What is AI Red Teaming?
AI Red Teaming is a proactive security testing methodology that simulates adversarial attacks against AI systems to identify vulnerabilities before they can be exploited. Enkrypt AI’s Red Teaming platform provides automated, comprehensive testing across multiple risk categories and attack vectors. You describe the system you want tested, choose the risks or compliance frameworks you care about, and pick the attack techniques to apply. The platform generates adversarial prompts, runs them against your target, judges the responses, and returns a scored report.How a run works
Every red team submission is asynchronous. You post a payload, receive arun_id
immediately, and then poll or stream until the run finishes.
1
Submit
POST /rt/redteam returns 202 Accepted with a run_id, a status_url, a
results_url and a websocket_url.2
Track
Poll
GET /rt/runs/{run_id} for the status, or subscribe to
GET /rt/runs/{run_id}/stream for live events.3
Read results
GET /rt/runs/{run_id}/results returns the scored summary — attack success rate
overall, per risk category, per sub-category and per attack method.4
Drill in
GET /rt/runs/{run_id}/records returns the individual prompt/response/verdict rows,
and GET /rt/runs/{run_id}/compliance/{framework_id} maps results onto a compliance
framework.Queued, Running, Finished or Failed.
Key concepts
Target
The system under test — an endpoint, an API key and a model name, plus its
system_type (foundation_model, chatbot or agent) and its modalities.Scope
What to test for. Either risk categories (8 categories, 35 sub-categories) or
compliance frameworks (6 supported). Exactly one of the two, never both.
Attacks
How to test. 21 attack techniques spanning plain baselines, evasion transforms and
adaptive multi-turn jailbreaks, configured per risk category.
Run
One asynchronous job, identified by
run_id, with a status, a scored summary and a
row-level record set.Scope: risk categories or compliance frameworks
risk_categories and compliance_frameworks are mutually exclusive — supply
exactly one. Supplying both, or neither, is rejected with a validation error.
Pick risk_categories when you know which risks matter for your system. Pick
compliance_frameworks when you want coverage expressed against a published standard;
the platform expands the framework into the categories and sub-categories its controls
map onto.
See the Risk Category Catalog for the full list.
System types
target.system_type tells the platform what kind of system it is probing, which
changes both the prompts generated and the judges applied.
See the Agent Testing Guide for agent-specific
configuration.
The four entry points
Red teaming is the main flow, but three related endpoints share the same vocabulary.Red Team
POST /rt/redteam — generate adversarial prompts, run them against a target, and score
the responses. The full pipeline.Threat Modeling
POST /rt/threat-modeling — generate a dataset only. No target, no attacks. Useful for
reviewing prompts before spending a run on them.Playground
POST /rt/playground — probe a single goal against a target with chosen attacks. No
category scaffolding, no dataset generation.Eval
POST /rt/eval — score prompt/response pairs you already have. Bring your own
transcripts and get verdicts back.Getting Started
1
Run your first test
Submit a red team run and read the report.Go to Quickstart →
2
Learn the payload
Understand the four blocks every payload is built from.Payload Guide →
3
Choose what to test for
Browse the risk categories and sub-categories, and the compliance frameworks they map to.
4
Choose how to test
Pick from the 21 attack techniques.Attack Methods Reference →
5
Reference every field
Field-by-field detail for every block of the payload.Configuration Reference →
6
Copy an example
Ready-to-run payloads for common scenarios.Browse Examples →
7
Coming from the previous API?
Map the old tests, attacks, and endpoints onto
/rt.What’s New →Multi-modal testing
Targets declareinput_modalities and output_modalities. Attack techniques are
modality-specific — image attacks require an image-capable target, audio attacks an
audio-capable one. The Attack Methods Reference
lists which techniques apply to which modality.
Related
API Reference
Complete request and response schemas for every Red Team endpoint.
Python SDK
RedTeamClient wraps every endpoint documented here.Testing across providers
Target configuration for OpenAI, Anthropic, Bedrock, Gemini, Azure and more.
Credits & pricing
How Red Team runs are priced from the scope you submit.
What's new
What the Red Team revamp changed: endpoints, fields, tests, and attacks.