We ship AI software that earns its keep.
For SaaS founders and operators who need AI in production — not in a slide deck. We’ve built 37 products ourselves — email triage, AI tutors, content engines, CRM tools — so your project gets proven infrastructure from day one. First working demo in 1–2 weeks.
This is for you if…
You have a workflow that still runs on people, not software — and you want to change that without a six-month engineering project.
You know where AI could help but don’t have the team to build the eval pipeline, prompt ops, and infrastructure that make it reliable.
You know what an LLM is. You know the business case. You need a team that’s actually shipped it in production — not just demo’d it.
Why Dainty Trading
Most AI agencies spend eight weeks writing a deck. We spend it writing code.
Proof of work, not pitch decks
We have 37 products — 13 live and paying — you can click on right now. Every project page shows the real stack, the build timeline, and what broke. That’s the portfolio. Judge us on it.
Speed that’s earned, not promised
First working demo in 1–2 weeks. First paying customer in 4–8 weeks. We move fast because we’ve already built the boring parts — billing, auth, LLM routing, observability — and reuse them across every project.
Proven plumbing, not glued-together demos
We’ve already built the layer most AI projects trip over — routing, billing, observability, evals. Every client gets it on day one, because we run it for our own products first. Stack: Claude · LiteLLM · n8n · FastAPI · Postgres
We align on P&L, not feature lists
AI that doesn’t reduce headcount, cut support tickets, or generate revenue isn’t AI — it’s a line item. We build to measurable outcomes and tell you what success looks like before we start.
How an engagement works
Hard deadlines at every stage. No discovery phase that lasts longer than the build.
Brief received
Fill in the contact form. We reply with our read on the project and any clarifying questions — same business day.
Scope agreed
If it’s a fit, we send a one-page scope for the first sprint: fixed price, hard end date, and exactly what you’ll have at the end of it.
First demo live
A working slice of your product, deployed somewhere you can use it. Not a mockup, not a Figma — running software.
37 AI Products Built and Running
Each project is a real product running in production. Click any card to read the full build story and visit the live site.
Live 13 products
BrightPath
Personalised K-12 online school with an AI tutor named Pax, gamified rewards, and progress tracking that actually nudges kids.
AI tutor in production · K–12 students on-platform daily Read the story → AI · ProductivityEmail Triage
Claude-powered email categorizer that scores priority, drafts replies, and runs across multiple Gmail and Outlook accounts.
200+ emails processed daily · Runs across Gmail & Outlook Read the story → Tools · APIEmail Cleanup
FastAPI service that validates email domains, flags disposable providers, and gives you a single endpoint for bulk list hygiene.
Read the story → AI · ConsumerSubscription Incinerator
Finds the subscriptions you forgot, ranks them, and burns the ones you don’t want. Claude drafts merchant-specific cancellation emails; SMS chases the rest.
Read the story → AI · CRMEveryring.ai
Captures missed phone calls, prioritises follow-ups, and uses Claude to draft the right next message for each contact — in seconds.
Read the story → AI · CareersCV Matcher
Scrapes LinkedIn job postings, scores them against your CV with Claude, and tells you why each match scored the way it did.
Read the story → AI · Local SEOBizPage Builder
Discovers small businesses without websites, generates SEO-ready landing pages with Claude, and ships them as deployable ZIPs.
Read the story → Productivity · MobileFocusShield
Cross-platform focus and task app — web, iOS, Android — with productivity analytics and JWT auth wired into a Postgres backend.
Read the story → Email · AutomationAutoArchive
Built for a Big 4 Australian bank. Backs up 45 shared email boxes four times a day to a secure local disk — each email named by message ID for instant retrieval, no database needed.
Read the story → SaaS · Cross-platformTimerForge
Countdown timer that ships as a desktop app for Windows/Mac/Linux and a web SaaS — embeddable, shareable, billed by Stripe.
Read the story → AI · ContentGhost Writer
End-to-end content engine: detects trending topics, writes 1,500-word articles, runs 6-layer quality checks, and auto-publishes to LinkedIn and Medium.
3 articles/week published · No human writer in the loop Read the story → AI · CoachingConvoForge
Multimodal AI communication coach. Speech analysis, body-language feedback, AI avatar roleplay, and a live meeting overlay.
Read the story → Finance · AutomationSolar Loan Reconciler
Built for a financial company. Collects Mon–Fri solar loan transaction CSVs, matches them against the weekly Loan Payout Report, flags any gaps, and emails a clean HTML report to the loans team every Friday.
Zero missed loans since go-live · Fully automated every Friday Read the story →In final testing 12 products
Meditation
Subscription meditation library with a 7-day free trial, Stripe billing, and a content gate that doesn’t feel like a content gate.
Read the story → AI · Bots in testNudgle
Telegram reminder bot with natural-language scheduling. Quiet hours, vacation mode, recurring tasks — all parsed by Claude.
Read the story → AI · Marketing Ops in testMarketing OS
The internal control tower for our marketing — campaign planning, web automation via Puppeteer, and an AI-assisted content brief queue.
Read the story → AI · Knowledge in testChatVault
One searchable archive of every conversation across Claude, ChatGPT, Gemini, Grok, and Perplexity. Stop losing the answer you got three weeks ago in a different tab.
Read the story → AI · Personal Finance in testTax Prep
Drop receipts, statements, and slips in throughout the year. Claude classifies and tags. At year-end, one export gives your accountant a structured handover.
Read the story → AI · Knowledge in testSecond Brain
Telegram-native note-taking. Forward anything — voice, photo, link, half-thought — and Claude tags it, links it, and gives it back when you actually need it.
Read the story → AI · Cost-of-living in testPrice Scout
Cost-of-living dashboard tracking grocery, fuel, and energy prices across Australia and the UK. Households see how their spend compares week to week.
Read the story → AI · Developer Tools in testAuto-Claude
Autonomous multi-agent coding framework. Plans, builds, runs tests, and iterates until the goal is met — humans only when it asks.
Read the story → AI · Mobile in testFakeCall
Schedule a believable incoming call with an AI on the other end having a real conversation. CallKit on iOS, streaming Claude responses.
Read the story → AI · Marketing automation in testStoryPulse
Instagram growth-automation SaaS. Automated story views and reactions, AI captions, multi-account campaigns, anti-detection layer, Stripe-billed plans.
Read the story → AI · Social media in testPost Reel
Social media scheduler with an AI video studio built in. Give it a URL, it crawls the site, writes a script, synthesises a voiceover, and produces a finished short-form video — scheduled across 12 platforms automatically.
Read the story → Infrastructure · SaaS in testBilling API
Shared billing service across our portfolio. Stripe, Brevo, Postgres, and a Fastify core that lets every product launch on day one with payments wired in.
Read the story →In active development 12 products
DevTodo
Pulls TODOs from your code, syncs Google Calendar, runs through n8n, and uses Claude to write the summary you would’ve skipped.
Read the story → AI · Lifestyle in devChefForge
AI recipe and meal planning service. Tell it your constraints, get a week of dinners and a shopping list that actually adds up.
Read the story → Wellness · Mobile in devYoga Platform
500+ poses, sequence builder, mobile + web. Filter by chakra, prop, body part, or style — then save your flow.
Read the story → API · Backend in devRecipe API
Django REST API for recipes and ingredients — filtering, pagination, auth, and a clean schema you can plug into any front-end.
Read the story → AI · OCR SaaS in devScreenshot to Text
Production OCR for tables, handwriting, and complex layouts. Tesseract for the easy text, GPT-4 Vision for the hard, Stripe for billing.
Read the story → AI · Field operations in devReceipt Bridge
Field workers text a receipt photo to a shared number. OCR extracts the data, finance reviews in a dashboard. No paper, no manual entry.
Read the story → AI · Productivity in devPrompt Builder
A 3-step wizard that turns rough ideas into polished AI prompts. Adaptive clarifying questions per goal, not a fixed checklist.
Read the story → Personal finance in devFinance Tracker
No-frills personal finance tracker for income, expenses, and budgets. Manual entry, clean charts, no SaaS subscription.
Read the story → Fintech · Automation in devBanking Alerts
Push alerts when bank balances drop below thresholds. Open Banking via Basiq, n8n on top, ntfy for the notifications.
Read the story → AI · Crypto research in devTelegram Crypto Sentiment
Monitors crypto Telegram groups for sentiment, scores it with Claude, and correlates against price movement to surface predictive channels.
Read the story → Productivity · Automation in devScreenShoot Cleaner
Drop a folder of screenshots, get back a clean PDF. Auto-crop, deskew, contrast-normalise, sort, bundle. Local-first, no cloud.
Read the story → AI · Mobile in devReceiptSnap AI
Native iOS and Android receipt scanner. One-handed capture at the till, OCR via Google Cloud Vision, year-end export for your accountant.
Read the story →Supporting cast
The open-source stack we self-host alongside our own builds. We don’t bolt onto SaaS treadmills — we run the tools we recommend.
The open-source stack we self-host. Each one replaces a SaaS, runs on our own boxes, and is something we can stand up for clients on day one.
AI & Automation 3 tools
LiteLLM Proxy
Unified API gateway for LLM providers. One endpoint speaks Claude, OpenAI, Gemini, and others.
Visit project → Open source · vs ChatGPT.comOpen WebUI
Self-hosted chat interface for any LLM. Pairs with Ollama or any OpenAI-compatible endpoint.
Visit project → Open source · vs Zapiern8n
Visual workflow automation. Connects APIs, databases, and webhooks in versionable graphs.
Visit project →Files & Productivity 3 tools
Cal.com
Open-source scheduling. Calendar-aware booking links, team rotations, and event types.
Visit project → Open source · vs filing cabinetsPaperless-NGX
Document management for the paperless office. OCR, tagging, full-text search across PDFs and scans.
Visit project → Open source · vs DropboxSyncthing
Peer-to-peer file synchronisation. Continuous sync between devices on your own network.
Visit project →Site & Studio Ops 3 tools
Umami
Privacy-friendly web analytics. Tracks page views, referrers, and user flows without cookies.
Visit project → Open source · vs tweeting at the ISPSpeedtest Tracker
Internet-speed monitor. Logs throughput on a schedule and triggers actions when it drops.
Visit project → Open source · vs ssh + docker psPortainer
Docker management UI. Visual control over containers, images, networks, and volumes across hosts.
Visit project →Why this matters for clients. When we build for you we’re not stitching together SaaS subscriptions and hoping the prices don’t change. We know what each of these tools costs, what they break under, and how they fail — because we run them ourselves. Same stack, your hardware, your auth.
AI Development Services
We don’t do AI demos. We ship AI features that show up in your P&L. Four things, done well.
AI product builds
Full-stack delivery. We take an idea — yours or ours — and ship a paying product. Backend, frontend, mobile, billing, observability, and the LLM glue that makes it real.
Automation retrofits
Already have a SaaS or internal tool? We bolt in AI where it earns its keep — email triage, support deflection, content generation, structured extraction — without rewriting the world.
AI infrastructure
LLM gateways, prompt versioning, evals, queue workers, billing plumbing, observability. The unsexy layer that decides whether your AI feature stays up at 3am.
SEO & GEO optimization
Get found by Google and by AI answer engines. We audit and fix meta tags, schema markup, llms.txt, and AI-crawler access — shipped directly to your codebase, not a PDF. Free audit, Setup from $2,450 — not the $5k–$15k-plus retainer agencies typically quote for the same audit-and-fix scope.
How we work
No retainers, no long SoWs to sign. Three steps from brief to paying customers.
Brief → scope in 48 hours
Tell us the workflow or product in two paragraphs. We come back with a realistic scope: what ships in sprint one, what the stack looks like, and what it costs. No proposal theatre.
Sprint one → demo in 1–2 weeks
We don’t start with architecture reviews. We ship the smallest thing that proves the idea works, put it in front of a real user, and let you decide whether to continue. One working feature. Deployed. Clickable.
Iterate to a product → weeks 3–8
Each sprint adds one feature that earns its keep. Daily written updates. Weekly live demo. You own the roadmap; we own the execution. By week eight, you have paying customers or we’ve told you why.
Frequently asked questions
Short answers to what people ask before booking a call.
What is Dainty Trading?
Dainty Trading is an AI automation studio. We design, build, and operate production AI software — 37 products covering email, content, education, knowledge management, marketing automation, scheduling, billing, and SaaS infrastructure. Some are shipped and live; others are in final testing or active development. Each project page is honest about which.
What kind of AI projects do you take on?
LLM-powered features (Claude, Gemini, OpenRouter), agentic workflows, content automation pipelines, AI-driven personalisation, and structured-extraction systems. We also do the boring infrastructure that keeps them up — gateways, queues, evals, billing.
What stack do you build on?
Python (FastAPI, Django) and Node.js (Fastify, Express) on the backend; Next.js, React, and React Native on the front; PostgreSQL and Redis for state; n8n for orchestration; Stripe for billing; LiteLLM for routing across model providers; Docker everywhere.
Do you only build with Claude?
No. We default to Anthropic Claude because it punches above its weight on long-context and structured tasks, but we route through OpenRouter and LiteLLM so projects can pick Gemini, OpenAI, or open-weights when the economics or latency demand it.
How fast can you ship?
First demo in 1–2 weeks for most builds. A first paying customer in 4–8 weeks. We move fast because we’ve already built the boring parts (billing, auth, LLM routing, observability) and reuse them across every project.
Where are you based?
Australia. We work async with clients globally and are happy to operate in your timezone.
How do I start?
Email us via the contact page with two paragraphs: what you want built and why it matters. We’ll reply within one business day with a scoped first sprint.
From the blog
How we think about building AI in production.
How long does it take to build a production AI agent?
The demo takes a week. The gap to reliable production is evaluation pipelines, fallback handling, and edge cases — here’s the honest timeline.
Read → EngineeringRules Still Win: When Not to Use an LLM
LLMs aren’t a silver bullet. Our decision tree for when deterministic rules outperform AI models — and when to use both.
Read → CostToken Cost Optimization: Where the Savings Actually Are
The highest-ROI strategies for reducing LLM costs in production: prompt caching, model routing, context trimming, and output constraints.
Read →What users say
“SATs week and we have been using BrightPath for about 2 weeks now. Ethan just learnt long division, in the space of a day and actually enjoyed the lessons. He asked me why didn’t school teach me this way — the step-by-step guides at the start help so much. Thanks for the help BrightPath team, keep up the good work.”