# Feras Allaou

> Technical Growth Strategist. Ten years building software, cloud infrastructure and AI systems. Now I help companies find what’s holding them back, and what to do about it.

I work with companies that are stuck on engineering, visibility, growth or what to build next. I diagnose the problem, brainstorm options with the team, and recommend what to do. The work is mostly advisory; I build only when it makes sense. Every engagement starts with a free 15-minute call.

## Who I help

### Technical founder

Your team is shipping slower and your cloud bill keeps growing. I find out why and what to fix first, so you can get back to building.

### Founder

You have users, but growth has stalled. I go through your numbers, find where people drop off, and suggest what to try next.

### Starting out

You have an idea and want to get it online the right way. I help you choose what to build first, and make sure people (and AI) can find it.

## Services

- **Engineering:** High cloud bills, slow releases, messy architecture. I find what’s slowing you down and what it’s costing you.
- **Team growth:** I look at how your engineering team plans, ships and works together, and help it move faster without burning people out.
- **Visibility & AI readiness:** Get found on Google and cited by ChatGPT, Claude and Perplexity. Use AI inside your company where it actually saves time.
- **Growth:** We go through your numbers together, find where people drop off, and decide what to try next.
- **Product ideas:** New ways to improve your platform. My ideas won two internal hackathons at companies I worked for.

## How it works

1. A free 15-minute call to understand what's stuck.
2. A working session to dig into the numbers, the system or the team, and brainstorm options.
3. A prioritised action plan. Your team builds it, or I help.

## Work

### From search filters to search by prompt

- Role / type: Case study · Property marketplace
- Status: Live
- Link: https://ferasallaou.com/work/filters-to-prompt/

Users ignored the search filters. Instead of a rebuild, people now describe the home they want and AI sets the filters. Prototype in 2–3 days, live in 2 weeks.

### Plurity.ai

- Role / type: Founding Engineer · AI search visibility
- Status: Current
- Link: https://plurity.ai/

Helping brands in regulated industries like pharma, finance and insurance get found and cited by AI search.

### AgentReady

- Role / type: ChatGPT app · AI readiness
- Status: Live
- Link: https://agentready.ferasallaou.com/

Checks whether ChatGPT, Claude, Perplexity and others can find, read and quote your website, and tells you what to fix.

### Sportswear brand

- Role / type: Growth audit
- Status: In progress

Online sales had stalled. Going through the numbers with the founder to find where buyers drop off, and what to try next.

### Marillo.ai

- Role / type: Founder · AI
- Status: Product experiment
- Link: https://marillo.ai/

Letting non-engineers ask questions of their data in plain language, and earning their trust about where that data goes.

### Laranja.io

- Role / type: Founder · Developer tools
- Status: Product experiment
- Link: https://laranja.io/

Deploys Node.js apps to AWS and Azure from one config file, with no hand-written infrastructure code.

## Case study: From search filters to search by prompt

- Client: A property marketplace (anonymised)
- Link: https://ferasallaou.com/work/filters-to-prompt/
- Prototype: 2–3 days
- Live: 2 weeks
- Rebuild: None
- My role: Idea and build

Users ignored the search filters, and the team thought smart search meant a rebuild. Instead, I gave an AI agent the search they already had. Working prototype in 2–3 days, live in 2 weeks.

### The problem

The search worked like most big booking and property sites: a location box, a few dropdowns, and a long column of filters on the left. Most people typed a place, hit search, and scrolled. The filters that would have found them the right home went mostly unused. The team knew search had to get smarter, but assumed it meant months of work on a new search system.

### The insight

The search already knew every filter, and every possible value, for each location. That’s how the sidebar was built. So the AI didn’t need a new search engine. It needed to know which filters exist, and permission to set them. We gave it the existing search functions as tools.

### How it works

1. **Describe it:** The person writes what they want, in their own words.
2. **Read the options:** The AI asks the existing search which filters exist for that place.
3. **Set the filters:** It picks the values that match the request and runs the normal search.
4. **Show the results:** Results appear on the same page, with the filters visible so people can adjust them.

### Example

"3-bedroom flat in Lisbon near a good school, under €2,000 a month. We have a dog and need parking."

- "Lisbon" → Location: Lisbon
- "a month" → Type: Rent
- "flat" → Property type: Apartment
- "3-bedroom" → Bedrooms: 3
- "under €2,000" → Max price: €2,000 / month
- "We have a dog" → Features: Pets allowed
- "need parking" → Features: Parking
- "near a good school" → Nearby: Schools

### Timeline

- Day 1: The idea: the filters already exist, so let the AI use them.
- Days 2–3: Working prototype, connected to the real search.
- Week 2: Live for users, with the classic filters still there.

Under the hood: The existing search API, which already returned the filters and values for each location, wrapped as tools for a LangChain agent. No new search engine and no data migration.

### Takeaways

- Being AI-ready rarely starts with a rebuild. Often the pieces are already there.
- Keep the old way working. AI fills in the filters, and people can still change them.
- Ship a prototype in days, then decide. It’s cheaper than a planning cycle.

Next step: The same tools can be exposed over MCP, so assistants like ChatGPT and Claude can search the platform directly.

## Background

I have spent ten-plus years as a remote software engineer and technical lead, across fintech, proptech, media and developer tools, now focused on growth strategy and AI.

### Experience

- Founding Engineer, Plurity.ai (current)
- Founder and Product Engineer, Alzulejos (laranja.io, marillo.ai) (2026 – present)
- Senior Full-Stack Engineer, OWNR GmbH (2022 – 2026)
- Senior Full-Stack Engineer (fintech, PSD2, BNPL), Finbyte GmbH (2021 – 2022)
- Technical Team Leader, Dama Dev (2018 – 2021)
- Backend Engineer, Stowk Inc. (2019 – 2021)
- Tech Editor and Developer, Al Jazeera (2016 – 2018)

### Expertise

- Cloud: AWS (Lambda, CDK, CloudFormation, API Gateway, S3, SQS, EventBridge), Azure, Google Cloud, Terraform, Docker
- Backend: NestJS, Node.js, GraphQL, REST, PostgreSQL, MongoDB
- Frontend and mobile: React, Next.js, React Native
- AI: LangChain, LangGraph, multi-agent systems, tool calling, natural language to SQL, MCP servers and ChatGPT apps
- Practice: infrastructure as code, CI/CD, technical leadership, mentoring

### Credentials

- Won two internal hackathons with ideas for improving company platforms
- Mentor on ADPList; previously entrepreneurship mentor at Impact Hub and Habitat Derneği
- Creator of an Agentic AI video course on YouTube, with open-source companion code

## Topics

Technical Growth Strategist, growth engineering, growth consulting, technical advisor, fractional technical advisor, startup advisor, AEO (Answer Engine Optimization), GEO (Generative Engine Optimization), AI search visibility, AI readiness, llms.txt, MCP (Model Context Protocol), SEO, cloud cost optimization, AWS cost reduction, software architecture review, engineering team performance, engineering productivity, product strategy, conversion and funnel analysis, product ideation, AI adoption, agentic AI, AI-powered search, natural language search, LLM tool calling

## Contact

- Email: me@ferasallaou.com
- Book a free 15-minute intro call: https://calendly.com/feras-allaou/15min
- Mentorship on ADPList: https://adplist.org/mentors/feras-allaou-mul0qs9a
- LinkedIn: https://www.linkedin.com/in/ferasallaou/
- GitHub: https://github.com/ferasallaou/
- YouTube: https://www.youtube.com/@FerasAllaou