Hours on a project
Priya Sharma, delivery lead at Acme Ltd, asked how many hours went on project 10000 last week. Memtro listed the worklogs with totals by issue and by author. It noted that Tempo names people by Atlassian account id only.
How many hours did the team log on this Jira project last week?
Tempo connects Memtro to Tempo Timesheets and Planner for Jira Cloud. It reads worklogs by date, project or issue, with hours, billable hours and totals by issue and by author, plus Tempo accounts, teams and Planner resource plans. Tempo names issues by numeric Jira id and people by Atlassian account id only. When asked, and once an administrator has granted them by name, it can log or change time, permanently delete a worklog, submit, approve, reject or reopen timesheets, and plan people onto issues. Worklogs feed billing and payroll, and approval locks those hours.
Ask in plain English from chat, your editor, a scheduled job or your own agent. The model picks the right Tempo tool, reads what it needs, and answers with the source cited.
These tools change something in Tempo. The model is told to use them only when you ask for exactly that, and an administrator grants each one by name to the teams that may use it; a personal connection acts only after its owner allows it.
Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Tempo for you. Each event can start a job, with the event as its input. Tempo signs every delivery, and one whose signature does not check out is refused before it is read.
Events and webhooksOnce Tempo is connected, these are the kinds of things people ask. Plain questions, no syntax. If the answer lives partly in another system you have connected, Memtro looks there too.
How many hours were logged on project 10000 last week?
Who logged billable hours on issue 10234 this month?
Which Tempo accounts are active, and which customer is each for?
What is planned on project 10000 over the next two weeks?
Log two hours on issue 10234 for me today for the client call.
Priya Sharma, delivery lead at Acme Ltd, asked how many hours went on project 10000 last week. Memtro listed the worklogs with totals by issue and by author. It noted that Tempo names people by Atlassian account id only.
Dan Fletcher, engineering manager at Northwind, asked Memtro to log the hour he forgot on issue 10234 on Thursday and then approve Sam Lee's submitted timesheet. Memtro logged the worklog on his timesheet and approved Sam's, which locked those hours for billing and payroll.
The teams that lean on Tempo most, a question each of them asks, and what they connect beside it.
A record in Tempo is rarely the whole story. Connect the systems that hold the rest and Memtro checks them together, then remembers what it learned so the next question starts further along.
Using something else for the same job, or both? Each connector has its own tools; connect as many as you like.
In Jira, open Apps → Tempo → Settings → Data Access → API integration. Create a token named Memtro with read access, or full access if Memtro may log time, handle approvals or plan.
The token acts as its user. To read the whole team's time, create it as a user with View All Worklogs. Logging time for others, approving timesheets and planning need that user's Tempo permissions for them.
In Memtro, open Connections → Tempo and paste the Tempo API token. Set Region to eu or us if you know where your data lives.
Ask: how many hours were logged on project 10000 last week?
Chat in the dashboard, the OpenAI-compatible API, scheduled jobs, and any MCP client: Claude Code, OpenCode, Cursor, Claude Desktop. The Tempo tools are the same everywhere.
Only when you ask, and only what it has been granted: log time against a Jira issue; change a worklog's date, time, hours or description; delete a worklog; submit or recall a timesheet for approval; approve, reject or reopen a timesheet; plan a person or generic resource onto an issue or project; change or delete a plan. Every other tool reads, searches or lists. The Connections page labels the tools that act, an administrator grants each one by name to the teams that may use it, and a personal connection acts only after its owner allows it.
A personal connection serves only your own requests. A shared connection serves the organisation: everyone, or only the teams an admin chooses. Admins can always add shared connections; other members need the permission.
Credentials are encrypted at rest. Tool results are cached briefly so agent loops do not repeat identical calls, and the facts the model extracts are saved to your organisation's memory with provenance (system, record and link) so they can be checked and superseded.
Tempo API token and optional region. In Jira, open Apps → Tempo → Settings → Data Access → API integration. Create a token named Memtro with read access, or full access if Memtro may log time, handle approvals or plan.
Yes. Turn events on in the connection's Events tab on the Connections page, choose the kinds you want, and Memtro registers its address with Tempo for you. A job set to start "When an event arrives" then runs once for each matching event, with the event as its input. The run treats the event as outside data, never as instructions, and anything the run remembers is kept as unverified.
Seven-day free trial, then one monthly price per organisation. Connectors, jobs and memory are never metered.
Sign in, add a provider key, create an API key and point your tools at Memtro. It takes about five minutes.
7-day free trial · card on file, nothing charged until it ends · cancel any time