AI Development
AI features inside real software
Code Sage Labs builds AI features into real software from Colombo, Sri Lanka: assistants and chatbots that answer from your own documents, document extraction and classification, and automation of repetitive work with a person reviewing the result. We use hosted models from OpenAI and Anthropic, or open-source models where data has to stay in your infrastructure.
What we can build
- Assistants grounded in your documents and data
- Document extraction, classification and summarisation
- AI features inside existing products: search, tagging, drafting
- Workflow automation with human review steps
- Evaluation sets and monitoring so quality is measured, not assumed
Typical projects
- 1.A support assistant that answers from product documentation and hands off to a person when unsure
- 2.Extracting structured data from supplier PDFs into an operations system
- 3.An internal knowledge assistant over policies, procedures and past projects
Relevant technologies
- OpenAI
- Anthropic Claude
- Open-source models
- LangChain
- pgvector
- Python
- FastAPI
What's the refund window for goods damaged in transit?
Fourteen days from delivery, with photos of the damage and the packaging. Claims after that go to the carrier directly.
Returns policy, section 3Carrier terms
Not sure? The assistant hands off to a person.
Offshore software development
Why work with a software team in Sri Lanka
Working hours that overlap yours
We work on Sri Lanka time, UTC+5:30, with no daylight saving. That covers the working day across Asia and the Middle East, mornings in Europe and afternoons in Australia and New Zealand, and we schedule early or late calls for the Americas.
Written down, in English
Scope, decisions and progress are written down in English and kept in your project tools, so you can see where things stand from any time zone without chasing anyone.
Engineers, not account managers
You talk directly to the engineers building your software. Technical questions get technical answers, not a relay through a sales layer.
Scoped before work starts, owned by you after
Fixed-scope projects or ongoing monthly work, agreed in writing before anything starts. You own the source code, infrastructure and deployment pipelines.
Questions
AI Development: common questions
Can an AI assistant answer only from our own documents?
Yes. We ground assistants in your documents and data with retrieval, show where each answer came from, and hand off to a person when the assistant is not sure.
Does our data have to leave our infrastructure?
No. Where data must stay inside your environment we use open-source models you host. Otherwise we use OpenAI or Anthropic under their business terms.
How do you know the AI is giving good answers?
We build evaluation sets from real questions, measure answers against them before release, and keep monitoring quality after launch.