Input Requests: Collect Structured Information from External Users
Generate a secure, time-limited access code, send it to anyone outside your organization, and have them submit a structured form — without needing an account.
Read post →Product updates
The Agentwise Blog
Updates from the product, implementation notes, and lessons from building enterprise AI systems that improve with use.
Real-Time Voice & Phone Calling: Configurable AI Voice Conversations
Agents can now handle real-time voice conversations over WebRTC and phone channels — with configurable turn detection, barge-in sensitivity, audio recording, and multiple voice models.
Read post →Entity Extraction & Recognition: Automatic Data Intelligence from Conversations
Agentwise now automatically detects and extracts named entities from your data — people, organizations, locations, IBANs, VAT numbers, and more — powered by Microsoft Presidio and Azure Language Services.
Read post →Liquid Templating for Agent Instructions: Dynamic, Context-Aware Prompts
Agent instructions now support Liquid templating syntax, letting you inject dynamic context — conversation metadata, user fields, or runtime values — directly into your system prompts.
Read post →Terms & Abbreviations Knowledge Base: Build a Living Glossary
Maintain a structured Terms and Abbreviations library, mine abbreviations automatically from imported content, and make your organization's language searchable and consistent.
Read post →Microsoft Teams Integration: Bring Agents Into Your Team Channels
Connect Agentwise agents to Microsoft Teams via webhook bridge — turning any agent into a Teams bot that your team can talk to directly in their channels.
Read post →Assessment Tests & Evaluations: Automated Quality Scoring for Your Agents
Run structured evaluation suites against your agents, score responses against predefined scenarios, and track performance over time to catch regressions before users do.
Read post →Roles, Permissions & Backend Access: Fine-Grained Access Control
A fully configurable role and permission system lets you define exactly what each team member can see and do — with protected root roles and membership-level policies.
Read post →Language Model Provider Management: Bring Your Own LLM
Manage multiple language model providers directly in the UI. Assign specific models to individual agents, rotate API keys without downtime, and stay in control of your AI stack.
Read post →Multi-Language Support: Agentwise Now in English, German, and Japanese
The entire Agentwise platform UI — all settings, analytics, forms, and error messages — is now available in English, German, and Japanese with full locale coverage.
Read post →Analytics & Insights Dashboard: Understand How Conversations Are Going
Conversation volume, punchcard heatmaps, outcome distributions, sentiment trends, and language breakdowns — all filterable by agent or tag.
Read post →