As of 13 August 2026, AI can create a 30, 60 and 90-day onboarding plan.
Most people should hand this to a purpose-built tool.
Can you do it?
5 minutesto a draft.
30 minutesto something you’d act on.
Cost, all in£0
Skill neededchat-fluent
Who has to check ita colleague
What the alternative costsNo comparable human-service price is supplied in the available tool data.
If this goes wrong: the new starter receives unrealistic or irrelevant expectations and the manager has to reset the plan after time has been lost.
What to actually do
Use a tool built for this
The route this page recommends
Do it yourself
Second choiceA chat interface, chat-fluent skill, and roughly 30 minutes until you can act on the result.
How to actually do it
- Open the job description, role objectives, relevant team plans and internal onboarding material, then remove unnecessary personal information.
- Gather the new starter's role, manager, start date, working arrangement, expected outcomes, key stakeholders, systems, training needs and confirmed probation arrangements.
- Paste the information into the prompt and run it in ChatGPT, Claude or Gemini.
- Check the drafted milestones against the job description, current team priorities, available training and the manager's actual expectations.
- Ask the manager and a relevant HR or people colleague to confirm owners, timings, access requirements, check-ins and any policy-sensitive wording.
- Send the approved plan to the new starter and schedule the stated check-ins so progress and changed priorities can be recorded.
Prompt
Create a practical 30, 60 and 90-day onboarding plan for this role in a UK organisation. Role: [job title] Department: [department] Start date: [start date] Reports to: [manager and role] Working arrangement: [office, hybrid or remote] Probation arrangements: [details, if confirmed] Role purpose: [paste summary] Key responsibilities: [paste job description or list] Expected outcomes: [what success should look like] Team and stakeholders: [names or roles, without unnecessary personal data] Systems, processes and training: [list] Current team or business priorities: [list] Relevant company policies or constraints: [paste or summarise] Produce: 1. A table covering days 1 to 30, days 31 to 60 and days 61 to 90. 2. For each phase, list outcomes, specific activities, people to meet, training, evidence of progress, dependencies and a named owner. 3. Separate essential expectations from useful stretch goals. 4. Include manager check-ins and questions for the new starter. 5. Make the milestones realistic for the information supplied. Mark anything that needs confirmation rather than inventing it. 6. Keep the plan supportive and suitable for sharing with the new starter. 7. Do not make decisions about pay, disciplinary action, discrimination, reasonable adjustments or employment-law compliance. Flag those issues for the employer or an appropriate HR professional. 8. Finish with a short list of missing information and five questions the manager should answer before approving the plan.
Open it prefilled in ChatGPT or Claude, or copy it into Gemini, which takes no prefill link.
Hand it to a person
The distant thirdA person who owns the outcome does this end to end, worth it when the failure is dear.
What it gets wrong
- AI cannot know which priorities are genuinely urgent when the role description and team plans conflict.
- AI cannot judge whether a milestone is achievable for this particular person, manager or team without human context.
- AI cannot confirm that systems access, training places, introductions and decision rights will actually be available.
- AI cannot take responsibility for fair performance expectations or employment decisions that follow from the plan.
Even on a YES, the friction has a name: context depth and judgement under ambiguity.
How we scored this
Five axes, each scored nought to two by hand: ten means AI carries the task cleanly, and the thresholds that turn a total into YES, PARTLY or NO are published in the methodology. Each axis name links to its definition.
| Axis | Score (0–2) |
|---|---|
| Output | 2 |
| Inputs | 2 |
| Verification | 2 |
| Liability | 2 |
| Effort delta | 2 |
| Total | 10 / 10 |
The methodology and its thresholds are published in full.
FAQ
- Can ChatGPT create a 30, 60 and 90-day onboarding plan?
- Yes. It can organise the role information into phased outcomes, activities, owners, training and check-ins, but the manager must confirm that the expectations are realistic.
- What information does AI need to create an onboarding plan?
- Give it the job description, role outcomes, manager, team priorities, stakeholders, systems, training needs and working arrangements. Include only the personal information needed for the plan.
- Can AI make an onboarding plan suitable for a UK employee?
- It can draft a plan using your UK organisation's processes and policies. It cannot decide employment-law issues, reasonable adjustments or fair performance action, so those points need the employer or an appropriate HR professional.
- Should a manager approve an AI-generated onboarding plan?
- Yes. The manager should check every milestone, owner, dependency and deadline against the actual role and team capacity before sharing it. A people or HR colleague should check wording that touches policy, equality or employment decisions.
Nearby answers
Assessed by gpt-5.6-luna (gpt-5.6-luna) on 2026-08-13, second-checked by an independent model. Wrong somewhere? Email [email protected] and it gets re-checked.
The newsletter
AI news, new answers and product picks, straight to your inbox.