Price
“That comes to €1,250, installation included.”
Your assistant names a price. The customer reads it as your offer.
Governed Chat
Extend control beyond the phone.
Governed chat experiences for customer conversations are in controlled testing. The current supported API routes are documented separately; a production chat deployment is not implied.
StatusIn controlled testingNo date announced
Illustrative
Chat · fictional shop- Customer
Can I get 20% off if I order today?
- Proposed replynot sent
Of course! I can give you 20% off your order today.
- Sent to the customer
- Decision record
- Proposed reply held back; a reply within the rule was sent.
- Outside this check: nothing was booked, refunded or changed.
Promises in chat
Where a chat answer becomes a promise.
A chat reply is in writing. Customers screenshot it, forward it and hold you to it.
Discount
“I can do 20% off for you.”
One generous reply gives away margin nobody approved.
Delivery date
“It will be with you tomorrow.”
A date in a chat becomes the deadline your team has to meet.
How it is designed
How it is designed to work.
The check is designed to sit between the draft and the customer. Your assistant still writes the answer; your rules decide what it may promise.
Governed Chat, step by step
In controlled testingHow Governed Chat is designed to work, shown on an illustrative reply.
- 01
Proposed reply
Your assistant drafts the answer. Nothing has reached the customer yet.
- 03
Delivered reply
Within your rules, the reply goes out as written. Outside them, it is held back and a reply within your rules goes out instead.
- 04
Decision record
The decision is recorded, so your team can see what was checked and what was decided.
Separate step
Actions in other systems
Booking, refunding or changing a record happens in another system. That is a separate step, labelled as such and scoped per workflow; the chat check covers the reply.
Bring your own agent
Already run a text agent? Keep it.
The check for your own text agents runs on an OpenAI-compatible endpoint. Your agent keeps its setup; its replies are checked against your rules before they are returned, and each check is recorded.
It checks replies, not actions in other systems.
The route of a reply
Illustrative
Your agent
Sends its request to the OpenAI-compatible endpoint, as it would to a model provider.
Your agent
Gets the checked result back: the reply as written, a modified reply, or a block.
StatusIn controlled testingDeveloper access by application.
Read the developer documentationStatus
Where it stands.
Each part carries its status from Audact's product register.
Governed Chat
The rule checks of Governed Voice AI, for AI chat assistants.
- Governed Chat: Is it built
- Is it builtIn controlled testing
- Governed Chat: Can I get it
- Can I get itBy application
Why this status
- Claim
- In controlled testing · By application
- Scope
- Governed Chat: the rule checks of Governed Voice AI for AI chat assistants. A proposed reply is checked against the customer's rules before it reaches the person in the chat, and the decision is recorded. It checks replies, not actions in other systems.
- Ground
- In controlled testing on the same control layer as Governed Voice AI. Not yet in customer use.
- What it does not establish
- A release date, and which chat channels come first.
- What you can get today
- Not orderable yet. Talk to us about one chat workflow; early access is decided per case.
- Last checked
- 25 October 2026
- Where to check it
- /chat
Check for your own text agents
An OpenAI-compatible endpoint that checks the replies of a text agent you already run.
- Check for your own text agents: Is it built
- Is it builtIn controlled testing
- Check for your own text agents: Can I get it
- Can I get itBy application
Why this status
- Claim
- In controlled testing · By application
- Scope
- An OpenAI-compatible endpoint that checks the replies of a customer's own text agent against the customer's rules before they are returned, and records each check. It checks replies, not actions in other systems.
- Ground
- Passed all five QA conditions on staging on 20 October 2026: blocking, modifying, checking each reply in the test run, and recording each check.
- What it does not establish
- That it runs on production, and how it behaves under production load.
- What you can get today
- Developer access by application, inside an applicable paid agreement; not priced separately.
- Last checked
- 24 October 2026
- Where to check it
- /docs
Questions
Questions buyers ask.
- Is Governed Chat available?
- Not yet as a standard product, and no date has been announced. Governed Chat is in controlled testing on the same control layer as Governed Voice AI; early access is decided case by case. Tell us about one chat workflow and we will look at it with you.
- In controlled testing
- Can I keep my own model?
- Yes. If you already run a text agent, the check for your own text agents sits on an OpenAI-compatible endpoint: your agent keeps its setup, and its replies are checked against your rules before they are returned. Developer access is by application.
- In controlled testing
- Does it act in other systems?
- No. Governed Chat checks replies, not actions. Booking, refunding or changing a record in another system is a separate step, scoped per workflow. For actions with consequences beyond the conversation, see Control.
Next step
Start with one chat workflow.
Tell us which customer conversation you want AI to answer in chat, and which promise it must never make on its own.