01·Solar intelligence, both sides of the sale
Solas & Solis
A pair of tools for commercial solar in Lebanon: Solas turns raw generator data into a bankable proposal, and Solis checks the installed array against that promise. One sells; the other keeps you honest.
The problem
Most commercial sites in Lebanon run on diesel generators, and solar pitches are mostly guesswork — nobody measures the actual load before quoting, and nobody verifies the array after commissioning. Buyers are asked to trust a brochure.
What I built
Solas reads a generator-controller export, reconstructs the site’s load profile, pulls live irradiation data for the exact coordinates (PVGIS, EU Joint Research Centre), and produces a one-page trilingual investment study — headline payback, sizing, battery opportunity — as a PDF you can hand across a desk.
Solis closes the loop after installation: it reads monitoring exports from six inverter brands with zero configuration, rebuilds the expected output for that location and period, and issues a plain-language verdict — including per-string health, so a shaded or failing panel section is caught from the data alone.
62
automated tests across the pair
24
adversarial data scenarios in the parser suite
6
inverter vendors auto-detected, no config
3
languages — English, French, Arabic with full RTL
Both demos load a sample site in one click — or download the raw sample files (controller export .xlsx, inverter export .csv) and upload them like real ones. The study above was produced from exactly that flow. Download the one-page PDF it generates →
02·Measuring the new search
GEO Monitor
When customers ask ChatGPT instead of Google, does your brand come up? GEO Monitor asks the question a customer would actually type — to three AI engines — and turns their answers into a score you can act on.
The problem
AI assistants increasingly answer “who should I hire?” directly, and brands have no idea whether they are recommended, buried, or invisible — or which sources the engines are citing instead of them.
What I built
The same brand question goes to ChatGPT, Gemini, and Claude with web grounding on. A fourth model pass reads all three answers and extracts structure: was the brand mentioned, at what rank, described how, on the strength of which sources. Scores are discounted by rank and sentiment into a weighted visibility metric, tracked sweep over sweep.
Engines don’t give the same answer twice, so the design leans into it — repeated sampling with honest variance reporting, rather than pretending one answer is the truth.
3
AI engines queried with web grounding
4th
model pass extracts structured findings
2
scores — raw visibility and rank-weighted
0
framework dependencies in the core engine
The demo shows a seeded fictional brand — no client data appears anywhere.
03·The day job — platform product management at scale
Toters
By day I'm a Platform Product Manager at Toters, the delivery super-app serving Lebanon and Iraq. The projects above are nights and weekends; this is production work across customer, courier, and back-office apps — described here at case-study altitude.
Address revamp
Reducing undelivered orders
In markets where street addresses are often approximate, vague addresses fail deliveries and flood support. I own the program rebuilding addressing end to end: a richer address model with landmarks, photos, and voice notes; interception of incomplete addresses at checkout; and ops tooling to flag problem addresses back to the customer. Success is measured where it hurts — fewer “can’t find the customer” escalations and faster driver time-to-find.
Platform integrity
Device intelligence with Incognia
I drive Toters’ fraud-prevention program: a fraud engine built behind a provider abstraction, rolled out monitor-first behind feature flags, powering device-level blocklisting, promo-abuse prevention, and SMS-pumping defense. Represented Toters at the closed-door Platform Integrity Network workshop in Singapore, co-presenting our approach alongside our partner Incognia.
AI customer support
LLM automation with OpenCX
I own the rollout of LLM-driven support automation, starting where the volume concentrates: “where is my order?” chats. Scoped the pilot, defined the metric gates (repeat-contact rate as the AI-accuracy red flag), and shipped phased rollouts — including AI that doesn’t just answer but acts, assigning couriers on stuck orders, with chat ratings captured at the AI-to-human handover so quality is measured at the seam.
About
I’m Charles. I work at the seam between product and engineering — close enough to the business to know which number matters, close enough to the code to ship it.
Beyond the case studies above, I’ve built and shipped software for restaurants, insurance agencies, and hospitality operations — in English, French, and Arabic.