An AI that followsyour rules
Before talking to a customer, the agent learns from your company, goes through tests and goes live under control. After that, every reply can be explained.
WhatsApp service
Investigate reply
Instructions used
Support mission · Scope and limits · Don't make things up
Knowledge base excerpt
Cancellation policy, section 2: within 7 days, full refund
Decision
Request human service from finance
Teach, test, publish and monitor
Step 01
Teach
Knowledge base, mission and the agent's limits.
Step 02
Test
Simulations with personas and success criteria.
Step 03
Publish
Draft, comparison and restore of the previous version.
Step 04
Monitor
Live conversations and the trail of every reply.
Step 01
Teach
Knowledge base, mission and the agent's limits.
Step 02
Test
Simulations with personas and success criteria.
Step 03
Publish
Draft, comparison and restore of the previous version.
Step 04
Monitor
Live conversations and the trail of every reply.
What happens at each step
01
Teach
The AI learns from what your company already knows
You feed the knowledge base with files, links and text and define the agent's identity: mission, context, personality and tone. Governance blocks say what it can do, what it must refuse and when to call someone.
Knowledge base with files, links and text
Support, sales, engagement, education and productivity missions
Scope, refusal policies and quality criteria
Uncertainty rule: when in doubt, the agent doesn't make things up
02
Test
Simulate conversations before going live
In Simulations, you create personas and scenarios, define what counts as success and run conversations in batches. The report shows, turn by turn, where the agent got it right and where it needs adjusting.
Custom personas and scenarios
Success criteria per scenario
Batch conversation runs
Turn-by-turn report, with evidence
03
Publish
Changes with a draft, comparison and rollback
Adjustments go to a draft environment first. You compare it with what's live, publish with automatic backup and, if needed, restore the previous version. Each identity version records what changed.
Draft environments separate from production
Draft compared with the live version
Automatic backup on publish, and restore
Version history with a description of each change
04
Monitor
Every conversation shows what to improve
You follow conversations live and investigate any reply. Each conversation gets a summary, topic and sentiment, NPS is sent at the end and the dashboard shows how much the AI resolved alone and how much needed human support.
Live conversations, with AI pause and resume
Investigate: instructions, excerpts and calls behind every reply
Summary, topic and sentiment for each conversation
Automatic NPS at the end of service
What the agent respects in every conversation
Rules that apply to every message, not just on setup day.
Out of scope, it redirects
Questions unrelated to the agent's mission get a polite redirect.
When in doubt, it doesn't make things up
The agent is instructed to say it will check or call someone, instead of inventing an answer.
A second AI double-checks
On the decisions you choose, a second AI confirms the action before it runs.
Fallback model
You set a reliability threshold and a fallback model for when it isn't met.
People step in by rule
You write when the conversation goes to someone on the team, and it arrives with the full history.
The AI steps aside when someone steps in
The operator can pause the AI at any time. With WhatsApp coexistence, if someone replies from the phone, the AI pauses.
The AI serves, people decide
Operators see conversations as they happen, pause the AI, take over and hand back. Queues distribute cases by department and show why each one went to whom.
Pause and resume the AI in any conversation
Queues and automatic distribution by department
An explanation of why each case went to each person
An introduction message when someone takes over
What people ask most about trustworthy AI
The agent replies based on your company's knowledge base and follows governance blocks, such as the rule against making things up. The excerpts used pass through a relevance filter, decisions can be confirmed by a second AI and every reply can be investigated.
Yes. In Simulations, you create personas and scenarios, define success criteria and run conversations in batches. The report shows the result turn by turn, with evidence.
Through the Investigate feature. For each AI message, it shows the instructions used, the knowledge base excerpts that influenced the reply and the calls to external systems, with a plain-language summary.
When the rules you wrote say so, for example on a sensitive topic or at the customer's request. The team member gets the conversation with the history, and the operator can also take over at any time.
Yes. Changes go through a draft environment and, on publish, the live version gets an automatic backup. If something doesn't go as expected, you can restore the previous version.
OpenAI is the main provider, and the platform also works with other providers, such as Google Gemini and Mistral. The model is set per agent and can vary by decision.
See the AI followingyour operation's rules
In the demo, we build an agent with your rules, simulate conversations and show the trail behind every reply.
