A reference architecture here shows the lanes and components of a real build. It lists what the build costs. It says what breaks if a piece goes missing.
Patterns and failure modes on this site work at component level. Each one covers one decision and one thing that breaks. A reference architecture is the level above. It is the whole system a buyer asks for. It joins several of those components. It adds the cost shape and the security posture. Pick the one that matches what you would say if someone asked what you need built.
Answer questions from your own documents and cite the source. The model does not answer from its training data.
“We want a search box or chatbot that answers from our own docs. It must show where each answer came from.”
Read the architecture →An agent that works a queue of cases end to end. It runs in a bounded loop. A human checkpoint covers any action it cannot cleanly undo.
“We have a queue our team processes by hand, and we want an agent to work through it without babysitting every case.”
Read the architecture →Turn inbound documents into structured records. A person reviews only the cases where the model is unsure.
“We get PDFs, forms, or emails. Someone keys the data into our system by hand. Can software read them for us?”
Read the architecture →An assistant embedded in a product you already ship. It is scoped to the signed-in user's own data and permissions.
“Our users keep asking support the same questions. They could answer them alone if the product told them.”
Read the architecture →One call site in front of every model provider. A price change or an outage becomes a config change.
“We call one provider's SDK directly from a dozen places. We want to switch or split traffic without touching all of them.”
Read the architecture →A control plane for running many coding agents at once. The agents do not collide on the same files. You can see what each one costs.
“We already run several coding agents. It has turned into a wall of terminal tabs. We have no idea what it costs.”
Read the architecture →Start from the sentence a stakeholder would say. "Answer questions from our own docs" is grounded answering. "We have a queue we process by hand" is the workflow runner. "Someone keys data in from documents all day" is extraction. "Users ask support what the product could tell them" is the copilot. "We're stuck on one model provider" is the gateway. "We're running agents and losing track of them" is the delivery fleet. Some systems are two of these at once. A copilot that also extracts from an upload is one example. Read both pages and combine the parts that apply.
Or skip the self-diagnosis. The Architecture Picker turns these same questions into a scored primary and a likely bolt-on. It takes about a minute.
What a reference architecture means on this site, and how to use one.
A named system shape that we have built more than once. It lists the lanes and nodes the system runs through. It names the components that break something specific if you remove them. It covers the build-versus-buy calls and the cost to run.
Link to this answer: What exactly counts as "a reference architecture" here?Start from the sentence you would say out loud. "We want to answer questions from our own docs" is grounded answering. "We have a queue we process by hand" is the workflow runner. "Someone keys data from documents by hand" is extraction. "Our users ask support what the product could tell them" is the copilot. "We are locked into one model provider" is the gateway. "We run agents and lose track of them" is the delivery fleet. Most real projects are one of these plus a second one. Few are entirely new.
Link to this answer: How do I pick which one applies to us?No. They sit one level above it. A pattern like bounded agent loop or typed tool contractA tool contract is the schema a tool exposes to a model. is a component-level decision. A reference architecture is the whole system that those components form. It adds the cost shape, the build-versus-buy calls, and the security posture. Those make sense only when you see the whole system.
Link to this answer: Do these replace the patterns library?We would cite them as examples of the pattern anyway. CostMon and CodeHerder are our own answers to the cost-telemetry and fleet-control problems in the model gateway and delivery fleet architectures. We offer them as one option among several.
Link to this answer: Why do two of these mention your own products?Most production systems are. A copilot that also extracts data from an uploaded document is both. Read both pages. Take the components and build-versus-buy calls that apply from each. Use the "not for you if" sections to filter out the parts that do not apply.
Link to this answer: What if our system is a mix of two of these?A Ship Audit checks which of these your system needs. It also checks which parts of your build already have them. You then commit budget to the rest.
Source: https://customlabs.io/architectures/