Deliverd Tasks · persistent objectives for AI work
Stop losing the thread
when AI work gets complicated.
A task keeps what the work is for, where it stands and what comes next, outside any one conversation. Side tasks branch the problem — a bug, a piece of research — and come back with a result rather than a transcript. Switch tools and the next one reads where things stand instead of starting over.
Included in Team, Business and Enterprise · MCP, REST, CLI and SDKs for TypeScript and Python
How the work runs
Step by step
- 01
Start with the objective
An agent, or a person, starts a task with the outcome the work is for — not the first step.
- 02
Keep the state short and current
Where it stands, the next action, open questions and what is in the way. It is what any agent reads when it resumes.
- 03
Branch the problem, not the conversation
A bug or a piece of research becomes a side task that starts from a snapshot of its parent.
- 04
Bring the result back
Apply a finished side task: its decisions are confirmed, its questions added, its next action becomes the parent's.
- 05
Pick it up anywhere
ChatGPT, Claude, Cursor or Codex read the same task through the same server, so nobody re-explains the project.
- 06
Report from the record
The agent writes the update from the task's context and publishes it with the task's id, so the report stays with the work.
What it does
Everything on this page ships today
Each part names what an agent calls for it and the plans that include it.
A persistent objective
The outcome the work is for, kept apart from the conversation doing it. An agent can update the state and record findings; only a person changes the objective, so no model can redefine success and then meet it.
- Plans
- Included in Team, Business and Enterprise
- It calls
create_taskupdate_task
A short task state
Where the work stands, the next action, open questions, constraints and what is blocking it. It is what an agent reads when it resumes after a restart, a new session or a different model, instead of the whole history.
- Plans
- Included in Team, Business and Enterprise
- It calls
get_task_context
Side tasks
A side task starts from a snapshot of its parent — the objective, the decisions and the constraints — and finishes with a result: findings, proposed decisions, open questions and a suggested next action. They nest up to three levels below the objective.
- Plans
- Included in Team, Business and Enterprise
- It calls
create_side_taskcomplete_task
Apply, keep or discard
Apply a finished side task to its parent and its decisions are confirmed in your name, its open questions are added and its next action becomes the parent's. Or keep it as reference, or discard it. Either way it stays on the record.
- Plans
- Included in Team, Business and Enterprise
- It calls
apply_side_task
Findings and decisions
Hypotheses, tests, evidence, conclusions and risks, written for a reader to check — never the model's private reasoning, which is not stored. A decision an agent records is a suggestion until a person confirms it or approves it.
- Plans
- Included in Team, Business and Enterprise
- It calls
add_findingrequest_decision_approval
The task's reports
Publish a report with the task's id and it appears on the task's page, and the next context the agent reads hands it back — so it revises the report it already wrote rather than starting another.
- Plans
- Included in Team, Business and Enterprise
- It calls
publish_reportget_task_context
The task graph
Link work that depends on, blocks, supersedes or resulted from other work, and read it as one graph. Your systems hear when a task is completed or blocked, through signed webhooks.
- Plans
- Included in Team, Business and Enterprise
- It calls
get_task_graph
Questions
Tasks and Deliverd.
Which plans include Tasks?
Tasks are included in Team, Business and Enterprise. Free includes Flow and Reports, and the Tasks page there explains what tasks are for.
Do we have to change the AI tools we use?
No. Tasks are reached through the same MCP server, REST API, SDKs and CLI as the rest of Deliverd, so ChatGPT, Claude, Cursor, Codex and your own agents read and write the same task.
Can an agent change what the work is for?
No. An agent can update the state, record findings and suggest decisions. Only a person changes the objective: an agent that could would be able to redefine success and then meet it.
Who can see a task?
Everyone in the organisation, unless the objective was started in a workspace — then that workspace's members and the organisation's administrators. A side task is exactly as visible as its objective. Owners, administrators, workspace administrators and publishers change tasks; viewers read them.
What happens to our tasks if we change plan?
Everything already recorded stays readable — on the page, over the API and to agents. Creating or changing tasks needs a plan that includes them.
Is the model's reasoning stored?
No. Findings are written for a person to check. The model's private reasoning is never shown or stored.
AI does the work. People make the calls. Deliverd keeps the record.
- Gates and evidence— The agent says what it is about to do
- Compliance Mode— Govern AI work