AI assistants and decision tools for your business.
Choose Cloudflare-powered assistants or a private deployment configured for your organization, with optional fine-tuning.
Sage Cloud is available today. Sage Private is a scoped pilot: each deployment is assessed and validated for your workload before it answers. Retenta does not currently host the custom Sage engine.
Sage Cloud or Sage Private.
Sage Cloud · available
Powered by Cloudflare
Assistants on Cloudflare Workers AI models, paired with your cloud Thyme RAG Capsules. Choose from 25 models by price and capability, and switch at any time.
Sage Private · scoped pilot
Custom cloud or on-prem
Models configured for your organization in a custom cloud deployment or on hardware you own, with optional fine-tuning scoped as a separate project. Where supported, it can use the custom Sage engine.
Inside Sage Private
Private text models · pilot
Assistants that answer in your private deployment
Open models served in your custom cloud or on your own hardware write answers from your private capsules. With private retrieval and a private model, documents and questions are processed inside that deployment. Connect an external model and it receives the passages sent to it.
Custom Sage engine · not yet available
Developer-reported symbolic lookup
According to its developer, the custom Sage engine performs symbolic lookups directly in the model’s forward pass. This capability belongs to the custom engine, not the Cloudflare-powered offering. Private deployments are scoped and validated for your workload. Until its outputs are established, it is offered for structured decision tasks, never as a chat model.
Sage doesn't lock you in.
Each capsule can answer with Sage Cloud, Claude, ChatGPT or a Sage Private model, and you can switch at any time. A private deployment never falls back to the cloud.
Structured decision models, explained
Some newer models return a typed decision instead of free-form text. TypeSafe AI describes its Jev model as a non-autoregressive “System One” model that produces typed probabilistic decisions using parallel sampling, trained with a method it calls RLCD (Reinforcement Learning for Calibrated Decisions).
Retenta is not affiliated with TypeSafe AI, and Sage does not use Jev or share its architecture or training method. The point is the category: when a model returns a decision in a fixed schema, software can check it, route it and ask a person to review it. Typed output can still be wrong, so Sage decisions carry evidence references and a review state, and a person approves anything that matters.
Source: TypeSafe AI, “Introducing System One models and Jev” (September 2026).
Your capsules, with the AI you choose.
A Thyme RAG Capsule does the retrieval. The model you pick writes the answer from the passages it finds. Choose per capsule and switch at any time. Your knowledge stays the same.
Sage Cloud · available
Powered by Cloudflare
Assistants on Cloudflare Workers AI models, on the same network as your capsule. Questions and passages stay on Cloudflare. Pick from 25 models.
Compatible AI
Claude · ChatGPT
Claude from Anthropic or ChatGPT from OpenAI writes the answer. Each question sends that lab the passages retrieved for it, never your whole library.
Sage Private · scoped pilot
Custom cloud or on-prem
Models configured for your organization in a custom cloud deployment or on hardware you own, with optional fine-tuning scoped separately. Each deployment is assessed and validated before it answers.
Managed on Cloudflare, or private on your hardware.
Both use the same capsule format: corpus, manifest and eval set. Moving between them rebuilds only the index.
Cloudflare-hosted · available
Managed by Retenta on Cloudflare
Self-serve and running in minutes. Retrieval is Retenta's own pipeline on Cloudflare: documents in R2, Workers AI embeddings, and a Vectorize index for each capsule.
- Sign up and build today
- Free Developer tier
- Pairs with Sage Cloud, Claude, ChatGPT or any MCP client
Private · scoped per customer
On hardware you own
A custom retrieval deployment on servers you own, scoped to your workload. Retenta can help you buy and install the hardware. Each deployment is assessed, quoted and validated before it goes live.
- Requirements intake, assessment, then a quote
- Hardware purchase and installation facilitated
- Validated on your workload before activation
Tell us about your corpus, tasks and network. A private customer is never enrolled in the cloud by default; a cloud trial is a separate choice.
Start with Sage Cloud today.
Create a capsule, pick a Workers AI model and chat with it from your dashboard. For Sage Private, tell us about your workload.