30-60-90 Plan Drafting Agent
A 30-60-90 plan drafting agent is an AI agent for onboarding that drafts a first version of the new hire's 30-60-90 plan from the job description, team goals, prior plans for similar roles and the manager's own notes, so the manager starts from something rather than a blank page.
How does the 30-60-90 plan drafting agent work?
What flows in, what the agent does with it, where a person decides, and what comes out.
Reads from
Job description and role profile · Team goals or objectives · Manager's own notes · Prior plans for similar roles
AI agent · runs when a start date is confirmed, ahead of day one
30-60-90 Plan Drafting Agent
A person decides
Manager edits, owns and discusses the plan with the new hire
Produces
Draft 30-60-90 plan · Suggested people to meet · Suggested check-in points
What does the 30-60-90 plan drafting agent do?
Drafts a first version of the new hire's 30-60-90 plan from the job description, team goals, prior plans for similar roles and the manager's own notes, so the manager starts from something rather than a blank page.
What does it produce?
An editable draft plan with milestones, first deliverables, key people to meet and check-in points.
Who decides?
The manager sets the expectations, edits the plan and owns the conversation with the new hire. The AI drafts and suggests; it does not set targets or judge progress against them.
What systems does the 30-60-90 plan drafting agent connect to?
Examples of the kind of systems this agent would read from or write to, so you can picture it in your own stack. The actual set is whatever you run.
-
HRIS / talent
role profile and team goals
-
Documents
prior plans and team docs
-
Chat
manager prompt and draft delivery
What data does it need?
- job description and role profile
- team goals or OKRs
- previous 30-60-90 plans (anonymized)
- manager input
How would you measure it?
share of new hires with an agreed plan by end of week one, monthly, by team; manager minutes spent drafting; how much of the draft survives editing
What does a first proof look like?
Choose two or three common roles with several past hires. Managers get a draft before each new start and mark what they kept, cut or rewrote.
You'd call it working when
Managers use the draft as a starting point rather than deleting it, and the plan reaches the new hire earlier than before.
What usually goes wrong?
- Drafts full of generic milestones that read like a template; needs real team goals as input.
- Prior plans contain names or performance judgments; anonymize before reuse.
- Managers treat the draft as final and never adapt it to the person.
What are the guardrails?
- Never sets targets or rates progress; the manager does.
- Prior plans are anonymized before use as examples.
- The draft is visible only to the manager until they share it.
- No link to performance systems or ratings.
What leaves your boundary is set per build; the inputs above are the ceiling, and where the model runs, what it retains, and the DPA are agreed with your security team before anything is connected.
Our read
Clearly valuable with real deployments behind it. Needs care on data and adoption.
Parts of this may exist in your current tools. The case for building is usually the join across systems, or your rules and language, that a suite feature cannot carry.
Where it sits in the order
Low sensitivity, an obvious manager time saving, and it needs only documents the team already has.
Is a 30-60-90 Plan Drafting Agent worth building for your function?
That depends on your numbers, your data, and what else is on the map for you. The strategy month works that out.
Thirty minutes. Bring the number this would move.