About me
Portrait of Anano Kutchava
I'M aka xranano

AnanoKutchava

Forward Deployed Engineer at Meama. I build the LLM systems companies run their daily operations on, and research what makes them reliable.Forward Deployed Engineer at Meama. I build LLM systems that run daily operations.

FORWARD DEPLOYED · TBILISI · GMT+4 ·
About(01)

I work inside operations teams, find the work that still runs on spreadsheets, and build the AI systems that replace it. My research asks why those systems fail and how to make them dependable.I build the AI systems operations teams run on. My research is about making them dependable.

220K+orders processed by systems I builtorders processed
15departments mapped to find what to automatedepartments mapped
4enterprise clients running PRMTRPRMTR enterprise clients
Top 10%ranked 16th of 167 in Computer Science at KIU16th of 167 at KIU
Selected work(01 / 05)

CADNS

Meama · Company operating system

A shared workspace where Meama's employees and AI agents work on the same company data. Underneath is one data foundation: a warehouse, a metrics layer and access control. On top, people ask for work in a chat, and agents act with the permissions of the person who asked. Consequential actions wait for human approval. I mapped workflows across 15 departments to decide what to build first. In development.One workspace where employees and AI agents share company data. Agents act with the asker's permissions; big actions need human approval. In development.

Selected work(02 / 05)

Statica

Meama · Call-centre intelligence

Transcribes and classifies calls to Meama's call centre, pulls the exact customer quotes behind each classification, and tracks every commitment made to a customer by owner, deadline and completion. Unclear cases go to a person, and their decisions improve the next classification.Classifies call-centre calls, quotes the evidence, and tracks every promise to a customer until it's kept.

Python · LLM APIs · Speech-to-text · PostgreSQL
Selected work(03 / 05)

Wilco

Lead Software Engineer · EV taxi platform

I lead a team of three building Wilco, an all-electric taxi platform for Tbilisi. It is three products on one backend: a rider app, a driver app and an admin panel, plus charging software for the fleet's own stations, where drivers plug in and are billed per kWh. In development.Leading a team of three on an all-electric taxi platform for Tbilisi: rider app, driver app, admin panel and fleet charging.

Selected work(04 / 05)

PRMTR

Co-founder & CTO · Commercial analytics

AI agents investigate sales and marketing data and propose actions; a person approves each one. I designed the reliability layer: an independent verifier re-runs the SQL behind every finding, and pricing and margin rules stay in ordinary code, not in the model. Live at four enterprise clients, with 220K+ orders processed and $50K in attributed revenue in the first two weeks.AI agents propose commercial actions and a person approves each. A verifier re-runs the SQL behind every finding. Live at four enterprise clients.

Python · FastAPI · PostgreSQL · LLM agents
Selected work(05 / 05)

Grid Park

ARCI Engineering Hub · Operations platform

I designed the database for an operations platform covering orders, dispatch, fleet, billing and pricing. Business rules are stored as data, so pricing and workflows can change without new code.Database for an operations platform: orders, dispatch, fleet, billing, pricing. Business rules live as data.

PostgreSQL · Supabase · SQL
Experience(03)

Where I build

02.2026 — NOW
Meama / Forward Deployed Engineer Building CADNS, a shared workspace where employees and AI agents work on company data. Agents act with the permissions of the person who asked, and consequential actions need human approval. Before that, mapped workflows across 15 departments, built Statica, and shipped an agent platform for pricing, campaigns and inventory.Building CADNS. Before that: Statica and an agent platform for pricing and inventory.
10.2026 — NOW
Wilco / Lead Software Engineer Part-time Lead a team of three building an all-electric taxi platform for Tbilisi: rider app, driver app, admin panel and fleet charging.Leading a team of three on an EV taxi platform.
08.2026 — NOW
ARCI Engineering Hub / AI & Data Specialist Project-based Designed the data architecture for Grid Park, an operations platform.Data architecture for Grid Park.
2023 — 2027
KIU / Senior Student B.Sc. Computer Science at Kutaisi International University. Thesis on LLM coding agents with Prof. Walter Tichy; student tutor in Computer Architecture.B.Sc. Computer Science. Thesis with Prof. Walter Tichy.
Research & education(04)

Research

Thesis · with Prof. Walter Tichy · 2026 — now Where LLM coding agents break Controlled experiments comparing the productivity of LLM coding agents with human developers, and why agents fail to repair constraint violations mid-task.Why LLM coding agents fail to fix constraint violations mid-task.
Coursework project Agon: LLMs in structured debate Language models debate 25 philosophical problems in front of an LLM judge. Changing the judge's persona changed who won, which shows how much evaluation design shapes results.Changing an LLM judge's persona changed who won the debate.
NLP · Low-resource language Georgian spellchecker ↗ Built a Georgian spelling-error dataset from scratch and trained a seq2seq model for word-level correction.Dataset built from scratch, plus a seq2seq corrector.
KIU · B.Sc. Computer Science · 2023–2027 Ranked 16th of 167 (top 10%) · Full national scholarship (top 100 nationally) · State and university stipends · Student tutor, Computer ArchitectureTop 10% of class · Full national scholarship · Student tutor
AI
LangGraphLangChainAnthropic APIOpenAI APIMulti-agent orchestrationRAGAgent evaluation
Backend
PythonTypeScriptFastAPISQLPostgreSQLSupabase
Data / ML
PyTorchscikit-learnXGBoostForecastingAWSDocker
Contact(05)

Let'stalk

© 2026 Anano Kutchava (xranano) · Tbilisi, GMT+4