Your team’s prompts deserve their own database, not a code repo.
Versioned templates with Jinja2 variables, A/B testing, AI recommendations, and per-key selection. Ship prompt changes without redeploying — and roll back in one click when they regress.
Active templates
- Versioning
- Every save
- Per-key selection
- extra_body
- A/B variants
- Deterministic
- Prompt logs
- Opt-in
Snapshot + diff + author + timestamp
nemo_prompt_template_id on any request
Hash-routed by request id
Honors org-level data policy
support-agent.jinja2 — every version, one pointer, zero redeploys.
The active-version pointer moves; your code never changes. Roll back from the dashboard in one click when a change regresses.
Initial draft
Authored in the dashboard. Never committed to a repo.
Token-reduction pass
-15% input tokens. Diff reviewed, one-click activated.
Clarity rewrite
activeActive now. Serving every request that references the template.
Draft — A/B candidate
A/B runningRunning 60/40 against v3. Promote or discard from the dashboard.
Test prompts the way you test features
Don’t guess which version is better. Measure it. Split traffic deterministically, capture cost + latency + quality per branch, and promote the winner without a code change.
A/B testing
Deterministic splits, statistical confidence
Create two or more variants with a configurable traffic split. Routing is hash-deterministic per request id, so the same input always lands on the same variant. Per-branch metrics roll up in the analytics dashboard.
- Lifecycle: draft → running → paused → completed
- Per-variant cost, latency, p95, and quality metrics
- Promote the winner from the dashboard without code change
- Stop the test instantly if a variant regresses
Variant performance (last 24h)
Full prompt reference: Jinja2, recommendations, audit, storage
- Jinja2 templates
- Double-brace variables, conditionals, loops, filters, defaults. Values injected per-request via nemo_prompt_variables. Never compiled into code. A linter flags missing variables before activation.
- Version history + rollback
- Every save creates a snapshot with author, timestamp, and diff. Linear version chain with an active-version pointer; activate any version instantly, no redeploy. Soft-delete preserves audit history.
- AI-powered recommendations
- Clarity rewrites with predicted quality lift, token-reduction passes with a -% estimate, passive-voice and ambiguous-role detection. Generated, never auto-applied. One-click apply creates a new version.
- Per-request selection
- Pass nemo_prompt_template_id + nemo_prompt_variables in extra_body on any chat completion — works with the unmodified OpenAI SDK in every language. Stripped from the upstream payload before forwarding.
- Audit trail
- Every save, activation, A/B start, and rollback captured with actor, IP, and full diff. Append-only, filterable, CSV + JSON export for SIEM ingestion — pinned for SOC 2 evidence collection.
- Tenant-isolated storage
- Templates, versions, and variable payloads live in org-scoped rows (nemo.prompt_templates, nemo.prompt_versions) with Row-Level Security. Cross-org reads are impossible at the database layer.
Common prompt questions
How do variables work in a prompt template?
Templates use Jinja2 syntax: double braces wrap variable names, and values are injected at request time via the nemo_prompt_variables field in extra_body. You can use conditionals, loops, filters, and default values. Variables never appear in your source code, so you can change prompts without redeploying.
Can I version prompts and roll back?
Yes. Every save creates a new version with author, timestamp, and diff. Any version can be activated instantly from the dashboard. No redeploy. If a prompt change regresses output quality, roll back to the previous version in one click.
How does A/B testing compare prompts?
Create two or more variants of a prompt and set a traffic split (e.g. 60/40). nRouter routes each request to a variant deterministically and logs the variant, latency, cost, and response quality. Promote the winner when you have statistical confidence.
Is prompt data logged anywhere outside my org?
No. Prompt templates, versions, and variable payloads are stored in your org-scoped Supabase rows with Row-Level Security. Nothing crosses organization boundaries. You control logging granularity per-org via the data policy setting.
Ship without redeploying
Move every prompt out of the codebase — today
Free to start. Versioning, variants, recommendations, and the audit trail are unlocked on every plan from day one.