HR & Management

Verified against ChatGPT · 2026-08-13

Draft a 30-60-90 day plan for a new manager that names the political landmines, not just the goals

Builds a phased 30-60-90 day plan for someone stepping into a new leadership role, structured around what they need to observe before acting, what early trust-building move to make, and which specific team dynamics could sink a well-intentioned first change.

ChatGPT (GPT-5.1)4 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Write a 30-60-90 day plan for someone starting a new leadership role described below. This should read like advice from someone who has actually seen new managers succeed and fail in similar situations, not a generic "listen first, then act" template.

NEW ROLE AND SITUATION
Newly promoted Engineering Manager over a team of 6 she used to be a peer on, one of whom also applied for the role.

WHAT THIS TEAM/ORG IS LIKE RIGHT NOW
Team shipped reliably but morale has been flat since a reorg six months ago cut their headcount from 8 to 6 with no backfill.

WHAT THIS PERSON IS EXPECTED TO CHANGE OR IMPROVE
Cut the team's deploy cycle time in half over the next two quarters.

KNOWN SENSITIVE DYNAMICS
The peer who also applied for the role is well-liked and technically excellent; how she's treated in the first month will be watched closely by the rest of the team.

DAYS 1-30: OBSERVE AND BUILD TRUST
Focus this phase on specific listening actions (named 1:1s to run, specific questions to ask, what to deliberately not change yet) rather than generic advice to "build relationships." If a known sensitive dynamic is named (a passed-over internal candidate, a team recovering from a layoff, a predecessor who left on bad terms), name the specific behavior this new manager should adopt or avoid because of it — do not leave this as an unstated undertone the manager has to infer for themselves.

DAYS 31-60: MAKE ONE VISIBLE, LOW-RISK CHANGE
Name one specific, contained change this person should make in this window that demonstrates competence and responsiveness to what they heard in days 1-30, without touching anything structurally risky yet (compensation, headcount, reporting lines). Explain why this particular window is wrong for anything higher-risk.

DAYS 61-90: ADDRESS THE EXPECTED CHANGE DIRECTLY
By this phase, connect back to the expected-change input and lay out the first real move toward it, including one specific risk this move carries given the known sensitivities, and how to sequence communication about it so it doesn't blindside the team.

WHAT NOT TO DO
Do not suggest any change in days 1-30 beyond genuinely reversible, low-stakes adjustments. Do not have this person send a team-wide "here's my vision" message before day 30 — that reads as arriving with a pre-formed agenda rather than one shaped by what they actually heard.

OUTPUT FORMAT
Three phase sections (Days 1-30, 31-60, 61-90), each with 3-5 concrete actions, followed by a short paragraph naming the single biggest risk to this plan given the known sensitivities.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

Leadership-transition research (echoing the structure Michael Watkins popularized in first-90-days frameworks) consistently finds that the specific failure mode for new managers is not lack of ambition but moving too fast on structural change before earning credibility, or moving too slowly and reading as passive — a generic "listen first, then act" template gives no way to actually calibrate that timing to the specific situation. Requiring the plan to name a genuinely low-risk, reversible change for days 31-60 forces a concrete distinction between a competence-signaling move (visible, contained, easy to reverse if wrong) and the higher-risk structural changes leadership actually wants, which is exactly the distinction new managers blur when they're anxious to prove themselves quickly. Feeding in a known sensitivity — here, a passed-over internal candidate — and requiring the plan to name explicit behavior around it rather than leaving it as subtext matters because this is precisely the kind of dynamic a new manager under pressure will handle by instinct and often get wrong (either over-correcting with visible favoritism to reassure the passed-over peer, or avoiding them altogether, both of which the rest of the team will notice and read as a signal). Explicitly banning a pre-day-30 "vision" announcement targets a specific, common new-manager mistake: arriving with a pre-formed agenda reads as not having actually listened, undermining the exact trust-building the first 30 days are meant to establish, even when the content of the vision is objectively sound.

What you get back

Days 1-30: Run individual 1:1s with all 6 engineers before any group meeting; ask each one directly what's working and what they'd change if they were in this seat; treat the peer who also applied with the same cadence and substance as everyone else, no more no less, since either extra warmth or visible distance will be read as a signal by the team. Days 31-60: Fix one concrete process friction surfaced in the 1:1s (e.g., a slow code-review turnaround) as a visible, reversible win. Days 61-90: Introduce the deploy-cycle-time initiative, framed around the team's own stated frustrations with the current process rather than as a top-down mandate.

Verified against

ChatGPT GPT-5.1 · 2026-08-13

Changelog

  • 2026-08-13 Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — what Scult builds, built and maintained for you — that's Scult's day job.

EXPLORE WHAT SCULT BUILDS
Write a job description that matches the actual hiring bar instead of a wish list nobody meetsTurns a hiring manager's notes into a job description built around a true must-have vs. nice-to-have split, so the posting attracts candidates who can actually clear the bar instead of scaring off good ones with an inflated requirements list.ChatGPT (GPT-5.1)2026-08-08Build a candidate scorecard that stops a 4-person panel from scoring the same interview four different waysGenerates a per-candidate scorecard tied to the specific competencies this role was actually interviewed for, so a hiring panel's individual scores are comparable instead of reflecting how generous or strict each interviewer happens to be.ChatGPT (GPT-5.1)2026-08-09Calibrate what a 1 through 4 actually means before four interviewers disagree about it in the debriefProduces the scoring rubric itself — the shared definition of what each competency and each score level means — that a hiring panel reviews together before interviews start, so scorecards filled out later are measuring the same thing.ChatGPT (GPT-5.1)2026-08-10Generate interview questions with the follow-up probes that catch a rehearsed answerWrites a set of role-specific interview questions, each paired with two or three follow-up probes designed to surface real depth or expose a memorized answer, plus a flag on any question that risks drifting into illegal or discriminatory territory.ChatGPT (GPT-5.1)2026-08-11
All HR & Management prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY