anamjalal

anamjalal has not published an app.

• Askly, 8 Nov 2026: Tested on Web (Chrome, desktop). Signed up with Google from the Log in popup (Google, Apple, email or phone are all offered, which is good). I landed in the chat workspace with "5 FREE questions left" in the top corner, which is clear and honest. *What I asked* A real task from my work: "Write a 3-line WhatsApp reply to a dental clinic patient in Dubai who asked if we have an appointment tomorrow evening. Give it in English and Arabic." The answer came back in a few seconds and was genuinely usable: a short, friendly English reply, a natural Arabic version, and a note that 6:30 PM was a placeholder because it doesn't know my schedule. That last line is a nice touch. Then I asked "Make the English one more formal". It kept the context, rewrote only the English, and labelled the Arabic as "(unchanged)". Exactly right. The free counter went from 5 to 4 to 3 as expected. *Things to fix* Which AI answered? The header says "ASK PREMIUM AI" and the footer lists Claude, Gemini, ChatGPT and DeepSeek, but nothing tells me which model replied. Since you sell access to several models, show the model name on each answer, or let me pick. Top-up modal: the subtitle says "Choose a preset or enter a custom local-currency amount", but all presets and the custom box are in USD. I'm in the UAE and saw $, not AED. The $1.99 card lists "Writing, planning and study support" twice. It's a copy-paste duplicate. None of the tiers ($0.99 / $1.99 / $4.97 / $9.97) says roughly how many questions or messages I get. "Quick answers" and "More room for Smart responses" don't help me choose. Something like "about 40 questions" would. The URL is askly.site/asia/chat even though I'm in the Middle East. Minor, but it made me wonder whether I was on the right regional version and the right prices. *What I liked* No subscription, pay as you go, and "Balance never expires" is a strong, simple pitch. The shortcut chips (Prepare for a Test, Understand an Error Message, Social Media Caption) make it obvious what to try first. Chat history shows on the left right away, with rename and delete. *Bottom line:* the answers are good and the pay-as-you-go model is clear. Show which AI answered, make the top-up tiers concrete (how many questions) and in my currency, and I'd happily top up $1.99 to keep using it.
• RAI Calendar, 8 Nov 2026: Tested on Web (Chrome, desktop, macOS). Signed up with Google. Before the dashboard I got a full-page "Review legal documents" screen with two checkboxes (Terms v2.0.0, Privacy v2.0.0), even though the signup page already had its own terms checkbox. That's two consent steps back to back for a new user. Merge them into one. *Onboarding tour* The dashboard opens with "Welcome to RAI Calendar, step 1 of 5", which is nice. Step 2 offers Connect Google Calendar or continue without it, which is good; I skipped it. Then the tour just disappeared after step 2. At the same moment the console logged two "Minified React error #185" exceptions (maximum update depth exceeded, so something is re-rendering in a loop). I think that's what killed the tour. Worth checking, because the same loop could explain the next issue. *Search / command bar* The placeholder is "Search, /rai for commands, @rai for AI", but the field is small and on first read I took it as "@ for AI". Typing "@ demo call..." just shows "No results" with no hint. Show the @rai and /rai hint as a chip or in the empty dropdown. Once I used @rai, the input dropped keystrokes as I typed. I typed "@rai demo call with Dr Omar tomorrow at 3pm for 30 minutes" and the field actually contained "Dr Oma ... 30 miutes". I typed the same way in other apps today without losing characters, so it looks like the input lags while the suggestion list re-renders on every key. *Rai AI result* Pressing Enter on "Ask Rai AI" created the event right away on the correct day (tomorrow) at 15:00. Fast, and it got the date right. But: The title became "demo call with Dr Oma for 30 miutes", so it put the duration into the title. The event is 15:00 to 16:00 (1 hour), not 30 minutes. Even with a typo like "miutes", "for 30 ..." should become the duration and come out of the title. It was created with no confirmation or undo toast. A one-line "Created: Demo call, Tue 15:00 to 15:30, Undo" would build trust in the AI. *Calendar* Clicking an event in Month view switched the whole calendar to Day view instead of opening the event's details. I expected a details popover. The dark UI is clean, and the left mini-calendar, Invited and People sections are easy to scan. *Didn't test* Google Calendar sync, voice Record, the CRM side and the Community page. *Bottom line:* creating an event in plain English, on the right day, in about 3 seconds is the core promise, and it nearly works. Fix the re-render loop (it probably causes the dropped keys and the vanishing tour), parse the duration properly, and confirm what the AI created.
• iLinked, 8 Nov 2026: Tested on Web (Chrome, desktop). Signed up with Google in one click and landed straight on the Shorten URL screen with "Synced to (my email)" and "Today: 0/20 links". Very fast start. *URL to statement (keyword link)* I made ilinked.online/TestMyBuildBounties pointing to testmybuild.app/apps?sort=bounty. The availability check ("Available! This keyword is unique") and the "Verified Safe Target" scan both appeared live as I typed. Shorten was instant and gave me the link plus a QR in one card, with Copy, Test Link, Share and Download. Very nice. I also typed the keyword in all lowercase (ilinked.online/testmybuildbounties) and it still worked. That matters for links people type from memory. *The big issue: the 15-second interstitial* Opening the keyword link doesn't take you to the site. It shows a "Verified Resource" card with "Auto-redirecting in 15 seconds", a Pause Timer button and a "Proceed to Destination" button. Your whole pitch is "just remember the keyword", but visitors then wait 15 seconds or have to click again. For a link on a sign or in a talk, most people will bounce. Make it a direct redirect by default, or 2 to 3 seconds at most, and keep the safety page only for links your scanner flags. *Layout shift while filling the form* After I pasted the destination URL, the "Verified Safe Target" banner appeared and pushed the Custom Keyword box down. My click meant for the keyword field landed on the label, and the first keyword I typed went nowhere. Reserve that space, or show the badge inline in the URL field. *QR Studio* The 12 types (Wi-Fi, WhatsApp, vCard, payment, calendar, maps and more) are genuinely useful, and the preview updates live. Two notes: The WhatsApp field says "digits only", but it accepted "+1 555-123-4567" with no warning. Either strip the symbols automatically and say so, or validate. "We do not save it in cloud, so make sure to download" is easy to miss. Most people will expect it in their dashboard like the short links. Save QR codes too, or make that warning much louder. *Tutorials, Use Cases* The library is big (26+ use cases), but the examples read like invented case studies, for example a real estate broker getting "3x more virtual tour views". Unless these are real customers, label them "Example idea" rather than presenting them as results. It hurts trust in a product that's selling safety. The yard-sign example is also exactly where the 15-second wait would hurt most. *Didn't test* The ilkd.in short domain and custom domains (paid). *Bottom line:* creating links is fast and the keyword idea is genuinely handy. Remove or shorten the interstitial and fix the layout jump, and this is something I'd use on printed material.
• Neesh AI, 8 Nov 2026: Tested on Web (Chrome, desktop, macOS). Signed up with Google, which was smooth, and landed on the dashboard ("No projects found"). *The blocker: you can't create a project right now* I clicked Create Your First Project and filled in a real idea: ClinicVoice, an AI voice receptionist for UAE dental and medical clinics in Arabic and English, HealthTech, stage Idea. Then I clicked Start Copilot. Nothing happened: no spinner, no error, the modal just stayed open. I tried 3 times over about 10 minutes, including after a full reload. I opened the browser console to see why. Every call to your backend fails with "TypeError: Failed to fetch" ([useProjects] Error creating project, [useProfile] Failed to fetch profile, [SubscriptionContext] Error fetching subscription). _Root cause, I'm fairly sure:_ your page's Content-Security-Policy header has connect-src 'self' https://*.supabase.co wss://*.supabase.co https://api.cashfree.com https://sandbox.cashfree.com https://generativelanguage.googleapis.com https://api.openai.com. It does NOT include https://neesh-2-o-backend.onrender.com, which is the API base URL in your JS bundle. So the browser blocks every request to your own backend before it's sent. The backend itself is up: hitting it directly returns {"status":"OK","service":"Neesh AI Service"}, though it took about 22 seconds to answer, which looks like a Render free-tier cold start. Reads still work because useProjects falls back to querying Supabase directly. But creating a project only goes through the backend, so it silently fails for every new user. The fix should be adding https://neesh-2-o-backend.onrender.com to connect-src (in vercel.json headers, or wherever you set the CSP). *Other things worth fixing* Show an error when Start Copilot fails. Right now a new user just thinks the button is broken and leaves. The Render cold start (about 20 seconds) will also hurt first impressions once the CSP is fixed. Keep the service warm or show a "waking up" state. *What I liked before it broke* The landing page is clear: "Turn raw ideas into interactive validation loops" plus "Start Validating for Free". Signup with Google or GitHub is quick, and the Create Workspace modal is short (name, one-line summary, industry, stage), with no long questionnaire up front. *Your questions* I couldn't get a validation score or a Spotlight link because project creation fails, so I can't yet say whether it answers "should I build this or not?". Happy to re-test once the CSP is fixed. I'd genuinely like to see what it says about this idea.
• BriefIntake, 8 Nov 2026: Tested on Web (Chrome, desktop) as a business owner. I run an agency that sets up AI receptionists for clinics and real estate in the UAE, so this is a real use case for me. Signed up with Google in seconds. *Setup* I set the company to MAJ, wrote one line on what I offer, and added two bar lines: "Budget of at least AED 15,000 for setup" and "Wants to go live within 2 months". Then I generated an invite and opened it in another tab as a fake client: Sara, who owns a 2-branch dental clinic, has a budget of about AED 12,000 (just under my bar), a 6 to 8 week timeline, and a partner who has to sign off. I used Chat with me. *Your question: would I take the call?* Yes. The brief scored 79, capped by my bar ("budget partly met"), and buying intent was 92. What decided it: the quantified loss ("15 to 20 new patients a month"), the clear success target (zero missed calls, 10 more bookings a month) and the partner needing a demo. That tells me exactly what to bring to the call. The recommendation line at the top is the most useful thing on the page. *What worked* Anika used my offer line straight away ("your clinic or real estate business"). The questions were good, especially "what changed recently" and "what happens if this doesn't get solved". The bar logic did what you promised: partly met, capped at 79, and no way to talk it up. *Where it went wrong or I felt unsure* _Currency:_ Anika asked for my budget "in USD", even though my bar is in AED and the client is in Dubai. Use the currency from the bar, or ask. _Leading question:_ "It's a one-off setup, right?" She assumed the pricing model, and the client had to correct her. _The ending loops:_ after I said "we can wrap up", she asked for my email, then "anything else or wrap up?" again, then asked for the company name, which I'd already given as my second answer. That last question made the client feel unheard. After my email she also said "(I'll correct that for you)" when nothing needed correcting. _Silent wait:_ after the last answer it showed "Noting that down" with a spinner for about 40 seconds before the thank-you page. Say "Writing your brief, about 30 seconds" so people don't close the tab. _Guessed score:_ the brief scored "Prior spend 18/18", but prior spend never came up in the chat. If it wasn't discussed, show "not asked". _Quote under the bar:_ the recommendation says to send a quote around AED 12,000, which is below my own AED 15,000 bar. It should flag the gap ("they're AED 3,000 under your bar") instead of quietly quoting under it. _Dashboard "Why" column:_ for this lead it just says "timeline complete", which isn't a reason. Put the one-line recommendation there. *Setup page UX* "What you offer" is the first thing you tell testers to fill in, but it's at the very bottom of the Intake page under Identity, below invites, the bar, website, sources and delivery. Put Identity first. The invite link uses my personal name (/i/anam-jalal) even after I set the company to MAJ. A prospect sees that URL. The prospect page shows a black screen for about 5 seconds before anything loads. *Bottom line:* the brief is genuinely better than my own discovery-call notes. Fix the ending loop and the currency question, stop scoring things that weren't asked, and I'd send this to real leads.
• Ventari, 8 Nov 2026: Tested on Web (Chrome, desktop). Signed up with Google in one click and landed on a friendly "Hi, Anam" home screen. *Intro* Visually strong. "Save together for your next trip" and "From group chat to boarding pass" explain the app instantly. It's still 7 steps before signup, though; I'd cut it to 3 (save together, one pool for the crew, goal reached so book it). Currency: only EUR, USD and GBP. I'm in Dubai, so there's no AED and no "Other". Anyone outside the UK, EU or US hits a wall here. *Starting a pool (Morocco)* Searching "Morocco" gives Marrakesh, Casablanca, Marrakech, Rabat and Agadir, so city-level results work. But Marrakesh and Marrakech both show up as separate entries. Merge them. Crew size, the "flying from different cities" toggle, the vibe chips and the flights/hotel/activities choice are all clear. The "How many nights?" step has no control. It only says the dates are Apr 15 to 22, 2027 and to go back and type a city if I want other dates. The heading asks a question I can't answer there. Show a nights picker or call it "Your dates". The itinerary step is the best moment in the app. I typed 150 a month and it warned me I'd only be paid up by May 2027, after the trip leaves. That's exactly the "will we actually make it" worry. *The numbers don't match (most important)* I entered 150 a month, the "Your pool is ready" screen said 159 a month each, and the pool page then said 133 each per month. That's three different numbers for the same thing within 30 seconds. For an app that holds people's money this has to be one number everywhere, or say clearly why it changed. A brand-new pool also shows "Behind" in red on day one, with 158 days to go and nothing due yet. It feels like a telling-off before I've started. Show "On track, first payment due X" until a payment is actually missed. *Inviting* On the "Your pool is ready" screen, "Share invite link" did nothing visible on desktop: no share sheet and no "copied" message. On the Crew tab, "Copy code" works and shows "Code copied". Make the first button fall back to copying on desktop. I didn't send the invite to a real friend. *Adding money* On the Pool tab, the floating +40 / +60 / +90 / Other bar sits on top of the "Set up auto-save" button and its "How does this work?" link. Only "Set up" peeks out. Add bottom padding. The add-money sheet is clean: preset amounts, and the line "Payments by Rapyd, a licensed payment institution. Your money is in an e-wallet in your name, not with Ventari." That's exactly the trust line this app needs. Show it on the home screen too, not only at payment. I stopped before the card form, so I didn't test the test-card payment or watch the pool grow. Good to see "Save automatically every month" is in. That's the core value. *Bottom line:* it looks premium and the planner logic is smart. Before anything else, fix the three different monthly amounts and the "Behind" label on day one. When money is involved, numbers that disagree kill trust faster than anything.
• AI Carousel Generator for Instagram & TikTok, 8 Nov 2026: Tested on Web (Chrome, desktop). Signed up with Google in a few seconds and landed straight in the app with 300 credits, no card. *What I made:* "Write from a topic", a 6-slide carousel on why clinics and real estate agencies in Dubai lose leads from missed calls, and how an AI receptionist fixes it. That's a real post I'd want for my own business. *1. Would I post it?* Almost. The structure is right (hook, problem, what happens next, the fix, use cases, CTA) and the copy is tight. Two things stop me. First, slide 4 added "Speaks English and Arabic" as a feature. I never said that. Inventing product claims is the one thing I can't risk on a business account. If the agent adds a claim, flag it: "I added X, keep it?" Second, it's not my brand: a clean blue healthcare look, but nothing asked me for my colours or logo first. After the slide 4 fix I'd post it with light tweaks. *2. AI slop anywhere?* Mostly no. Slide 1 is the weak spot: the illustration puts a "property for sale" sign standing on an office desk, and the desk is cut off at the bottom edge. Slides 2 to 6 look designer-made. *3. Remake:* I didn't test a link remake this round; I went topic-first. *4. Single-slide edit:* Yes, this worked well. I asked "Slide 4 only: remove the 'Speaks English and Arabic' line and make the headline punchier." Only slide 4 changed: the line was gone and the headline became "The fix / ZERO MISSED CALLS". The other 5 slides were untouched. *5. Stuck, waiting or confused:* On the start screen the prompt box grows as you type and the send button moves down with it. My first click landed where the button used to be and nothing happened. Enter works. When the edit started, the big preview showed slide 6 greyed out, not slide 4, which I was editing. For a second I thought it was redoing the wrong slide. Jump the preview to the slide being edited. Generation took about 2 minutes, the edit about 40 seconds. The progress labels ("Reading your message", "Building the slides", "Checking the slides") make the wait fine. Cost: the carousel took 82 credits and a one-line text edit took 49 (300 to 169). A small text fix costing 60% of a whole carousel feels steep. Show the cost before I send. *6. Anything broke:* Nothing broke. Slide 6 has a big empty gap between the headline and the body text, and the CTA "Message us to try it" has no handle or link. Ask me where to send people. *Bottom line:* the fastest I've gone from one sentence to a nearly postable carousel. Stop it from inventing claims, show the cost up front and let me set my brand first, and I'd use it every week.