Delegator
Assigning tasks in plain text in chat
You tell a Mattermost bot what needs doing and who should do it. The model proposes a task, code checks the assignee and deadline, you confirm with a thumbs-up. Then the bot watches how the task goes.
The problem
Assigning a task means opening the right system, filling in a form, finding the assignee and working out the deadline. For short tasks that is more work than the task itself, so they get assigned verbally and get lost.
How it works
- 1
Message to the bot
The requester writes to the bot in a direct message, in plain text, what and by when.
- 2
Proposal
Code recognises known trigger phrases; otherwise a local model proposes a structured task against a JSON schema.
- 3
Verification by code
Code checks the assignee in the directory, the deadline against working days and holidays, the channel and the repository.
- 4
Confirmation
The proposal appears in a thread. The task is created only after a confirming reaction, and the proposal is valid for 24 hours.
- 5
Write
The task is created in Group-Office, GitLab or a Mattermost channel.
- 6
Daily check
Every morning the bot goes through open tasks and sends an overview of their status.
Guardrails
- Nothing is created without confirmation.
- The model proposes, but code verifies the assignee, deadline and target.
- An audit log and idempotency per message: one message, at most one task.
- A kill switch for an immediate stop and a preview mode for the overview.
- Reminder limits: at most one a day, only during working hours.
A small local model makes mistakes and code often corrects its proposals. The thumbs-up confirmation is a cheap safeguard: an error is caught before the task exists, not when it reaches the assignee.
More case studies
IMAP triage
Sorting company mail and drafting replies
In the morning it is clear what is on fire. The agent sorts the NOC, CSIRT, billing and sales mailboxes and drafts replies to selected messages. It cannot send them.
GitLab triage
A daily issue digest for developers and teams
Every morning, what changed in GitLab and what is expected of whom. Code builds the sections; a local model only adds summaries. Client data never sees the cloud, and code enforces it.
Day digest
A morning overview from company systems
One e-mail before the day starts: calendar, tasks, mail, GitLab and Mattermost. The agent calls no model itself; it assembles the output of the other agents.
Expense hub
Re-billing company expenses
Statements for fuel, phones, insurance and internet arrive by e-mail and end up as an overview for each holder. No model: the parsers are deterministic and the totals match to the cent.
No-obligation consultation
Let’s find the first job for AI in your company.
An hour’s conversation about where your data lives, which processes slow you down and what of it may leave your network. You leave with a proposal for a first pilot, not a tool demo.
Built and is accountable for the AI layer at Nux
Radek Růžička
Managing Director and CTO, Nux s.r.o.