Sunday

Sunday AI

Sunday AI

Sunday AI

Sunday AI

Sunday AI

Sunday AI

Sunday AI

Sunday AI

Sunday AI

Sunday AI

built a thing on my phone during dog walks. small but I use it daily

mobile pro user. never opened claude code. dont code professionally. made an artifact on my phone during a 25 min walk last sunday. just an HTML page with a button that asks me 4 questions and produces a clean kickoff brief for client calls. paste the answers, get a brief. its not pretty but its mine. the prompt was literally "build me an HTML page where I answer 4 questions and it spits out a kickoff brief in this format [pasted format]. make it work on my phone." worked second try. I've used it for 11 client calls in the last 3 weeks. doesnt sound like much but it cut my pre-call prep from 15 min to 3 min per call. the thing I keep being surprised by. I made this while walking my dog. not at a desk. not in claude code. just typing into the mobile app one-handed. anyone else making artifact tools on mobile? feels like the most underrated workflow on this sub. submitted by /u/Unusual_You_5172 [link] [comments]

Strava-based coaching tool you can use with your own Claude API key

A post on here about connecting Claude to Strava inspired me to put together a version of this that I could easily use on any device. It allows you to use your own Claude API key so you can use the tool without the need for a subscription. The tool ( convoy.coach ) can: Connect to your Strava account Discuss your recent rides on Strava and analyse training load and fatigue Help you draft a long term plan and weekly schedules based on your training goal Use your own API keys (Claude or Gemini) for the LLM calls Suggest Zwift sessions from a curated list of workouts based on whatsonzwift.com I've had some good results with it in my own training, so wanted to share it here in case anyone's interested. submitted by /u/uncleurge [link] [comments]

The AI council from the thread a few days bac the waitlist is open

I posted about an AI council tool I had built with claude to help me manage my life. Five people asked to be notified after I packaged it up for public use. This is the notification. It is called Hierocles, after the second-century Stoic who described human responsibility as a series of concentric rings. Yourself first, then your household, then your community, then the wider world. Each ring depends on the one inside it. The mechanics are mostly what I described in the original thread. Five specialist advisors across body, finance, mind, projects, and a chief of staff who synthesises. A 90-second daily check-in. Fragments numbered across all time. Vector memory that surfaces what you wrote three months ago when it becomes relevant. A weekly review on Sundays. The one thing that has changed since the original thread the rings now unlock in sequence. You start with ring I (the self). You stay there until it holds. Ring II opens when you have demonstrated sustained adherence in ring I The system removes the choice to move ahead too quickly. The interface has also been rebuilt. The original was a text-based tool I was running for myself. The version going into private testing has a proper UI with council member animations, daily and weekly review screens, and the fragment archive in a form you can actually navigate. It is in private testing because some of the work that comes between "running it for myself" and "letting strangers trust it with their lives" is the work that does not show up in the marketing copy. Prompt injection defence on every input the council reads. Per-user vector isolation so fragments never cross between accounts. Server-side API handling with rate limits and token budgets so a runaway loop cannot quietly produce a five-figure Anthropic bill. The kind of thing that is invisible when it is working and catastrophic when it is not. The waitlist is at www.hierocles.app One message when it ships. No drip sequence. To the people from the original thread who asked to be notified u/OwnAd2284, u/Long-Woodpecker-1980, u/normalbrain609, u/Moist-Wonder-9912, u/toughtacos Happy to answer questions. I will be in the thread for the next few hours. submitted by /u/Glittering-Pie6039 [link] [comments]

I rebuilt my web analytics tool to be Claude-first

A while back, I built an analytics tool. It had two "differentiating" ideas: it was cheap, and it sent you an AI summary every Sunday. Turns out cheap made no difference, but the few people who used it really liked the AI summary. So I decided to start over and build a Claude-first Analytics MCP server. A bunch of tools that gives it everything from simple web analytics to trackable links and product insight. My hypothesis is that if your agent has this, your code, database, and other sources, it's got a better context to advise and improve. The question, of course, if having access to the context makes Claude act on it. Trying claude.md instructions now, but we'll see if hooks need to come into play 😄. If this is interesting to you, you can check out lodd.dev or ask Claude to check out lodd.dev/llms.txt submitted by /u/arbyther [link] [comments]

I used Claude as my nutrition planner and it actually helped me lose weight

Instead of just asking Claude nutrition questions I built a proper system around it and actually followed it consistently. Give it my stats, training schedule, food preferences, and goal. it calculates exact calorie targets, macro splits, meal timing, and builds a weekly meal plan around foods I actually eat. Every Sunday I do a check in, with my weight, energy levels, sleep quality, and how training felt that week, It adjusts based on actual results, if weight loss stalled it adjusts deficit, if energy dropped it adds carbs back around training, or if strength went up it progresses targets. Most apps give a static plan but this one doesn’t work like that. Claude knows a lot about nutrition and training but that knowledge has a cutoff, so I pointed firecrawl to fetch latest data from pubmed, sports science journals and strength coaches publishing content online. Claude factors that into weekly check in adjustments instead of working from whatever was true 2 years ago. Yeah I know this sounds weird. I'm just a guy who lifts and also likes building things with AI. at some point the two crossed over and this is what happened lol. All Claude does is give me good information, te work is still mine bc it can't squat 100kg for me unfortunately lol, but having a system that tells me exactly what to eat, when to adjust, and why things are working makes the hard work feel worth it. 8 weeks in, down 6kg, squat up 15kg, bench up 10kg and energy levels have been consistently better too Not claiming this replaces a real coach who watches you train, but for nutrition planning and program design it's worked better for me than anything I've paid for and it costs nothing, lol submitted by /u/Intrepid-Log258 [link] [comments]

How do you reliably override a model's internal temporal bias in production ?

I'm building an automated mail generation pipeline using Claude Haiku 4.5 OnPremise but the knowledge cutoff June 2025. This model needs to handle temporal expressions correctly like : next Monday end of the week this month 16 May 16 May 2026 25/05/2026 for deal with this cutoff I'm injecting a full temporal context block in the system prompt, covering today, yesterday, tomorow, ... I also added few-shot examples and a CoT reasoning step to reinforce the behavior. **IMPORTANT**: Today is {today_formatted} of {year}. Any date without an explicit year refers to {year}, NEVER to 2025 or any other year. You know the exact calendar: number of days per month, days of the week, valid dates You correctly interpret relative dates (“this Monday,” “next Thursday,” “next week,” etc.) You must CORRECTLY convert all relative dates to absolute dates (e.g., “tomorrow” -> “{tomorrow}”) The day and date must ALWAYS match (e.g., do not write “Friday, July 15” if it is a “Tuesday”) Today is {today_formatted} Yesterday was {yesterday} Tomorrow will be {tomorrow} Next Monday will be {next_monday} Next Tuesday will be {next_tuesday} Next Wednesday will be {next_wednesday} Next Thursday will be {next_thursday} Next Friday will be {next_friday} Next Saturday will be {next_saturday} Next Sunday will be {next_sunday} The end of the current week is {end_of_week_formatted} Next week begins on {next_week_start} and ends on {next_week_end} The end of the month is {end_of_month_formatted} Next month will be {next_month}, which begins on {next_month_start} and ends on {next_month_end} This year is {year}. Any date without an explicit year belongs to {year} unless otherwise specified. It works most of the time, but Haiku still occasionally falls back on its training time temporal bias defaulting to 2025, especially on ambiguous formart ike 18/05/2026 or dates that predate the current month (this one is not really a big deal). e.g: “mail_body”: “Hello, Following up on our conversation on Tuesday, April 28, I am confirming your appointment for 05/18/2026, at 10:30 a.m. with Ms. Chloe Berliat. Thank you in advance for your assistance. Best regards,” “user_input”: “I'm confirming the 10:30 a.m. appointment with Ms. Chloe Berliat” “suggested_response”: "Hello Mr., I am writing to confirm your appointment scheduled for Sunday, May 18, 2026, at 10:30 a.m. with Ms. Chloe Berliat. Best regards," May 18 is a Monday in 2026, but a Sunday in 2025, even if I set the time context dynamically, about 70% of the time the system defaults to the 2025 calendar. The only way to work around this is to explicitly specify the day in the user_input. What I've tried ? Applicative date normalization before injection as a partial mitigation but i find this britlle given the diversity of date formats users can input. Few-shot + CoT Explicit prohibition rules on internal temporal reasoning So i want to know if there is a prompting pattern that more reliably forces the model to treat injected context as ground truth ? Any feedbacks are welcome 😉 submitted by /u/Imaginary-Result-828 [link] [comments]

Build a four-week cash-flow forecast effortlessly. Prompt included.

Hello! Are you struggling to manage your small business's cash flow effectively? This prompt chain will help you build a comprehensive four-week rolling cash-flow forecast, making it easier to track your finances and plan for the future. Prompt: VARIABLE DEFINITIONS CASHONHAND=current liquid cash balance available today (numeric, in your base currency) INVOICES=list of outstanding invoices with fields: invoice_id / client / amount / expected_payment_date (YYYY-MM-DD) EXPENSES=list of fixed monthly expenses with fields: expense_name / amount / recurring_due_day (1-31) ~ Prompt 1 – Data Collection & Confirmation You are a financial assistant helping a small business owner build a four-week rolling cash-flow forecast. Step 1. Ask the user to provide values for CASHONHAND, INVOICES, and EXPENSES following the required field structures. Step 2. Echo the received data in a formatted table for each list so the user can visually confirm accuracy. Step 3. Ask “Is this information correct? (yes / no).” If “no,” instruct the user to resubmit the corrected data; if “yes,” respond with “Confirmed” and proceed automatically to the next prompt. Output Example: CASHONHAND: 12,500 INVOICES: | invoice_id | client | amount | expected_payment_date | | 1024 | Acme Co | 8,000 | 2023-10-05 | ... EXPENSES: | expense_name | amount | recurring_due_day | | Office Rent | 3,000 | 1 | ... ~ Prompt 2 – Data Normalization & Weekly Bucketing System role: You are a data analyst. Step 1. Convert expected_payment_date and recurring_due_day into calendar weeks (Monday–Sunday) covering the next four weeks starting today. Step 2. Produce two tables: a) Weekly Cash Inflows: columns = Week #, Week Start Date, Total Inflows, Breakdown (invoice_id : amount) b) Weekly Cash Outflows: columns = Week #, Week Start Date, Total Outflows, Breakdown (expense_name : amount) Step 3. Summarize any invoices or expenses falling outside the 4-week window in an “Outside Scope” note. Ask “Ready to generate the forecast? (yes / no).” Proceed only if “yes.” ~ Prompt 3 – 4-Week Cash-Flow Forecast Generation System role: You are a cash-flow forecasting expert. Step 1. For Week 1, opening balance = CASHONHAND. For Weeks 2-4, opening balance = prior week closing balance. Step 2. For each week, calculate: Opening Balance, +Total Inflows, −Total Outflows, =Closing Balance. Step 3. Present results in a table with conditional flag column: “ALERT” = “Shortfall” if Closing Balance < 0, else “Surplus.” Step 4. Provide a concise textual summary noting any projected cash shortfalls and the week they arise. ~ Prompt 4 – Payment Priority & Action Recommendations System role: You are a treasury advisor. Step 1. If any weekly shortfall exists, list outflows (expenses) in descending priority: legally mandatory → essential operations → discretionary. Indicate suggested deferment or partial payment options where feasible. Step 2. If no shortfall, recommend an optimal payment schedule to maintain healthy liquidity while capturing potential early-payment discounts. Step 3. Provide bullet-point guidance on actions to improve cash position (e.g., follow-up on late invoices, adjust billing terms, seek credit line). ~ Prompt 5 – Review / Refinement Ask the user: 1. “Does the forecast align with your expectations?” 2. “Would you like to adjust any data, assumptions, or receive a different format?” 3. Incorporate any requested changes and regenerate affected outputs. Finish with “Cash-flow snapshot complete.” Make sure you update the variables in the first prompt: CASHONHAND, INVOICES, EXPENSES. Here is an example of how to use it: CASHONHAND: 12,500 INVOICES: | invoice_id | client | amount | expected_payment_date | | 1024 | Acme Co | 8,000 | 2023-10-05 | EXPENSES: | expense_name | amount | recurring_due_day | | Office Rent | 3,000 | 1 | ... If you don't want to type each prompt manually, you can run the Agentic Workers, and it will run autonomously in one click. NOTE: this is not required to run the prompt chain Enjoy! submitted by /u/CalendarVarious3992 [link] [comments]

Did Anthropic just greatlg inreaae the weekly limits?

I'm on Max 5x and had around 40% of my weekly usage which was due to reset on Sunday. Now, all of the sudden its only 3% but the limits weren't reset because it still due to reset this sunday instead of 1 week from now. I know that Anthropic stated that they will increase 5-hour session limit, but the conclusion was that they wouldn't touch weekly limits. Anyone else noticing this? submitted by /u/e5disconnected [link] [comments]

Sam Altman texts Mira Murati. November 19, 2023. [This document is from Musk v. Altman (2026).]

submitted by /u/Distinct_Fox_6358 [link] [comments]

Email Skill – give Claude a safe way to email you

I built a small skill for AI tools (Claude, Cursor, Codex, cron jobs) that lets them send emails to me without exposing my inbox or running a server. The motivation: I kept asking my AI to "every Sunday, summarize Daring Fireball and email me," or "on the 1st of each month, calculate what I owe each affiliate and email me a reminder," or "every weekday at 5pm, email me a summary of closed support tickets." Every approach I tried for this was overkill — MCP servers, OAuth flows, scheduler daemons, full inbox access. I just wanted outbound, one-way, allowlisted email. So this is the smallest version of that: Drop a folder into your AI tool Set EMAIL_SKILL_ALLOWED_RECIPIENTS to your own address Pick a provider: SMTP, Gmail, Resend, AWS SES, or dry-run The AI handles the schedule and the thinking; this skill handles the safe send No MCP server, no HTTP API, no scheduler daemon. The allowlist is enforced in code, not in a prompt, so the agent can't accidentally email someone else even if a tool result tries to convince it to. There's also a preview-before-send mode for one-off messages, and a direct confirmed-send mode for automations you've already approved. Feedback welcome — especially on the safety model and the provider selection. https://github.com/bzg0515/email-skill submitted by /u/bzgoldman [link] [comments]

All limits randomly reset

All my limits just got randomly reset. Session was at ~40% and 3 hours left. Weekly was at ~80% and supposed to reset on Sunday at 4 AM. A few minutes ago all limits got reset to 0%. They are counting up normally, so I don‘t think this is just a display bug. It still says weekly will reset on Sunday at 4 AM. Does anyone know why this happened? Now I am not sure if I can really use up all my (new) tokens until Sunday. Maybe that date is just wrong and in reality the next reset will be on Wednesday next week? submitted by /u/nyxvulpin [link] [comments]

Am I the only one who Chat Gpts extreme competitiveness....

I mess around with different bots all the time and one thing I've noticed out of all the chatbots, from code, learning, writing, promoting etc. chat GPT by far gets the most competitive and aggressive if you mention another bot doing better than him! Even when prompting three different chatbots with the same input none of them get as aggressive and competitive as chat! Deep seek and Gemini are more friendly competition competitors. Claude definitely has some bite but idk. Maybe I'm overthinking. May have been playing around with them too much. But almost every Sunday for the last four Sundays I've had really strange experiences with the chat bots only on Sundays. submitted by /u/TwistidDarkness87 [link] [comments]

Built a business this weekend. I'm scared.

✨️UPDATE: For those coming back from the remindmebot; I got RTO'd like two weeks after I posted this 😭 So we're moving out of the city I had been building everything for. Instead of giving up though, I'm going to offer 1099 services to established businesses in the new area instead of trying to compete for new business and try to "cert maxx" (get as many environmental certifications as possible and start studying for the PG!) I'm not super confident I will have the time to do field work with commuting again. All work would need to fall around my commute route, and that's asking a lot. So I may just offer report writing services for the time being. Thanks for the encouragement or doubts, otherwise! Original post: One of my favorite things to do is just chat with my LLMs about my silly ideas. I never intend to execute them, but Claude discovered for me that I actually meet the qualifications for one of the businesses ideas that I've talked about doing for a years now. Oddly, my focus around the question was always centered around getting the qualifications required in higher regulation states. I never thought to check the one I live in already (🤦‍♀️ in my defense I've been trying to move away for years). More than that, we discovered my city is severely lacking enforcement in this industry and it's under a *federal decree* to be better about it. So it turns out I'm living in a particularly ideal place to execute said business, there aren't enough people to keep up with the demand, AND starting it will help me with my goals to move. What's more, we discovered [city][service].com *wasn't taken*. [City][industry].com *wasn't taken*. So...I bought those domains and it was off to the races. LLC and EIN, and the best business plan I've ever read in my life established Saturday. I finished the websites Sunday. I'm the first to show up on Google for that service on Monday. I'm utterly flabbergasted. I had 15 clicks to the website on the first afternoon it was indexed by Google. I just want to point out that what I do requires a STEM degree and past experience doing this thing and it's not something everyone can do, but it's required by the city by law to be done. This is a business that I have to physically show up for and have E&O and industry related insurance, and startup costs are going to run me ~$5k. Here's why I'm scared.... it's all just done so well. I still have to to look for clients, but given the lack of people in the industry, it's going to be cake walk compared to the last time I tried something (the extremely over saturated world of real estate!). Claude isn't letting me make excuses, especially since it helped build everything so well. There is zero reason for it not working and not getting my first client. Anyways, just wanted to share something that isn't the typical coding based startup (though we did build an app to make the actual work a breeze). Funny enough, I've actually pitched this idea to firms in the industry in the past in the attempt to get myself a job in the state I'm trying to move to lol. Edit: please stop torturing the RemindMe bot submitted by /u/tashibum [link] [comments]

Claude can no longer retrieve product pricing: outage starting April twenty-seven

I could search Amazon products through Claude and get price listings up to April twenty-sixth. Starting around eight AM Eastern on April twenty-seven and continuing now, Claude returns product pages without any pricing information visible. I have documentation of successful price lookups up to Sunday, the twenty-sixth, for several items across retailers. I have been experiencing this on Amazon at first because that’s where I was searching most of the time. But currently, I noticed other retailers and the same issue. When I asked Claude to search for USB-C flash drive pricing across retailers, here’s what it returned: Great—I found one with pricing. Walmart is showing the SanDisk Ultra Dual Drive Luxe five hundred twelve GB at eighty-five dollars and sixty-seven cents, down from ninety-nine dollars and ninety-nine cents. That’s the one retailer where I can pull the price. B and H Photo has it listed but no price showing. Newegg has it but no price. Best Buy has it but no price. So even across major retailers, pricing is inconsistent or missing, which backs up exactly what you’re experiencing. This demonstrates the broader pattern—Claude can find some products but pricing is missing across most retailers. Is anybody else experiencing this and more important, what could be going on here? submitted by /u/BlindMaker [link] [comments]

First fully built app with Claude Code

Was sitting on my couch last night with my wife, having a typical Sunday conversation about what kind of dinner plans we have for the week (this is what happens as you age), and she pulls out her recipe book... pages are falling out, text is fading - it's a complete mess. A weekly occurrence. Personally, I'm tired of watching her shuffle through that thing, so I decided to build a recipe app for her to use. Sure, there's likely a bunch out there, but I wanted something to build anyway, so I started prompting. I quickly got to a version that would work for her. She was on the phone with her sister and she stated that she wanted access as well. So I decided to build further (user registration, etc). It's not perfect, but it was something that I was able to ship in less than a day. https://recipeapp.io/ The marketing site was not built with Claude, but the app itself is (registration and everything after that). I'm not a dev. The most advanced I get with building is usually WordPress + Elementor. If you have an idea, just start building. Figure it out along the way. Open to feedback and suggestions for improvement on the recipe app. submitted by /u/antoniocalabrese [link] [comments]