Skip to content

Gantt chart · reads task

Gantt chart

Tasks & phases with dependencies and durations.

Tasks as bars across time, with what blocks what.

Permits slipping a week moves first fix a week. The chart is where that becomes obvious.
Survey and drawings
Permits
Order materials
First fix

What it does

Behaviours, not fields. Choosing between two modules is choosing between these.

Dependencies are drawn, so moving one bar shows everything downstream that just moved with it.

The finish date is derived rather than hoped for.

Works over weeks and months, where a day schedule would be noise.

How it works

  1. 1

    Tasks are entered with a start and an end; the chart derives a shared timeline from the earliest and latest dates.

  2. 2

    A dependency records which task blocks which, so moving one shows what moved with it.

  3. 3

    Changing an end date redraws everything downstream.

  4. 4

    A task with no usable dates is reported rather than drawn at zero length.

Best for

Work with real dependencies and a deadline.

Not the right choice for

A simple to-do list, which a Gantt makes heavier, not clearer.

What a row holds

Every field, and what the agent listens for to fill it — which is the difference between a page you type into and one that fills itself.

FieldTypeFilled from
TaskrequiredtextA named piece of work spanning days or weeks, not a single action.
StartrequireddateWhen it begins. Required — a bar needs two ends.
EndrequireddateWhen it finishes. Without both there is no length and no chart.
Depends ontextThe task that must finish first. This is what makes a slip cascade.

What it does not do

A module chosen for something it cannot do costs more than one that was never offered.

  • Dependencies are recorded but not enforced — nothing prevents a task starting before its blocker ends.
  • No resource levelling. Two tasks can be assigned to one person on the same day without complaint.
  • No critical path calculation; the chart shows the shape, not the arithmetic.
  • Weeks and months. A day-level schedule is a planning timeline.

Before it works

What you have to provide, if anything.

  • Both date columns have to be parseable. The module names the offending column when they are not.
  • Pair with Milestones for the handful of dates that need reporting outside the team.

In practice

A fit-out running from survey to handover across three months.

Permits are going to take until the tenth of October, not the first.
What was said to the agent

What the agent built

The permit bar extended, and first fix pushed with it because it depends on permits.

What changed

The handover date moved by a week on screen rather than in a phone call three weeks later.

Questions

What data does the Gantt chart page use?

It reads task records the agent has collected. Tasks & phases with dependencies and durations. Nothing has to be imported first — the page appears once there is something to show.

Do I have to build or configure it?

No. You describe what you need in a sentence and the agent chooses the view and fills it. Custom pages exist for the cases no built-in view covers, and those are reviewed before they go live.

When is a gantt chart the wrong choice?

A simple to-do list, which a Gantt makes heavier, not clearer. It is best for: work with real dependencies and a deadline.

Does it stay up to date?

Yes. The page is a view over the data rather than a copy of it, so anything the agent learns afterwards shows up without a rebuild or a re-import.

Ask for it in a sentence

You do not configure this page. You tell your agent what you need and it builds it from what it has already collected.

Build your agent free

Agents

More

👤
Profile
FAQ