knew the...