Services
AI & Machine Learning
AI agents, LLM pipelines with retrieval, forecasting, computer vision and document AI — built into your product and measured by before/after numbers.
Services
AI & Machine Learning
Free Open-Source AI Chatbot for Business Automation
Discover Glanit's open-source AI chatbot solution. Automate customer support 24/7 using Grok, Gemini, and ChatGPT. A self-hosted, free alternative to expensive SaaS tools—pay only for API usage.
Learn More →
How AI agents work: architecture of a production agent
An AI agent is not a chatbot with a longer prompt. It is a system: a model for reasoning wrapped in perception, memory, tools, orchestration and monitoring. We build agents for clients and for our own products — this is the architecture behind them.
Learn More →
What do we build?
We build AI that ships as part of a product: agents that act inside your workflows, LLM pipelines with retrieval over your documents, forecasting and scoring models, computer vision and document AI — with monitoring and an owner, never a separate science project. Our AI team works inside the same delivery process as the rest of Glanit: discovery, pilot, rollout, support. This is now mainstream work: McKinsey reports that 78% of organisations use AI in at least one business function (McKinsey, 2025), and the difference between them is not the model but whether it reached production.
- AI agents that act inside your workflows: read and write CRM/ERP records, answer customers, prepare documents, escalate to people when confidence is low.
- LLM pipelines with retrieval (RAG) over your documents, tickets and databases — grounded answers with sources.
- Forecasting and scoring: demand, churn, risk, pricing, lead quality.
- Computer vision: quality control, document and image classification, OCR.
- Document AI: invoices, contracts, forms — extraction, validation, posting to the ERP.
- NLP: classification and routing of feedback, emails and tickets in many languages.
RAG vs fine-tuning: which one do you need?
For most business cases the answer is retrieval (RAG) first: it grounds answers in your current documents with sources, updates instantly when the documents change and needs no training run. Fine-tuning is worth it when you need a specific style, format or narrow skill at lower cost per call. The two combine well; retrieval-augmented generation was introduced by Lewis et al. (2020) precisely to give language models fresh, citable knowledge without retraining.
| Criterion | RAG (retrieval) | Fine-tuning |
|---|---|---|
| Best for | Answers over changing documents, tickets, databases | Style, format, tone, narrow classification tasks |
| Freshness | Immediate — update the index | Requires a new training run |
| Traceability | Answers cite the source passages | No sources; knowledge is baked into weights |
| Data needed | Your documents, access rules | Hundreds to thousands of curated examples |
| Cost profile | More tokens per call, no training cost | Training cost up front, cheaper calls later |
| Typical risk | Retrieval quality, access control leaks | Overfitting, drift, expensive to correct |
How does an AI project run?
An AI project runs in four stages — discovery, pilot, rollout, support — and every stage ends with a number you can check. The reason for the discipline is simple: Gartner predicted that at least 30% of generative AI projects would be abandoned after proof of concept by the end of 2025, citing poor data quality, unclear business value and escalating costs (Gartner, 2024). A pilot that is measured against your real cases from week one does not become one of them.
Discovery (1–2 weeks). We map the process, collect a sample of real data and agree on the metric that decides success — hours saved, error rate, conversion, response time.
Pilot (4–8 weeks). A working system on a narrow slice with an evaluation set built from your real cases. You get a number, not a demo.
Rollout. Integration with your systems, guardrails, human-in-the-loop where actions are irreversible, monitoring of quality, cost and drift.
Support. Evaluation on every change, model updates, an improvements backlog — under an SLA.
Which stack do we use?
The stack is Python first: PyTorch, scikit-learn, LangChain/LlamaIndex or plain SDKs; OpenAI, Anthropic, Google and open-weights models (Llama, Mistral, Qwen) — self-hosted when data must stay inside your perimeter. Vector search runs in pgvector, Qdrant or Elasticsearch; serving on Kubernetes or serverless; tracing with OpenTelemetry/Langfuse. We pick the smallest model that reliably hits the target, because prices keep falling: Stanford's AI Index estimates that the cost of running a model at GPT-3.5 level fell more than 280-fold between November 2022 and October 2024 (Stanford HAI, 2025) — a good reason not to lock the architecture to one vendor.
Where is the proof?
The proof is in the case studies and in the numbers they report. See our case studies: retail assistants on RAG, invoice Document AI, catalogue deduplication, customer-feedback NLP, and our own AI products. We also explain how AI agents work in production, and every AI system we ship is built with our AI security practice in mind.
Frequently asked questions
Case studies
Related case studies
Catalogue AI: classifying new SKUs and cleaning 182 000 product cards
Two models on the product catalogue of a grocery chain: one suggests the classification code and category for every new item with top-3 probabilities, the other finds duplicate product cards semantically. Category managers confirm with one click instead of searching the classifier by hand; every confirmation feeds back into training.
- Retail · Master data
- Python
- scikit-learn
- Sentence Transformers
AI knowledge assistants for a 30 000-employee grocery chain
Three RAG assistants on one platform — for commercial staff, store directors (by voice, from the shop floor) and HR — answer questions from corporate regulations with a citation to the exact clause, or say honestly that they do not know — so staff stop phoning head office for routine questions.
- Retail
- Python
- LangChain
- PostgreSQL + pgvector
Document AI that reads 1 300 supplier invoices a day
Scans and photos of invoices, delivery notes and acts go through a multimodal model that extracts typed fields with a confidence score per field, reconciles them with the supplier and contract master data, and posts to the ERP. Only low-confidence documents reach a human — roughly one in nine.
- Retail · Finance
- Python
- PyTorch
- Multimodal LLM
Insights
Related articles
AI & Machine Learning
From the shared inbox to the CRM in minutes: an AI agent that triages quote requests and support tickets, and waits for your approval
A two-line email with a 14-page drawing pack and an Excel sheet lands in the shared inbox, and someone has to read all of it before a quote can start. An AI triage agent does that reading, fills your CRM and drafts the quote or ticket, then waits while a named person approves price, delivery and terms.
AI & Machine Learning
Your best leads arrive at 9 pm: an AI intake agent that answers, qualifies and routes them before morning
A request that lands after hours or in a shared inbox goes to whoever replies first. An intake agent reads it in any channel, checks your CRM, asks what is missing, scores it against your rules and hands a ready summary to the right person, while anything that commits the company waits for a human.
Python
Python 3.10 reached end of life on 1 October: a dependency-first upgrade plan for production services
Python 3.10 stopped getting fixes with 3.10.22 on 1 October 2026, and AWS deprecated the python3.10 Lambda runtime on 31 October. Bump dependencies first while you are still on 3.10, target 3.13 or 3.14, and move one service at a time behind a CI matrix.