RAG chatbots for customers
Website or in-app chat that answers from your help center, catalog and policies, cites the article and hands off to support when it should.
LLM and RAG development for assistants that answer from your documents
We build retrieval-augmented generation (RAG) systems and LLM applications that search your policies, contracts, manuals and records, answer in plain English and show the passage behind every claim. When the documents don’t cover a question, the assistant says so and passes it to a person.
Free consultation
Tell us what you want to automate. An engineer will read it and reach out to set up a free consultation.
A RAG system answers in two moves. First it searches your content for the passages that matter, then the language model writes the answer from those passages only. In this illustrative example, a tenant of a Denver property management company asks about the pet policy, and every sentence of the reply points to its source.
Illustrative example Fictional business, people and data. Not a real client, conversation or result.
Most of the answer quality gets decided before the model writes a word. If retrieval brings back the wrong passage, the best model in the world will still get it wrong. That’s why most of our RAG development time goes into the first four steps.
We connect the sources (shared drives, wikis, help centers, databases), remove duplicates and outdated versions, and record who’s allowed to see each document.
We split documents into passages that keep headings, tables and section numbers intact, and tag them with metadata like date, product or location.
Each passage becomes a vector stored in a vector database, alongside a keyword index, so the system can match both meaning and exact terms.
At question time, hybrid search finds candidate passages, a reranker puts them in order and permission filters drop anything the user isn’t allowed to see.
The model writes the answer only from the retrieved passages, cites each one and says “I don’t know” when they don’t contain the answer.
Questions, passages and answers are logged and scored against a test set, so any change to any step gets measured before it ships.
Use RAG when the model needs to know your facts. Use fine-tuning when it needs to learn a format, tone or narrow task it keeps getting wrong. Use a well-written prompt alone when the knowledge fits in the instructions. Most production systems are RAG plus good prompting. Fine-tuning is the exception, and we add it only when the evaluation shows it helps.
General comparison. These techniques are often combined. For the longer version, see our blog article on RAG vs fine-tuning.
Our LLM application development covers six kinds of systems. Most clients start with one assistant over one set of documents, then add sources and channels once the answers hold up.
Website or in-app chat that answers from your help center, catalog and policies, cites the article and hands off to support when it should.
An internal assistant for staff in Slack, Teams or a web app that answers from SOPs, HR policies and past tickets.
Ask questions across contracts, reports or technical manuals and get answers with the clause, page or section linked.
Pull fields, dates and obligations out of long documents into your database, with the source passage stored next to each value.
When evaluation shows a base model can’t hold a format or a narrow task, we fine-tune on curated examples and test it against the baseline.
Your knowledge base or product exposed as a Model Context Protocol server, so AI assistants can search it and call its tools with scoped access.
MCP server development: MCP serversThese terms come up in every RAG conversation. Here’s what each one means for your project, in plain English.
A vector database stores each passage of your content as a list of numbers (an embedding) that captures its meaning, so the system can find passages about “canceling a lease early” even when the document says “early termination.” It works alongside a keyword index, because exact terms like SKUs, policy numbers and names still matter.
Before anything gets embedded, documents are split into passages. Split a table in half or separate a rule from its exception, and retrieval will hand the model half the truth. We chunk by structure (headings, sections, rows) and test several strategies against your questions before choosing one.
Fine-tuning retrains a model on your examples so it reliably produces a specific format, tone or classification. It doesn’t keep the model up to date on your facts, and it costs more to maintain. We recommend it only when a RAG system with good prompts still misses the bar on your evaluation set. Our article on RAG vs fine-tuning goes deeper.
The Model Context Protocol is an open standard for connecting AI assistants to data and tools. An MCP server wraps your knowledge base or system so any compatible assistant can search it or call its functions, with authentication and scopes you control, instead of building a separate integration for each AI tool. More in our guide to the Model Context Protocol.
Enterprise RAG is a RAG system built for many users, many sources and real access rules. The chat window is the easy part. The hard part is making sure a sales rep never gets an answer pulled from an HR file, and that last week’s price change replaces last quarter’s.
We enforce permissions at search time using the access rules of the source system, re-index on a schedule or on change, keep versions so you can see which document an answer came from, and log every question for review. If the assistant also needs to act, like opening a ticket or updating a record, that’s where AI integration with your systems comes in.
RAG development starts with the sources you already have. These are the categories and common tools we work with. We confirm connectors for your specific accounts during scoping.
RAG is only as good as the documents behind it. In these situations, we’ll tell you to fix something else first.
If three versions of the refund policy disagree, the assistant will find all three. Someone has to decide which one is true.
“What was our margin by region last quarter?” is a database query, not a document search. We route those to SQL tools or reports.
If the answer lives in a senior employee’s head, retrieval has nothing to find. Capturing it is step one.
Faded faxes and photos of handwritten notes need OCR and cleanup before anyone can search them, and some never will be searchable.
Clinical, legal or financial determinations stay with qualified people. The assistant can find the passage. It doesn’t make the call.
If everything fits in a few pages, a well-written prompt may do the job without a retrieval pipeline.
Every rule below gets written into the system and covered by the evaluation set, so you can see it hold up before launch.
We prove answer quality on your real questions before anything touches a live channel.
Step 1 of 5
We inventory your documents, find duplicates and gaps, and agree on what the assistant may use.
Deliverable: a source map with owners, access rules and refresh frequency.
Step 2 of 5
Your team gives us real questions and the correct answers. This becomes the evaluation set every version is scored on.
Step 3 of 5
We test chunking, embeddings and search settings until the right passages come back, then add generation and citations.
You see a scored report: which questions pass, which fail and why.
Step 4 of 5
Permissions, re-indexing, guardrails, logging, the user interface or channel, and handoff to your team.
Step 5 of 5
A small group uses it for real work. We review flagged answers every week and add sources or users once it holds up.
The pattern repeats: a pile of documents people search every day, and a real cost when they grab the wrong version. These are examples of what we build, not reported results.
Answers staff questions on insurance, cancellations and visit preparation from the practice’s own policies, with links.
Explains what the office’s written procedures say about a treatment, so staff give patients the same answer every time.
Lets therapists search home-exercise guidance and clinic protocols in plain language, citing the source document.
Answers guest questions about ingredients from the current menu specs, and hands uncertain cases to the manager.
A customer chat that answers from the help center and passes unresolved cases to a support rep, context included.
Search across signed agreements for renewal terms, notice periods and liability caps, with the clause linked.
We build and run AI agents and MCP servers in production, so retrieval, permissions and evaluation are everyday work for us, not experiments.
Every version is scored on your questions. You see pass rates and failures, not a polished demo.
We compare providers on your data and structure the code so the model can change without a rebuild.
Pipeline design, prompts, tests and runbooks, all in writing, from a team headquartered in Austin, Texas, with engineers in Spain.
Custom AI software, LLM and RAG systems, AI integrations and AI SaaS, built by in-house engineers.
Learn moreGenerative AI that drafts, summarizes, extracts and creates on-brand content, with a person approving.
Learn moreAI connected to your CRM, ERP, help desk and product through APIs, webhooks and MCP servers.
Learn moreAI support agents that answer from your docs, act in your systems and hand off to people with context.
Learn moreAn LLM development company builds applications on top of large language models: assistants that answer from your documents, extraction pipelines, chat and search experiences, and the integrations around them. The model usually comes from OpenAI, Anthropic or an open-weight project. The company designs retrieval, prompts, guardrails, evaluation and operations.
A RAG chatbot is a chat assistant that searches your own content before answering and writes the reply from what it found, with the source cited. Unlike a general chatbot, it can answer about your products, policies and procedures, and it can say “I don’t know” when the documents don’t cover the question.
Enterprise RAG is retrieval-augmented generation built for an organization: many sources, many users and real access rules. It adds permission filtering at search time, scheduled re-indexing, version tracking, audit logs and hosting that meets the company’s data requirements.
For knowledge that changes, such as policies, prices or product details, use RAG. It stays current and cites sources. Fine-tuning helps when a model must reliably follow a format, tone or narrow task. Plenty of projects need only RAG and good prompts. We add fine-tuning when the evaluation set shows a clear gain.
Most RAG systems use one, but it doesn’t have to be a separate product. For moderate volumes, a vector extension on a database you already run can be enough. We choose based on the size of your content, hosting rules and cost, and we usually combine vector search with keyword search.
No. RAG is a technique for answering from your documents. An MCP server is a standard way to expose data and tools to AI assistants. They work well together: an MCP server can offer a “search the knowledge base” tool backed by a RAG pipeline, plus other tools such as looking up an order.
Yes, if it’s designed that way from the start. We store each passage with the access rules of its source and filter results by the user’s permissions before the model sees them, so the assistant can’t quote a document the person couldn’t open.
With an evaluation set of real questions and expected answers from your team. We score whether the right passages were retrieved, whether the answer is faithful to them and whether citations are correct, and we rerun the set before every release.
List the documents or systems it should answer from, who’ll use it and where. We’ll get back to you with a recommended approach, what we need from your team and what a first version would include.
Free AI audit
An engineer will review your answers and reach out to walk you through where AI can help most.
Pick the area you want us to look at. We’ll review how it runs today and tell you what to automate first, and what to leave alone.
Free, with no strings attached. An engineer reads your answers before reaching out.
Free consultation
Tell us what you want to automate. An engineer will read it and reach out to set up a free consultation.
Thanks, we got your request
Someone on our team will review it and reach out to schedule your free consultation.