What does an agent send when it logs hours?
A time tracker needs little to create an entry. Anything sent on top of that is extra risk without extra use. In Half5 the list looks like this:
| Data | Sent? | What for |
|---|---|---|
| Description | Yes, one line | What you did, in words a client could read |
| Date, duration, start and end time | When known | The entry itself |
| Client, project, activity | When you name them | Picking the right client |
| Repository name | From coding assistants | Recognising the client; the name only, never a local path |
| Branch and commit subjects | Optional, up to 10 | Extra hint for client and project |
| File paths, code, file contents | No | Not needed for a time entry |
The description can end up on an invoice. Put in your agent's project instructions that it writes one client-readable line, without file or class names.
What does the AI provider see, and what does Half5 store?
These are two different parties. Your assistant runs at an AI provider such as Anthropic, OpenAI or Cursor. It processes your whole conversation: your request, the agent's tool calls and Half5's responses, such as client names or a list of your entries. What the provider does with that is set out in its own terms and settings.
Half5 only sees what the agent sends in a tool call, not the rest of your conversation. It stores the entry itself, a note of which agent created it with the repository name, and your repository memory.
- At the AI provider: your conversation, including what Half5 sends back.
- At Half5: the entry (description, date, duration, client, project, activity), which agent created it, the repository name and your repository memory.
- Nowhere: your password. You sign in to Half5 in your browser, not in the assistant.
What do you consent to?
Connecting uses OAuth: the agent opens a Half5 consent screen, you sign in and choose the organisation. The screen lists exactly what the agent may do. An agent can't get more than this through the connection.
- View hours: your own hours, and the clients, projects and activities you're allowed to see in that organisation.
- Log hours: create new hours that still need approval, and change or delete your own unapproved hours.
- Not: view or change invoices, colleagues or settings.
If it says ‘Unverified app’, check that you just started this connection yourself. If you're not sure, choose Deny.
What does Half5 remember, and how do you make it forget?
Half5 remembers per user which repository belongs to which client, so the agent doesn't have to keep asking. That memory is tied to you and shown under Settings → ‘Linked agents’ → ‘Repository storage’. ‘Forget …’ clears one repository; ‘Forget all’ clears everything.
Two organisation settings under ‘AI agents’ decide whether Half5 also learns from others. ‘Learn from colleagues’: if a colleague already logged a repository on a client, Half5 suggests that client, but the agent always asks first. ‘Learn from the desktop app’: agent work you register in the desktop app counts towards your own memory. Admins switch these on or off.
How does this relate to your timeline?
The MCP connection is separate from the timeline in the Half5 apps. The desktop app can put your AI sessions in Claude Code, Codex and Cursor on your timeline, next to apps, documents and calendar. That timeline is end-to-end encrypted: only you can read it, Half5 can't see it, and it isn't shared with your organisation.
Your manager only sees what you deliberately register, such as hours. Productivity figures in Half5 come from those registered hours, not from the timeline. Why that distinction matters is in Productivity without surveillance; how the timeline works is in Automatic time tracking.
What should a team agree on?
A few agreements prevent most problems. They take little time and apply to any time tracker with an AI connection.
- Agree which AI assistants may be used and under which account, business or personal.
- Agree that descriptions are one client-readable line, without code, paths or confidential details.
- Only connect agents you started yourself, and deny an unverified app you don't recognise.
- Always send agent hours through approval, like other hours. See Logging hours with AI.
- As an admin, decide whether ‘Learn from colleagues’ and ‘Learn from the desktop app’ should be on.
- Review ‘Linked agents’ now and then and disconnect what's no longer used.
How Half5 does it
Half5's MCP server explicitly tells agents never to send file paths or code and to write the description as one line a client could read. Entries arrive as ‘Not approved yet’. Under Settings → ‘Linked agents’ you see each connection's name, whether it's verified, when it was last used and what it may do, and you revoke access with ‘Disconnect’.
How log_work uses the repository to pick a client is in How log_work works. Half5 makes no certification claims here; what it does and doesn't do with your data is on the privacy and trust page.
Frequently asked questions
Does Half5 read my conversation with Claude or ChatGPT?
No. Half5 only receives what the agent sends in a tool call, such as the description and duration. The conversation itself stays with the AI provider.
Can my manager see what I do with my AI assistant?
Not through Half5. Your manager sees the hours you register. AI sessions on your timeline are end-to-end encrypted and readable only by you.
How do I clear what Half5 knows about my repositories?
Go to Settings → ‘Linked agents’ → ‘Repository storage’. Clear one repository with ‘Forget …’ or everything with ‘Forget all’.
What does ‘Unverified app’ on the consent screen mean?
That Half5 can't confirm who made the client. It may well be an ordinary assistant, but only allow it if you just started the connection yourself.
Does an agent send my source code to Half5?
It shouldn't, and the server explicitly tells agents not to. At most the repository name, the branch and a few commit subjects are sent as hints for the client.
