AI agent stories that use Supabase

5 stories name Supabase among the tools used. By outcome: Get tasks done 3, Make money 1 and Save money 1. Countries: France 1, Philippines 1, Singapore 1, United Kingdom 1 and United States 1. Other tools named in 2 or more of them: Claude 3, Claude Code 2 and Next.js 2. Results are shown as claimed in each public source.

Get tasks doneBusiness size: SoloIncludes prompt

A UK consultant records a short voice note and gets a week of on-brand posts that she approves before anything goes out

Antonella Argentino · United Kingdom · Claude, OpenAI speech-to-text, Cloudflare, Supabase, Instagram API, LinkedIn API

Transcribed voice notes, drafted channel-specific posts and prepared branded carousels. A scheduler published approved posts.

Result, as claimed

The agency that built it reports 30 drafts written from her voice notes and 11 posts published, counted from the live system on 12 November 2026, three days from approved plan to a live app. She says the pilot lets her save time making content, without a number.

Make moneyBusiness size: SoloIncludes prompt

A Paris data scientist proved his LinkedIn prospecting agent in n8n, rebuilt it with Claude Code, and it now brings in about $11K a month

Mo Alani · France · n8n, Claude Code, Unipile, Next.js, Supabase, Stripe

Alani first automated his own LinkedIn prospecting, then spent about three months building the message logic, sequencing and LinkedIn orchestration in n8n and testing it on real outreach. He then spent about a month turning it into a SaaS, with Claude Code doing most of the feature work. The agent finds prospects, writes a personal first message, follows up, answers replies and books meetings. He also used it to prospect for MimikFlow itself.

Result, as claimed

MissumAI reports Stripe-verified revenue on Indie Hackers of $11,414.92 for October 2026 and $11,195.44 in the last 30 days on 2 Nov 2026, and $11,328 MRR from 84 active subscriptions on TrustMRR. Alani said in May that about seven of his 14 paying customers came from MimikFlow prospecting for itself, and the homepage says the system books him about five qualified meetings a week.

Save moneyBusiness size: Small teamIncludes prompt

A 14-truck Tennessee fleet owner built his own trucking back office with Claude Code and ChatGPT for $55 a month and says it saves 20 to 25 hours a week

Wes Oberman · United States · Claude Code, ChatGPT, Claude Sonnet 4.6, Claude Opus 4.8, GitHub, Supabase, Vercel, Resend

Claude Code built the system from prompts ChatGPT drafted. In daily use, Claude Sonnet 4.6, backed up by Claude Opus 4.8, reads a broker rate confirmation PDF and fills the load fields in 15 to 20 seconds, including deduction terms. The system emails load details to the owner operator, tracks status to delivery, and combines invoice, rate confirmation and proof of delivery into one PDF for the broker.

Result, as claimed

Oberman says the system saves 20 to 25 hours a week and costs $55 a month in tool subscriptions, against a cheapest outside quote of about $1,500 a month. A separate AI settlement tool he built cut his wife's Thursday settlements from a 12-hour day to about an hour.

Get tasks doneBusiness size: Small teamIncludes prompt

A Singapore AI studio cut vessel-repair quoting from 2 to 4 hours down to about 8 minutes with a Claude agent

Leon Lee (Connective Labs) · Singapore · Claude, LangChain, Supabase, Next.js, Vercel, Groq, OpenAI

Leon’s studio built an AI Worker for a maritime services client. It watches the inbox for job specs, extracts line items with Claude, matches them to a rate card in Supabase, drafts a quotation, flags unsure items and waits for human approval.

Result, as claimed

For a maritime services client, quoting vessel repairs used to take 2 to 4 hours while an ops manager checked 200+ line items against a rate card in Excel. The AI Worker Connective Labs built watches the inbox, extracts line items with Claude, matches them to the rate card in Supabase, drafts a quotation, flags uncertain items, and sends the draft for one-click approval. Leon says the draft cycle is 8 minutes including human review.

Get tasks doneBusiness size: SoloIncludes prompt

A Telegram bot and n8n system cut a Filipino fitness coach's daily admin from 45+ minutes to 3

John Vargas · Philippines · n8n, Telegram Bot API, Supabase, PayMongo, Claude, GPT-4o-mini

Mikes Sta. Ana built this system for Coach John. It sends check-ins in his voice across a 30-day programme, scores leads, onboards new clients with a payment link and drafts social posts for him to approve. The source is the builder's own case study, and the coach is not quoted.

Result, as claimed

Daily time on operations went from 45+ minutes to 3 minutes. Onboarding after a sale went from 1 to 3 days to under 60 seconds. Active client capacity went from 15 to 50+. AI API cost is under $1/month.

Other tools