Enterprise language model platform
How to use
AI21 Studio.
Building and operating language applications with AI21's Jamba models, including long-context chat, structured output, classification, summarization, extraction, and enterprise workflows.
AI21 Studio is a developer platform for Jamba language models, chat completions, structured generation, reasoning, document processing, and enterprise AI applications. Building and operating language applications with AI21's Jamba models, including long-context chat, structured output, classification, summarization, extraction, and enterprise workflows. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.
AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.
Access & setup
Find, install, and sign in to AI21 Studio
Get into the official AI21 Studio experience with the right account and a setup you understand.
- 01
Start at https://studio.ai21.com/ and confirm the domain before entering account or payment information.
- 02
Availability: AI21 Studio is managed in a browser and its models are accessed from server applications through REST APIs, Python and TypeScript SDKs, or supported cloud and private deployment options.
- 03
An AI21 Studio workspace and API key, server-side secret storage, billing and rate-limit capacity, an approved deployment region and data policy, representative evaluations, application safety controls, monitoring, and a rollback owner.
- 04
Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.
- 05
Run one low-risk test task before connecting sensitive files, repositories, or workspace data.
- Use official download pages.
- Review permissions during setup.
- Keep installers and applications updated.
First session
Your first useful AI21 Studio session
Learn the interaction loop using a small task with a clear outcome.
- 01
Define one bounded language task, intended users, input data classes, output schema, quality and safety thresholds, latency, throughput, cost, retention, deployment, and rollback requirements.
- 02
Create a dedicated workspace key, keep it server-side, select the smallest current Jamba model that can meet the task, and record the exact model, endpoint, context, rate, and regional constraints.
- 03
Build a frozen evaluation set and make a minimal SDK request with explicit system instructions, output limits, deterministic parsing, timeouts, retries, and request-level telemetry that excludes content.
- 04
Compare quality, safety, latency, errors, and total task cost, then canary the selected configuration with quotas, human review for consequential outputs, and a tested fallback.
- State the outcome before the background.
- Provide the real source material.
- Review the result before expanding the task.
Quality control
Check the quality of AI21 Studio output
Turn generated code into a change you would put your name on in review.
- 01
Restate the intended behaviour and the acceptance criteria before reading a single generated line.
- 02
Read the diff rather than the chat summary; the summary describes intent, the diff describes what actually changed.
- 03
Run the test suite, then write a test that would fail if the change were wrong, and confirm it passes for the right reason.
- 04
Check the edges the model tends to skip: error paths, null and empty cases, concurrency, and migration or rollback behaviour.
- 05
Trace every new dependency, network call, and file write, and confirm each one is genuinely required.
- Review the diff, never the description of the diff.
- A passing test suite proves the tests pass, not that the change is correct.
- Keep changes small enough that a human can actually review them.
Privacy & permissions
Use AI21 Studio safely
Give the tool enough repository access to help, and no more than that.
- 01
Decide what the tool may read and what it may write before connecting a repository.
- 02
Scope tokens and integrations to the narrowest repository, branch, and permission set that still works.
- 03
Keep secrets out of the context window: use environment variables and secret stores, never inline credentials.
- 04
Require review before generated code touches authentication, payments, permissions, migrations, or deletion paths.
- 05
Audit what the integration retained after the session, and revoke access that is no longer needed.
- Model output can be wrong, incomplete, unsafe, or structurally invalid, and limits differ between AI21 Studio, cloud partners, and private deployments. AI21's terms restrict personal and sensitive data unless specifically approved, place responsibility for lawful customer content on the customer, and say not to treat the service as an archive. Keep keys server-side, minimize data, verify the applicable agreement and deployment, pin and evaluate configurations, validate structured output, and keep consequential decisions human-controlled.
- Follow your organisation's approved-use policy.
- Never treat fluent output as authorization to act.
Core workflows
Step-by-step ways to use AI21 Studio for the work it does best.
Each workflow is a separate guide with its own steps and review checkpoints.
Select an exact Jamba model and API configuration through representative quality, safety, latency, limit, and cost evidence rather than a few successful prompts.
↗ 02 WorkflowBuild a governed long-document workflow with AI21Turn approved long documents into structured, cited outputs while preserving permissions, provenance, omission detection, and human release control.
↗Official references
Check the current product documentation.
Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.