Build AI into your SaaS
Ship AI features without building the AI platform first.
Codapult gives your product one production path for chat, agents, tools, retrieval, guardrails, model routing and usage-aware operations.
One gateway · Provider control · Production metering
ai-request.trace
One execution path
Request
A shared gateway for AI requests
Chat, agents, batch jobs and RAG enter one server-side execution path.
$ chat · agents · batch · RAG
One execution path
Build every AI workflow on the same foundation.
Start with a chat response. Grow into agents, tools, retrieval and asynchronous work without creating a second AI architecture for every feature.
Chat and streaming
Ship responsive AI experiences with persisted conversations and one gateway.
Agents and tools
Let models call product logic through typed, permission-aware tools.
RAG and embeddings
Bring tenant-scoped knowledge into requests when retrieval is enabled.
Gateway policies
Configure validation, organization access and guardrails where interactive requests enter the system.
Metering and budgets
See tokens, cost, latency and organization usage before surprises reach production.
Playground and batch
Compare prompts and models, then move repeatable work into asynchronous jobs.
AI inside the product
From first prompt to a feature your customers can trust.
The dashboard gives your team a real surface to configure prompts, agents, models, guardrails and usage — while the gateway keeps runtime behavior consistent.
Model catalogue with explicit IDs
Organization-aware quotas and metering
Playground before production release
Codapult workspacecodapult.app
Tenant-scoped retrieval
RAG when your product needs it.
Add retrieval and embeddings with explicit provider, tenant and usage boundaries.
Opt-in
RAG stays off until you configure the providers and enable it.
Tenant-scoped
Documents and search results stay inside the active organization.
Measurable
Limits for documents, chunks, scores and batches remain explicit.
Production controls
AI features with a runtime you can inspect.
The value is not only the model response. It is the gateway, boundaries and operational context around every feature you ship.
One gateway for multiple surfaces
Chat, agents, batch jobs and the playground use the same model gateway and response contract.
Context with boundaries
Tools, guardrails and optional retrieval can use organization-aware context instead of treating every request as global.
Operations stay visible
Usage, tokens, cost, latency, budgets and request outcomes remain available for product decisions and production debugging.
Fits the stack and AI coding tools your team already uses.
Next.js 16
TypeScript
PostgreSQL
Turso
Drizzle ORM
Tailwind CSS
shadcn/ui
Better Auth
Resend
tRPC v11
TanStack
Stripe
Lemon Squeezy
Vercel
Claude Code
Cursor
Codex
Windsurf
Gemini
VS Code
Make AI part of the product, not a separate experiment.
Build on a foundation where models can change, workflows can grow and your product team stays in control.