Redfield AB’s cover photo
Redfield AB

Redfield AB

Software Development

Kungsholmen, Stockholm County 1,005 followers

AI should make you more independent - not less. More capable — not more dependent.

About us

We've been doing this for over 20 years. That means we've seen enough projects fail — and succeed — to know the difference. Good planning. The right people. Tools that the people who actually understand the business can use themselves. Most consultancies build for IT departments. We build for the domain experts — the people who know the data, the processes, and the edge cases that no external consultant would ever find. Our job is to give those people tools powerful enough to change how their organisation works, without requiring them to write a single line of code. And when we're done, we leave. That's the point. We've never liked building dependency — it's in the DNA of how we work. We're independent, which means we're not tied to any vendor or platform. We recommend what actually works, not what generates the highest commissions.

Website
http://www.redfield.ai
Industry
Software Development
Company size
2-10 employees
Headquarters
Kungsholmen, Stockholm County
Type
Privately Held
Founded
2004
Specialties
Data warehouse, Business Intelligence, Neo4j, Machine Learning, KNIME, Python, Deep learning, Spark, NLP, Memgraph, Knowledge Graph, Entity resolution, LLM, AI, Elasticsearch, RAG, and GraphRAG

Products

Locations

  • Primary

    Fleminggatan 15

    Kungsholmen, Stockholm County 11226, SE

    Get directions

Employees at Redfield AB

Updates

  • Redfield AB reposted this

    Standard-RAG often struggles with corpus-level understanding. Questions like: "How many times did John visit Sally?" aren't answerable if no specific chunk directly contains that information. GraphRAG solves this by transforming text-data into a structured graph ahead of query time. In other words, we first build up a representation of all entities (names, companies etc.) and their relationships, so that when a user asks a question about something structural in the dataset, the information is there, ready-to-go. I built a small tech-demo that does this for a portion of Epstein files, showing how a dataset can be parsed in advance and uploaded to a graph database (in our case Memgraph) complete with a vector index. With the right setup, this enables us to quickly find information via a chat interface, enabling us to find global-level insights over the full dataset. This experimental version also incorporates other features such as hierarchical community detection, automatically generated community summaries, structured search (cypher), multi-hop search with reranking and more. If you're interested check out the article about how it works in Goose via MCP: https://lnkd.in/dY2_3qj7 P.S. Part 2 with a more detailed explainer on the technical details will be coming soon 😁

  • Redfield AB reposted this

    Entity resolution is one of those problems that looks simple until you actually try it in practice. If you’ve ever tried to match “the same” company across two different datasets, you know how quickly things fall apart. Minor typos, abbreviations, or missing fields turn a "simple join" into a weeks-long cleanup project. This article shows why probabilistic models beat rigid rules for messy data, and how to make it work at scale. https://lnkd.in/dMzhUAeh

Similar pages