AI & Machine Learning
Connect Metatext AI to Your AI Agents
Let your Wkil agents generate text, classify content, extract data, and apply safety guardrails through Metatext AI.
Authentication: API key
What you can do
- Generate and classify text with guardrails
- Extract structured data from text
- Test AI safety with red-team scans
Available capabilities may vary by authentication and workspace configuration.
Actions supported by the connector
Chat Completions
Generate a conversational AI response for a given prompt.
Classify Text
Categorize a piece of text into predefined labels.
Run Extraction
Pull structured data out of unstructured text.
Create Policy Guardrails
Define content-safety guardrail policies for AI output.
Run Red Team Test Scan
Test an AI application against adversarial red-team probes.
Practical agent use cases
- An agent classifies incoming support text before routing it to the right team.
- An agent applies guardrail policies before generating a customer-facing response.
How it works with Wkil
- 1Choose the integrationAdd MetatextAI to your agent from inside the Wkil platform.
- 2Grant the permissions it needsDefine precisely what the agent can access and perform.
- 3Test, then run itTest actions before they go live, with human approval where needed.
Permissions always stay in your control — you can scope access and require human approval before any sensitive action.
Related integrations
FAQ
Can this help enforce content policy automatically?
Yes — guardrail policies can be applied to AI outputs before they reach a user.