Your AI Action Plan

Turn raw notes into a weekly report

Paste metrics, wins, blockers, and next actions into AI to get a structured first draft you can edit quickly.

Recurring report drafting is a common low-risk AI workflow across office roles.

Last verified 2026-04-20

Write a weekly [TEAM / CLIENT / PROJECT] report.
Period: [DATE RANGE]
Metrics: [PASTE METRICS]
Highlights: [WHAT WENT WELL]
Risks or blockers: [WHAT NEEDS ATTENTION]
Next actions: [3-5 BULLETS]
Audience: [MANAGER / CLIENT / TEAM]. Keep it factual, concise, and easy to scan.

Ask for anomalies before writing the narrative

Use AI to spot unusual changes first, then write the report around the decisions those changes require.

Last verified 2026-04-20

Analyze this report data before drafting the summary.
Data: [PASTE TABLE OR METRICS]
Return: 1. Top 5 changes, 2. likely explanations, 3. questions to verify, 4. what should be highlighted, 5. what should not be overclaimed.

Spreadsheet export to decision memo

Export data from your system, use AI for synthesis, then store the final memo in your team workspace.

Last verified 2026-04-20

Turn this exported data into a decision memo.
Audience: [WHO WILL READ IT]
Data: [PASTE CSV OR TABLE]
Return: executive summary, key changes, likely causes, recommended action, risks, and a short appendix explaining assumptions.

Reusable monthly review system

Create a report template that compares periods, flags risks, and turns every monthly report into an action plan.

Last verified 2026-04-20

Create a reusable monthly review template for [ROLE / TEAM]. It should include: required inputs, KPI table, variance analysis, stakeholder narrative, recommended actions, risks, and a quality checklist before sending.

Summarize notes into decisions and action items

Paste rough notes or a transcript and ask AI for a concise summary, decisions, owners, and deadlines.

Meeting summarization is one of the most common low-friction AI workflows in office work.

Last verified 2026-04-20

Summarize this meeting.
Notes or transcript: [PASTE]
Return: 1. short summary, 2. decisions made, 3. action items with owner and due date, 4. risks, 5. follow-up message draft.

Use Otter.ai for transcript-first summaries

Record or import the meeting, then use AI to produce a transcript-based summary you can verify against the source.

Last verified 2026-04-20

Review this meeting transcript and create a follow-up note. Separate exact decisions from discussion points. Flag anything unclear. Transcript: [PASTE TRANSCRIPT].

Transcript to tasks to follow-up email

Combine transcription, AI summarization, and your project tool so meeting outcomes become assigned work.

Last verified 2026-04-20

Convert this meeting transcript into project tasks. For each task include owner, due date, dependency, priority, and a follow-up email paragraph. Transcript: [PASTE].

Meeting memory system

Build a repeatable workflow that stores decisions, recurring risks, and open loops across meetings.

Last verified 2026-04-20

Create a meeting memory template for [TEAM / CLIENT]. For each meeting, capture decisions, action items, repeated themes, unresolved questions, stakeholder commitments, and items to revisit next time.

Draft any email in 30 seconds with a single prompt

The most widely adopted AI habit in professional work. Start with one reusable email prompt.

Common first-step workflow for knowledge workers using AI.

Last verified 2026-04-20

Write a [TYPE - cold outreach / follow-up / proposal / status update] email.
From: [YOUR ROLE] at [COMPANY]
To: [RECIPIENT ROLE] at [THEIR COMPANY]
Context: [1-2 sentences of background]
Goal: [what you want them to do]
Tone: [professional / friendly / direct]
Length: [short = 3 sentences / medium = 1 short paragraph / full = structured email]

Build a personal prompt library for your 5 most common email types

Save your top prompts in Notion or a doc. One click, personalized output every time.

Last verified 2026-04-20

Write a weekly marketing performance report.
Period: [DATE RANGE]
Metrics to include: [list your KPIs]
Highlights: [what went well]
Issues: [what underperformed and brief reason]
Next week priorities: [3 bullet points]
Audience: [manager / team / client]
Tone: factual, no fluff. Use bullet points for metrics, short paragraphs for narrative.

Turn messy notes into client-ready updates

Capture rough bullets, let AI structure them, then save the final version back into your team workspace.

Last verified 2026-04-20

Turn these rough notes into a clear [EMAIL / STATUS UPDATE / REPORT].
Audience: [WHO WILL READ IT]
Purpose: [DECISION, UPDATE, REQUEST, OR ESCALATION]
Raw notes:
[PASTE NOTES]

Return:
1. Suggested subject line
2. Short summary
3. Main message in my tone: [DIRECT / WARM / EXECUTIVE]
4. Action items with owners and dates
5. Risks or open questions

Train Claude on your writing style once

Feed Claude 3-5 examples of your best emails. It learns your voice and tone so drafts need less editing.

Last verified 2026-04-20

I'll share 3 examples of emails I've written. After reading them, identify:
1. My typical sentence length and structure
2. Words or phrases I use often
3. My tone (formal / casual / direct / warm)
4. Things I never say

[PASTE EMAIL 1]
[PASTE EMAIL 2]
[PASTE EMAIL 3]

Now write a [TYPE] email using my style. Here's the context: [CONTEXT]

Generate slides with Gamma.app

Type your topic, get a full slide deck in under 2 minutes. Use this when you need a first draft fast.

Common first-step workflow for fast presentation drafts.

Last verified 2026-04-20

Create a 10-slide presentation on [TOPIC] for [AUDIENCE - e.g. "potential B2B clients"].
Slide structure: agenda, problem, solution, 3 key benefits, case study, data slide, pricing/next steps, CTA.
Tone: [professional / conversational / bold].

Write the script with Claude, design with Beautiful.ai

Split the work: use AI for structure and narrative, then Beautiful.ai auto-designs the slides to match your brand.

Last verified 2026-04-20

I need to create a presentation for [AUDIENCE] about [TOPIC].
My goal is to [GOAL - e.g. "convince the client to start a pilot project"].
Write a slide-by-slide script: title + 3 bullet points per slide.
Keep each bullet under 12 words. Total: 8-10 slides.
Start with the most important point, not context.

Research with Perplexity, outline with Claude, design with Gamma

Use a cited research pass before slide generation so the deck has sharper evidence and fewer generic claims.

Last verified 2026-04-20

Step 1 - Research brief (Perplexity):
"Find current, cited evidence for [TOPIC] relevant to [AUDIENCE]. Return 5 facts, 3 risks, and 3 credible examples."

Step 2 - Narrative outline (Claude):
"Turn this research into an 8-slide persuasive deck. For each slide include: title, core message, one supporting fact, and speaker note."

Step 3 - Paste the outline into Gamma and generate the draft deck.

Full presentation pipeline: brief to structure to design to brand polish

A three-step workflow used by top-performing marketing teams. Produces board-ready decks in under an hour.

Last verified 2026-04-20

Step 1 - Brief to structure (Claude):
"I'm preparing a [TYPE] presentation for [AUDIENCE].
Context: [2-3 sentences about the situation].
Goal: [what decision or action you want from the audience].
Constraints: [length, tone, things to avoid].
Create a presentation outline with: goal per slide, key message, supporting data point."

Step 2 - Paste outline into Gamma.app -> generate draft.
Step 3 - Export to Canva -> apply brand colors, fonts, logo.

Draft the scheduling email and agenda together

Use AI to write a concise scheduling message that includes purpose, time options, prep request, and agenda.

Scheduling messages are a common repetitive communication task across support, sales, HR, and admin roles.

Last verified 2026-04-20

Write a scheduling email for [MEETING PURPOSE].
Participants: [WHO]
Time options: [OPTIONS]
Duration: [LENGTH]
Prep needed: [PREP]
Tone: [FRIENDLY / DIRECT / FORMAL]
Include a 3-bullet agenda and a clear reply request.

Use Calendly to remove back-and-forth

Pair a booking link with an AI-written context note so the meeting gets scheduled and framed in one message.

Last verified 2026-04-20

Write a short message that shares my booking link and explains the purpose of the meeting.
Booking link: [LINK]
Purpose: [PURPOSE]
Who should attend: [ROLES]
What to prepare: [PREP]
Keep it under 120 words.

Booking link, intake questions, and prep brief

Collect context before the meeting and use AI to turn responses into a prep note for everyone involved.

Last verified 2026-04-20

Create intake questions for a [MEETING TYPE] booking page. Then write a prep brief template that summarizes the answers into: context, goal, risks, decisions needed, and agenda.

Meeting routing playbook

Create rules that determine which meetings should happen, who attends, what prep is required, and what can be handled async.

Last verified 2026-04-20

Build a meeting routing playbook for [TEAM / ROLE]. Include: meeting types, when to book vs handle async, required attendees, intake questions, agenda templates, prep checklist, and follow-up owner.

Build and update the schedule by hand in MS Project or Smartsheet

Most project managers start a new plan by copying a prior-project template into MS Project, Smartsheet, or a spreadsheet, entering tasks, durations, and dependencies, and adjusting by hand every time scope or resourcing changes. Re-baselining the plan after each change-control decision is a manual exercise that often gets deferred until the next steering committee.

Last verified 2026-04-20

Draft the work-breakdown structure and schedule with Claude, then load into MS Project

Drop the project charter or SOW into Claude with a prompt that asks for a work-breakdown structure, a sequenced task list with estimated durations, and dependency notes. Review the output, adjust for team capacity, and paste the final WBS into MS Project, Smartsheet, or Asana Timeline. The plan is still yours — AI just compresses the blank-page work.

Last verified 2026-04-20

You are helping a project manager draft a first-pass plan. I'll paste the project charter / SOW below. Produce: 1) a work-breakdown structure 3 levels deep, 2) a sequenced task list with estimated durations in days, 3) a dependency map (what blocks what), 4) three risks I should validate with engineering before baselining. Flag anything I should double-check. Charter: [PASTE]

Combine MS Project Copilot or Asana AI with Claude for variance replanning

Use Microsoft 365 Copilot inside Project (or Asana AI Studio / ClickUp Brain) to generate the first-pass schedule, resource allocation, and critical path. Each week, export the current state and pipe it through Claude with the latest status data to produce a re-forecast: which tasks slipped, which milestones are at risk, and two scenarios for getting back on track (scope cut vs. resource add).

Last verified 2026-04-20

Here's this week's project export: [PASTE]. Produce: 1) a delta vs. baseline (tasks slipped, tasks ahead), 2) milestones at risk with the driver, 3) two recovery scenarios — scope-cut and resource-add — with expected end-date impact and cost implications, 4) a recommended recommendation to take to steering committee. Use neutral, data-first language.

Run a Claude API schedule-maintenance bot that updates Jira and pages the PM on critical-path slips

Stand up a Claude API worker that reads the Jira/Asana/MS Project API nightly, reconciles actuals against the baseline, and produces a machine-generated forecast: tasks slipping, critical-path shifts, and a ranked 'things to decide this week' list delivered to the PM's Slack. The PM still decides what to cut and who to staff; the bot keeps the plan honest between planning sessions.

Last verified 2026-04-20

Maintain a RAID log by hand in Confluence or a Google Sheet

Most PMs keep their RAID log as a tab in a shared spreadsheet or a Confluence table. After each team meeting, the PM adds new rows, closes resolved items, and hopes engineers revisit it before the next steering committee. Quality varies; stale logs get ignored and surface as surprises at the worst moment.

Last verified 2026-04-20

Ask Claude to update the RAID log from weekly status and meeting notes

At the end of each status meeting, paste the transcript or notes into Claude with the current RAID log and ask it to draft updates: new risks or issues with an owner and severity, closed items with the resolution note, and dependencies that shifted. The PM reviews, edits, and commits — the log stays current instead of drifting.

Last verified 2026-04-20

You are helping me keep a RAID log current. Here is my current RAID log (risks, assumptions, issues, dependencies) and this week's meeting notes: [PASTE]. Produce: 1) proposed updates (new rows with owner + severity, closed rows with resolution, rows that shifted), 2) three items that look stale and need an owner check-in, 3) one recommended agenda item for next week's steering committee. Use neutral, factual language.

Combine Atlassian Intelligence + Claude to keep the RAID log in sync with Jira

Use Atlassian Intelligence to link risks and issues in Confluence to Jira tickets automatically. Each Friday, export the linked RAID tables and run them through Claude to produce a one-page RAID briefing for the steering committee: top 5 risks by severity × likelihood, top 3 blocked dependencies, and recommended decisions. The RAID log stops being a spreadsheet graveyard and becomes a working document.

Last verified 2026-04-20

Here is this week's RAID extract from Confluence/Jira: [PASTE]. Produce a one-page RAID briefing: 1) top 5 risks ranked by severity × likelihood with mitigation status, 2) top 3 blocked or at-risk dependencies with the unblocker ask, 3) recommended decisions for steering committee. Keep it under 400 words. Flag anything stale (>14 days no update).

Run a Claude API job that auto-drafts RAID entries from Slack threads and Jira updates

Wire Slack, Jira, and Confluence into a Claude API pipeline that reads new messages and tickets nightly and proposes RAID entries: risks flagged in engineering channels, issues surfaced in support escalations, dependency changes in upstream projects. The PM reviews a Slack digest each morning and accepts / edits / rejects each draft entry. The point is not to replace the PM's judgment — it's to make sure nothing real falls off the log.

Last verified 2026-04-20

Chase engineers for ticket updates after every standup

Many PMs spend 45+ minutes a day transcribing standup updates into Jira or Asana, closing tickets, updating status, and pestering the team to keep ticket comments current. The tracker is always a few days behind reality — which means status reports are always a few days behind reality.

Last verified 2026-04-20

Summarise standup notes with Claude and paste them into ticket comments

Record or take notes during standup. Paste them into Claude with a prompt that produces a per-ticket update in the exact Jira/Asana comment format, plus a short human-readable standup summary for the team Slack channel. The PM reviews, clicks through the tickets, and pastes — the tracker stays current without the drudgery.

Last verified 2026-04-20

Here are today's standup notes: [PASTE]. For each ticket mentioned, produce: 1) a Jira-style comment update in first person ('Pushed PR for X'), 2) a status change suggestion if warranted (To Do → In Progress → Review → Done), 3) one flag per ticket if I heard a blocker or a scope change. Then produce a 3-sentence team-Slack summary of where we are.

Use Atlassian Intelligence + Claude to auto-draft ticket updates from a standup transcription

Run the standup through a meeting recorder (Otter.ai, Fireflies, Microsoft Teams transcription). Pipe the transcript into Atlassian Intelligence or Claude with a prompt that drafts Jira/Asana updates per ticket, tags the owner, and flags scope or blocker changes. The PM reviews, accepts in bulk, and moves on to actual planning work.

Last verified 2026-04-20

Here's the standup transcript: [PASTE]. For every Jira or Asana ticket mentioned, produce: 1) a draft ticket comment (first-person), 2) a suggested status transition if applicable, 3) a tag for the owner if they named one. Flag any scope or blocker changes separately. Output as a table I can paste into a Jira bulk-update sheet.

Build a Claude API tracker-hygiene bot that reconciles Jira, GitHub, and Slack nightly

A Claude API job reads the Jira API, GitHub Actions, and Slack engineering channels each night, drafts ticket status transitions ('PR merged → move to Review', 'no activity 7 days → flag'), and posts a review queue to the PM's Slack. The PM accepts or rejects each draft in under five minutes a day. Never auto-close — surfacing the right questions is the point.

Last verified 2026-04-20

Eye-ball Gantt charts and dependency networks to spot risk

PMs open MS Project, Smartsheet, or Asana Timeline, filter for tasks that have slipped, and trace dependencies by hand to find the critical path. With a large project (>200 tasks), this exercise takes half a day every week and misses the subtle knock-on effects two or three hops away.

Last verified 2026-04-20

Export the schedule and ask Claude to identify slipped tasks and downstream impact

Export the current schedule as CSV or paste it into Claude, with this week's status updates. Ask Claude to produce a variance report: tasks more than N days behind, the downstream tasks affected, and a three-option recovery set. The PM walks into the steering committee with evidence, not gut feel.

Last verified 2026-04-20

Here is my current project schedule + this week's status: [PASTE]. Produce: 1) every task that has slipped more than 2 days behind baseline with reason, 2) for each slipped task, the list of downstream tasks that are now at risk with revised dates, 3) three recovery options — fast-track, crash, or scope-defer — with trade-offs, 4) a recommended steering-committee talking track in 3 bullets.

Combine MS Project critical-path reports with Claude commentary

Run the MS Project built-in Critical Path and Earned Value reports. Feed the exported tables into Claude with the project context and ask it to translate the numbers into a plain-English steering-committee update: what's on track, what's at risk, what needs decision this week, expressed in the way your stakeholders actually read.

Last verified 2026-04-20

Here's the MS Project critical path + earned-value export + project context: [PASTE]. Produce: 1) a 4-sentence executive summary, 2) a table of milestones with status, 3) a 'decisions needed this week' section, 4) a risk callout under 50 words. Keep it direct; no jargon, no filler.

Run a Claude API variance-detection job across the portfolio

For a PMO, schedule a nightly Claude API job that reads every project's schedule via the Jira/MS Project/Asana API and emits a portfolio-level variance dashboard: projects on track, at risk, blocked, with the specific critical-path driver. A weekly digest goes to the VP of Delivery. PMs retain control of their projects; the PMO gains visibility.

Last verified 2026-04-20

Survey vendors and methods through Google and analyst-report PDFs

PMs evaluate new tools or approaches by reading analyst reports (Gartner, Forrester), browsing vendor sites, and asking peers in Slack communities. The research lives in a personal doc and rarely feeds back into a structured decision record, so the same question gets re-researched every few quarters.

Last verified 2026-04-20

Ask Claude to produce a structured vendor brief from your notes

Paste your scattered vendor notes, analyst snippets, and internal requirements into Claude. Ask for a structured comparison: criteria × vendor matrix, top three finalists, trade-offs, and a recommended next step (reference call, pilot, decline). The brief becomes the starting point of your decision memo.

Last verified 2026-04-20

I'm evaluating vendors for [category]. Here are my notes and requirements: [PASTE]. Produce: 1) a criteria × vendor comparison matrix, 2) a short-list of three finalists with one-line rationale, 3) top trade-offs for each finalist, 4) recommended next step (reference call / pilot / decline / wait). Flag any claim that needs verification.

Use Perplexity + Claude for cited research and decision memo

Run initial discovery with Perplexity (or ChatGPT web search) to surface vendor sites, analyst coverage, and customer case studies — each with citations. Hand the results to Claude with your evaluation criteria and internal context to produce a structured decision memo: recommendation, trade-offs, risks, references. Cite everything; make the memo defensible.

Last verified 2026-04-20

Here's my research pack from Perplexity + internal notes: [PASTE]. Produce a decision memo: 1) recommendation in one sentence, 2) criteria × vendor scoring, 3) top trade-offs, 4) risks with mitigations, 5) references (bullet list linking each claim to a citation). Keep under 800 words.

Build a Claude API research assistant tied to your internal decision-record wiki

Stand up a Claude API agent that can read your internal decision-record wiki (Confluence / Notion), ingest vendor sites and analyst reports, and write a fresh research brief into a structured template. Each brief links to existing decision records so you don't re-litigate solved questions. All outputs are drafts — the PM signs off every recommendation.

Last verified 2026-04-20