Skip to content

Industries · SaaS & Startups

AI features your customers will pay for.

For a product team, AI has to do two things at once: delight users and keep margins intact. I build AI features end to end (chat, agents, voice, automation) with the cost controls, billing and testing a real product needs.

Book a free discovery call See the work
Where AI pays off

What I build for teams like yours.

  • 01

    In-product AI copilots

    Chat and assistance inside your app, grounded in your data.

  • 02

    Subscription AI products

    Stripe billing, trials and webhooks wired to the AI experience.

  • 03

    Voice and WhatsApp channels

    Reach users with voice notes and conversational support.

  • 04

    Workflow automation

    Internal operations automated with LLM steps where judgment is needed.

What makes it hard

The constraints are the project.

The model is rarely the problem. These are the requirements that decide whether a system ships, and they are designed in from the first week.

  • Unit economics

    Prompt caching, model routing and token budgets from day one.

  • Speed to market

    Weekly demos and a focused first release, then iterate.

  • Quality at scale

    Automated tests for conversations, sessions, webhooks and security.

  • Ownership

    Clean, documented code your team can run after handover.

Proof

Relevant case studies.

whatsapp · ai-sponsor
24/7
0:14

whisper → “Tonight is hard. Can we talk for a minute?”

0:19

I’m here. Let’s take it one step at a time. What’s on your mind?

prompt cache · input tokens≈90% saved

Illustrative interface · client data never shown
01AI Sponsor

Multi-Channel AI Support SaaS Platform

The backend for a 24/7 AI sponsor that supports people in 12-step recovery over chat and WhatsApp voice. It combines Claude-powered conversations, Stripe subscription billing and a prompt-caching architecture that cut LLM input costs by about 90%.

LLM input-cost reduction
~90%
Chat and voice availability
24/7
Automated test categories
12
Read case study
Productivity4 stages
  1. 01Research
  2. 02Score
  3. 03Draft
  4. 04Review

Stage 1, Research: Live web search. Stage 2, Score: Topic relevance scoring. Stage 3, Draft: Posts, comments, cover letters. Stage 4, Review: Human edits and publishes.

02Content Copilot

Human-in-the-Loop Content & Career Agent

A local-first, three-agent assistant that drafts LinkedIn posts, comments and tailored cover letters and scores topics against live web search. Every publish and apply action is left to a human by design.

Cooperating agents
3
Topic scoring
Web-grounded
Automated publishes, by design
0
Read case study
Customer Support & E-commerce5 stages
  1. 01Call
  2. 02Listen
  3. 03Understand
  4. 04Act
  5. 05Escalate

Stage 1, Call: Inbound phone call. Stage 2, Listen: Speech-to-text. Stage 3, Understand: LLM intent detection. Stage 4, Act: FAQ answers, order lookup. Stage 5, Escalate: Live-agent handoff.

03Voice Support Agent

Voice AI Customer-Support Agent

A conversational voice agent that answers inbound calls, resolves FAQ and order-status questions in natural speech, and hands off to a live agent as soon as a request is out of scope.

Inbound voice channel
Calls
Self-service coverage
FAQ + orders
Escalation path
Live handoff
Read case study
cloudops-agent · amazon bedrock
Confirm-first
Create a private S3 bucket for invoices in Ireland, with versioning.

I’ll create this resource. Please confirm:

Bucket
invoices-archive-eu
Region
eu-west-1
Access
Private, public access blocked
Versioning
Enabled
Confirm this change? (yes/no)Yes, createNo

boto3 call runs only after an explicit yes · claude 3.5 sonnet on bedrock

Illustrative interface · client data never shown
04CloudOps Agent

Natural-Language Cloud Operations Agent on Amazon Bedrock

A chat-driven AWS operations agent on Amazon Bedrock that lets non-engineers create, inspect, update and delete cloud resources in plain language, with validation and confirm-before-execute guardrails on every change.

Changes require explicit approval
100%
Full resource lifecycle in plain language
CRUD
Claude 3.5 Sonnet on AWS
Bedrock
Read case study

Services for SaaS & Startups

Other industries

AI project estimator

Get a tailored project plan in 60 seconds.

Five questions about what you’re building. Instantly see the recommended architecture, delivery phases and a realistic timeline, then email it to yourself.

  • Architecture
  • Phased plan
  • Timeline

Step 1 of 5 · What are you building?

Start the estimator
FAQ

SaaS & Startups: common questions.

How fast can we ship an AI MVP?

A focused first release typically takes a few weeks after a short discovery phase. Use the project estimator for a tailored timeline.

How do you keep LLM costs from eating our margins?

Cache-first prompt design, smaller models for simple steps, retrieval instead of oversized prompts, and usage monitoring. On one SaaS backend, caching cut input-token costs by about 90%.

Will our team be able to maintain it?

Yes. You get documented code, tests and a handover, plus optional ongoing support.

Available for new engagements

Have an AI initiative in mind? Let’s scope it in 30 minutes.

Free discovery call. You'll leave with a clear view of the architecture, risks and next steps, whether or not we work together. I reply within 24 hours.

Book a free discovery callSend project details

Not ready to talk yet? Get an instant project plan.