Skip to content
Stop Token

Stack chooser

Your AI stack, not the vendor's.

Fifteen layers in six blocks. You need the ones your problems light up.

Six facts pick the tools and price them. Nothing is sent.

An express draft. For the full one: AI of Common Sense · book a call

Six facts about you

Fill them in and the stack appears below. Name a platform and it gets a second column: the same layers, in that platform's own services, with their own price.

Who will run it
Data may live
Asked forpick any
Where you areone
Your platformone
Lean towardsoptional

Nothing stored, nothing sent.

Your recommended AI stack

Appears once the brief has who runs it, where data lives, what you are asked for, where you are, your platform.

  1. Model01Model
  2. Context02System prompt
  3. 03Knowledge base
  4. 04Semantic layer
  5. 05Data quality
  6. Agent06Harness
  7. 07Memory
  8. 08MCP & skills hub
  9. 09Channel + handoff
  10. Access10Identity + access
  11. 11Filter
  12. Run & Cost12Gateway
  13. Control13Traces
  14. 14Evals
  15. 15Feedback

The whole catalogue

Every tool, by layer and by what kind of thing it is. Once the brief is in, your picks light up here. The stage under each layer is the order from the article: pilot, production, scale.

  • open source
  • $ vendors
  • $$ high price vendor
  • first choice in its layer
  1. Model

    01Model

    Writes the answer: a hosted API, or open weights on an inference server you run.

    Stage 1: pilot

    hosted API

    • Anthropic APIFirst choice in this layer$$ vendors↗Hosted frontier models
    • OpenAI APIFirst choice in this layer$$ vendors↗Hosted frontier models
    • Amazon Bedrock models$$ vendors↗Models in AWS · AWS
    • Azure OpenAI$$ vendors↗OpenAI models in Azure · Azure
    • Cortex AI models$$$$ high price vendor↗Models in Snowflake · Snowflake
    • Gemini API$$ vendors↗Hosted frontier models · Google Cloud
    • Alibaba Cloud Model Studio$$ vendors↗Hosted Qwen
    • Cohere$$ vendors↗Enterprise models and rerank
    • Databricks Model Serving$$$$ high price vendor↗Inference · Databricks
    • DeepSeek API$$ vendors↗Hosted DeepSeek
    • Fireworks$$ vendorsModel cloud
    • Groq$$ vendorsFast inference
    • Mistral$$ vendors↗EU hosted models
    • Modal$$ vendorsGPU compute
    • Together$$ vendorsModel cloud
    • Baseten$$ vendorsModel serving

    open weights

    • Qwen (Alibaba)First choice in this layeropen source↗Open weights, frontier-class
    • DeepSeekopen source↗Open weights, reasoning
    • GLM (Zhipu / Z.ai)open source↗Open weights, agents and coding
    • Kimi K2 (Moonshot)open source↗Open weights, long context
    • gpt-oss (OpenAI)open source↗Open weights from OpenAI
    • Gemma (Google)open source↗Open weights, small
    • Llama (Meta)open source↗Open weights, the ecosystem default
    • MiniMax M-seriesopen source↗Open weights, efficient
    • Mistral open weightsopen source↗Open weights, EU

    inference server

    • vLLMFirst choice in this layeropen sourceInference server
    • Ollamaopen sourceLocal models
    • SGLangopen sourceInference server
  2. Context

    02System prompt

    The role and the limits, versioned and tested like code.

    Stage 1: pilot

    prompt management

    • Prompts in gitopen sourcePrompts as code
    • PromptLayer$$ vendors↗Prompt management
  3. 03Knowledge base

    Documents, the data catalogue and the links between them, searched within the user's rights.

    Stage 1: pilot

    document parsing

    • DoclingFirst choice in this layeropen source↗Document parsing
    • Azure Document Intelligence$$ vendors↗Parsing in Azure · Azure
    • Unstructuredopen source↗Document ETL
    • Amazon Textract$$ vendors↗Parsing in AWS · AWS
    • Document AI$$ vendors↗Parsing in GCP · Google Cloud
    • LlamaParse$$ vendors↗Hosted parsing

    retrieval

    • pgvectorFirst choice in this layeropen sourcePostgres vectors
    • Cortex Search$$$$ high price vendor↗Retrieval in Snowflake · Snowflake
    • Databricks Vector Search$$ vendors↗Retrieval in Databricks · Databricks
    • Qdrantopen sourceVector database
    • Vertex AI Search$$ vendors↗Retrieval in GCP · Google Cloud
    • Azure AI Search$$$$ high price vendor↗Enterprise search · Azure
    • Bedrock Knowledge Bases$$$$ high price vendor↗Managed RAG · AWS
    • BigQuery$$$$ high price vendor↗Knowledge base · Google Cloud
    • Chromaopen sourceEmbedded vectors
    • Elasticsearchopen sourceSearch engine
    • LanceDBopen sourceColumnar vectors
    • OpenSearchopen source↗Search engine
    • Pinecone$$ vendorsManaged vectors
    • Weaviateopen sourceVector database
    • Turbopuffer$$ vendorsObject-store vectors

    retrieval framework

    • LlamaIndexFirst choice in this layeropen source↗Data agents and RAG
    • Haystackopen sourcePipeline RAG

    data catalogue

    • DataHubopen source↗Open data catalogue
    • Atlan$$$$ high price vendor↗Hosted data catalogue
    • Dataplex$$ vendors↗Data governance in GCP · Google Cloud
    • Microsoft Purview$$$$ high price vendor↗Data governance in Azure · Azure
    • Unity Catalog$$$$ high price vendor↗Governed data · Databricks

    knowledge graph

    • Neo4jFirst choice in this layeropen source↗Graph database
    • Cogneeopen sourceMemory pipelines
    • LightRAGopen source↗Graph-augmented retrieval
    • Microsoft GraphRAGopen source↗GraphRAG pipeline · Azure
  4. 04Semantic layer

    One definition of each metric and entity, and questions answered over it rather than over raw tables.

    Stage 3: scale

    metric layer

    • CubeFirst choice in this layeropen source↗Semantic layer
    • Fabric and Power BI semantic models$$ vendors↗Metrics in Microsoft · Azure
    • Snowflake Semantic Views$$$$ high price vendor↗Metrics in the warehouse · Snowflake
    • Unity Catalog metric views$$ vendors↗Metrics in Databricks · Databricks
    • dbt Semantic Layer$$ vendors↗Metrics on dbt
    • Looker (LookML)$$$$ high price vendor↗Metrics in GCP · Google Cloud
    • Power BI semantic model$$ vendors↗Metrics in Microsoft · Azure

    questions over the model

    • AI/BI Genie$$ vendors↗Questions over the lakehouse · Databricks
    • Cortex Analyst$$$$ high price vendor↗Questions over semantic views · Snowflake
    • Wren AIopen source↗Text-to-SQL on a semantic model
    • Amazon Q in QuickSight$$ vendors↗Questions over QuickSight · AWS
    • Copilot in Power BI$$ vendors↗Questions over Power BI · Azure
    • Gemini in Looker$$$$ high price vendor↗Questions over LookML · Google Cloud
    • Vannaopen source↗Text-to-SQL
  5. 05Data quality

    Says whether the tables behind an answer can be trusted today.

    Stage 3: scale

    checks as code

    • Sodaopen source↗Data quality checks
    • AWS Glue Data Quality$$ vendors↗Data quality in AWS · AWS
    • Elementaryopen source↗dbt observability
    • Great Expectationsopen source↗Data contracts
    • Horizon data metric functions$$$$ high price vendor↗Data quality in Snowflake · Snowflake

    data observability

    • Monte Carlo$$$$ high price vendor↗Data observability
    • Lakehouse Monitoring$$ vendors↗Data quality in Databricks · Databricks
  6. Agent

    06Harness

    Runs the loop: the plan, the calls, the limits, the point where a person signs off.

    Stage 1: pilot

    agent framework

    • LangGraphFirst choice in this layeropen source↗Graph orchestrator
    • Microsoft Agent Frameworkopen source↗Enterprise agents · Azure
    • OpenAI Agents SDKopen source↗Handoff orchestration
    • Pydantic AIopen sourceTyped agents
    • CrewAIopen source↗Role crews
    • Google ADKopen source↗Graph workflows · Google Cloud
    • Gooseopen source↗Local coding agent
    • Mastraopen sourceTypeScript agents
    • Strands Agentsopen source↗AWS-native SDK · AWS
    • Agnoopen sourceLightweight agents
    • Hermes Agentopen source↗Reference runtime
    • LangChainopen sourceChain toolkit
    • OpenClawopen source↗Personal agent gateway
    • Microsoft AutoGenopen source↗Group chat · Azure
    • Semantic Kernelopen source↗Plugins and processes · Azure

    durable workflows

    • TemporalFirst choice in this layeropen source↗Durable workflows
    • Hatchetopen source↗Postgres workflows
    • Inngestopen source↗Event-driven steps
    • Restateopen sourceDurable handlers
    • Trigger.devopen source↗TS background jobs
    • AWS Lambda$$ vendors↗Action runtime · AWS
    • DBOSopen sourcePostgres durability

    managed agent platform

    • Microsoft FoundryFirst choice in this layer$$$$ high price vendor↗Microsoft agent service · Azure
    • Amazon Bedrock AgentCore$$$$ high price vendor↗AWS managed agents · AWS
    • Databricks Agent Bricks$$$$ high price vendor↗Lakehouse agents · Databricks
    • Gemini Enterprise Agent Platform$$$$ high price vendor↗GCP agent platform · Google Cloud
    • Snowflake Cortex Agents$$$$ high price vendor↗Warehouse agents · Snowflake
    • Salesforce Agentforce$$$$ high price vendorCRM agents · salesforce
    • Agynopen source↗Agent runtime control

    low-code builder

    • Difyopen source↗Low-code platform
    • n8nopen sourceWorkflow automation
    • Langflowopen source↗Visual builder
  7. 07Memory

    Remembers the conversation and the customer between sessions.

    Stage 2: production

    memory API

    • Mem0open source↗Memory API
    • Letta Codeopen source↗Stateful agents

    temporal memory graph

    • Zep / Graphitiopen source↗Temporal knowledge graph
  8. 08MCP & skills hub

    Tools, skills and sandboxes from one catalogue: what the agent can do, and where its code runs.

    Stage 1: pilot

    tool protocol

    • MCPFirst choice in this layeropen source↗Tool protocol
    • A2Aopen source↗Agent-to-agent

    MCP gateway and registry

    • MCP Registryopen source↗Server registry
    • Archestra.aiopen source↗MCP gateway
    • Docker MCP Toolkitopen source↗Containerised MCP
    • MetaMCPopen source↗MCP aggregator
    • Smithery$$ vendorsMCP registry

    skills

    • Agent SkillsFirst choice in this layeropen source↗Skill format

    servers over your data

    • Databricks managed MCP servers$$ vendors↗MCP over the lakehouse · Databricks
    • MCP Toolbox for Databasesopen source↗MCP over GCP data · Google Cloud
    • Snowflake$$$$ high price vendor↗Warehouse · Snowflake
    • dbtopen source↗Transformation
    • ClickHouseopen source↗OLAP analytics
    • PostgreSQLopen sourceRelational DB

    servers over your systems

    • AWS MCP serversopen source↗MCP over AWS · AWS
    • Azure MCP Serveropen source↗MCP over Azure · Azure
    • GitHubopen source↗Code and issues
    • Playwrightopen source↗Browser control
    • Composio$$ vendorsTool catalogue
    • GitLabopen source↗DevSecOps
    • Linear$$ vendors↗Issue tracking
    • Notionopen source↗Docs and databases
    • Sentryopen source↗Error tracking
    • Slack$$ vendors↗Team messaging
    • Stripeopen source↗Payments
    • Vaultopen source↗Secrets MCP
    • Nextcloudopen source↗Self-hosted files

    code sandbox

    • AgentCore Code Interpreter$$ vendors↗Sandbox in AWS · AWS
    • Azure Container Apps dynamic sessions$$ vendors↗Sandbox in Azure · Azure
    • E2Bopen source↗Code sandbox
    • Daytonaopen sourceDev sandboxes
  9. 09Channel + handoff

    Where people talk to it, and how a hard case reaches a person.

    Stage 1: pilot

    staff chat

    • LibreChatFirst choice in this layeropen source↗Multi-provider chat UI
    • Microsoft Copilot Studio$$$$ high price vendor↗Low-code agents in M365 · Azure
    • Open WebUIopen sourceSelf-host chat UI
    • Amazon Q Business$$$$ high price vendor↗Chat in AWS · AWS
    • Gemini Enterprise$$$$ high price vendor↗Chat in GCP · Google Cloud
    • Snowflake Intelligence$$$$ high price vendor↗Chat in Snowflake · Snowflake

    customer channel and handoff

    • Intercom Fin$$ vendors↗Customer AI agent
    • Zendesk AI agents$$$$ high price vendor↗Customer AI agent
  10. Access

    10Identity + access

    Acts on the user's behalf or under its own identity, with the right permissions and secrets.

    Stage 2: production

    on the user's behalf

    • Auth0 for AI Agents$$ vendors↗Agent auth
    • Descope$$ vendorsAgentic identity
    • WorkOS$$ vendorsEnterprise auth

    agent identity

    • AgentCore Identity$$ vendors↗Agent identity in AWS · AWS
    • Microsoft Entra Agent ID$$ vendors↗Agent identity in Azure · Azure
    • Okta for AI Agents$$$$ high price vendor↗Agent IAM

    fine-grained authorisation

    • OpenFGAopen source↗Relationship-based authorisation
    • Cerbosopen sourceAuthorisation
    • OPAopen source↗Policy engine

    secrets

    • OpenBaoFirst choice in this layeropen source↗Secrets
    • AWS Secrets Manager$$ vendors↗Secrets in AWS · AWS
    • Azure Key Vault$$ vendors↗Secrets in Azure · Azure
    • Infisicalopen sourceSecrets platform
    • Secret Manager$$ vendors↗Secrets in GCP · Google Cloud
    • Databricks secrets$$ vendors↗Secrets in Databricks · Databricks
    • Doppler$$ vendors↗Managed secrets
    • HashiCorp Vault$$$$ high price vendor↗Secrets
    • AWS IAM$$ vendors↗Cloud IAM · AWS
  11. 11Filter

    Catches prompt injection on the way in and checks answers on the way out.

    Stage 1: pilot

    injection guard

    • Azure AI Content Safety$$ vendors↗Guardrails in Azure · Azure
    • Bedrock Guardrails$$ vendors↗Guardrails in AWS · AWS
    • Lakera (Check Point)$$$$ high price vendor↗Prompt injection filter
    • Model Armor$$ vendors↗Guardrails in GCP · Google Cloud
    • NeMo Guardrailsopen source↗Programmable rails
    • Cisco AI Defense$$$$ high price vendor↗AI firewall
    • Cortex Guard$$$$ high price vendor↗Guardrails in Snowflake · Snowflake
    • LLM Guardopen source↗Input and output scanners
    • Palo Alto Prisma AIRS$$$$ high price vendor↗AI runtime security
    • HiddenLayer$$$$ high price vendorModel security
    • Zenity$$$$ high price vendorAgent posture

    output validation

    • Guardrails AIopen sourceOutput validation
    • Llama Guardopen sourceSafety classifier
  12. Run & Cost

    12Gateway

    One door for every model call: masks personal data before it leaves, keys and budgets, a fallback when a provider fails, a cache that respects rights, routing by price and quality, a log of every call.

    Stage 1: pilot

    model proxy

    • LiteLLMFirst choice in this layeropen source↗Model proxy
    • AgentCore Gateway$$ vendors↗Gateway in AWS · AWS
    • Azure API Management AI gateway$$ vendors↗Gateway in Azure · Azure
    • Mosaic AI Gateway$$ vendors↗Gateway in Databricks · Databricks
    • Portkeyopen sourceAI gateway
    • Apigee$$$$ high price vendor↗Gateway in GCP · Google Cloud
    • Kong AI Gateway$$$$ high price vendorAPI gateway

    router

    • OpenRouter$$ vendorsModel router
    • RouteLLMopen source↗Cost-based routing

    cache

    • Cloudflare AI Gateway$$ vendorsEdge gateway

    personal data masking

    • Presidioopen source↗PII detection and masking
    • AI Gateway guardrails$$ vendors↗Guardrails in Databricks · Databricks
  13. Control

    13Traces

    Records every step the system took.

    Stage 1: pilot

    tracing

    • LangfuseFirst choice in this layeropen source↗Traces and prompts
    • Arize Phoenixopen sourceOpen tracing
    • LangSmith$$ vendorsHosted tracing
    • MLflowopen source↗ML lifecycle · Databricks
    • Opikopen sourceTraces and evals
    • W&B Weave$$ vendorsExperiment tracking
    • CloudWatch$$ vendors↗AWS observability · AWS
  14. 14Evals

    Tests every change against a set of reference questions.

    Stage 1: pilot

    CI evals

    • Promptfooopen source↗CI evals
    • DeepEvalopen sourceTest-style evals

    RAG evals

    • Ragasopen source↗RAG evals

    eval platform

    • Bedrock Evaluations and CloudWatch$$ vendors↗Evals in AWS · AWS
    • Foundry evaluations and observability$$ vendors↗Evals in Azure · Azure
    • MLflow agent evaluation$$ vendors↗Evals in Databricks · Databricks
    • Vertex AI Evaluation$$ vendors↗Evals in GCP · Google Cloud
    • Braintrust$$ vendorsEval platform
    • Cortex AI Observability$$$$ high price vendor↗Evals in Snowflake · Snowflake
  15. 15Feedback

    Turns bad answers from real users into tests and fixes.

    Stage 3: scale

    labelling

    • Argillaopen source↗Feedback and labelling

Questions

What is an AI stack?
The fifteen layers a working AI system is assembled from, in six blocks: model, context, agent, access, cost and control. Most companies need some of them, and the ones you do not need are the expensive part of the answer.
What does an AI stack cost to run?
Licences, hosting and people, per month in dollars, for the tools your six facts pick. These are the tools' own prices; building the layers is a separate cost. Naming a platform adds a second column priced in that platform's own services.
How does this relate to the article on the fifteen layers?
Same layers, same numbers, same order. The article says what each layer does, what breaks without it and what building it costs; the chooser says which tool to put in it and what that tool costs a month.
Build or buy?
Asked per layer, not per stack. The chooser names a tool for each layer you need and dims the ones you do not, so the question only comes up where it changes something.
Can it run without a cloud?
Say so in the sixth fact — data may live on our own servers — and the chooser picks from what can run there, with the price that follows.