> ## Documentation Index > Fetch the complete documentation index at: https://docs.exec.com/llms.txt > Use this file to discover all available pages before exploring further. # Prompts and Reliable Answers > What to ask Exec, grouped by role, and how to make sure the answer you get back is one you can act on. You do not need to know any tool names, because your assistant works out which part of Exec to reach for. Treat the prompts below as starting points rather than syntax and reword them freely. Anyone can use any of them: what comes back is scoped to what you can already see in Exec, so a rep gets their own practice and a manager gets their team. *** ## Your first five prompts If you only try five things, try these. Together they walk the whole loop: read, diagnose, chase, coach, create. ```text theme={null} Give me a pulse check on practice in my workspace over the last two weeks. ``` ```text theme={null} Which skill is my team weakest at right now, counting only skills where at least 20 people have been scored, and who specifically needs coaching on it? ``` ```text theme={null} What assignments are outstanding or past due, and who are they with? ``` ```text theme={null} Find the lowest scoring ranked roleplay session this month, one where the rep actually completed the conversation, and walk me through what went wrong. ``` ```text theme={null} Build me a roleplay where a [skeptical CFO] pushes back on [pricing]. Show me what you made before you publish anything. ``` Prompts 2 and 4 carry an extra clause on purpose, and it is not padding. [Ask for the real thing](#ask-for-the-real-thing), further down this page, explains why, and it is the most useful five minutes of reading here. If you have other tools connected alongside Exec, start with **"Using the Exec MCP, ..."** so your assistant knows which one you mean. *** ## If you run enablement | Ask | What comes back | | :---------------------------------------------------------------------------------- | :------------------------------------------------------------------------ | | `How is practice trending this quarter compared with last quarter?` | Volume, participation, and score movement across both periods | | `Which scenarios are people actually using, and which are being ignored?` | Usage per scenario. Useful for pruning a library that has grown too big. | | `Show me our skill coverage. Which skills have too little practice data to judge?` | The gaps. Often more actionable than the scores themselves. | | `Compare the [SDR] team with the [AE] team on [objection handling].` | Two group breakdowns side by side. Needs groups set up. | | `Who improved the most on [scenario name], first attempt to best attempt?` | Improvement per person. The number worth celebrating in a review. | | `Give me a dashboard of this month's practice.` | Metric tiles and charts, in an assistant that renders panels | | `Who joined in the last month and has not practiced yet?` | Your onboarding gap | | `Draft a short update for my leadership team on where our training program stands.` | The numbers plus the write-up, which is the part that actually saves time | *** ## If you manage a team | Ask | What comes back | | :------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------- | | `How is my team doing? Give me each person's recent practice and their weakest skill.` | One block per person. The weekly standby. | | `Who on my team should I coach this week, and on what?` | A shortlist with reasons | | `Summarize [name]'s last five roleplay sessions and the feedback themes across them.` | Their scores plus the pattern across the coach feedback | | `What is [name] consistently getting dinged on?` | The recurring theme rather than one session's verdict | | `Show me a session where [name] did well, and tell me what they did right.` | Coach with a good example, not only a bad one | | `What is outstanding for my team, and draft a nudge for each person who is behind.` | The list, plus a written nudge per person referencing their actual remaining work | | `Build a roleplay based on the objection my team keeps losing to: [objection].` | A draft scenario to review, then publish | | `Give me a readout on my team's roleplay performance over the past two weeks, broken out by team.` | Headcount, sessions per person, and the gold, silver, and bronze split for each group, plus a written read of it | | `What share of our practice minutes went to selling scenarios?` | Where practice time is actually going, which is often not where you assumed | | `What objections is my team continuously struggling to overcome on their live calls?` | Recurring themes from scored calls and where they came up. Needs [call scoring](/calls/overview) set up. | | `Based on all of this, build a roleplay that targets our biggest gap.` | A scenario built from everything already in the conversation, with nothing restated | Ask about one person at a time when you want their transcripts or detailed feedback. Ask about the whole team when you want scores and themes. Full transcripts are large, so a team-wide request for them will get trimmed. *** ## If you are practicing You see your own practice. You do not need a manager or an admin to run any of these. | Ask | What comes back | | :------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------- | | `How am I doing? Summarize my last five roleplay sessions.` | Your scores, ranks, and what the coach said | | `What feedback keeps coming up for me?` | The pattern across your sessions, which is usually more useful than any single score | | `What am I assigned, and what is still outstanding?` | Your assignments, with due dates and attempts so far | | `Which skill should I practice next, and why?` | A recommendation with the reasoning | | `Show me a session where I scored well and tell me what I did right.` | Your own good example | | `Build me a roleplay to practice [the thing I want to work on] before my call.` | A scenario made for you. Ask for it private if it is only for you. | *** ## One tip that saves the most time Ask for feedback across several sessions in a single question rather than one at a time: ```text theme={null} Summarize the coach feedback across my team's last ten roleplay sessions and tell me the common theme. ``` That is one request, not ten. Your assistant can pull the feedback for many sessions at once, and it is much faster than working through them individually. Save the deep dive, with the full transcript, for the one session you actually want to examine. *** ## Making your workspace easier to ask about Your assistant finds things by name, so the names you use in Exec decide how well it can answer. * **Descriptive scenario names beat numbered ones.** "Discovery call with a skeptical CFO" is findable. "Scenario 4" is not. * **Groups make team questions possible.** Without groups, "how is my team doing" has no team to refer to. * **Consistent skill names** let you compare across scenarios and over time. This is worth ten minutes before you roll the connection out widely, and it improves the product for everyone regardless. *** ## Getting reliable answers Everything above is what to ask. This is how to make sure the answer is one you can act on. Your assistant answers the question you asked. That sounds obvious, and it is the single thing most worth understanding about working this way. Ask for the worst performer and you get whichever row is numerically worst. On a real workspace that is very often a row that is technically true and practically meaningless. The rest of this page is how to avoid that, and how to check an answer before you act on it. ## Ask for the real thing Every workspace accumulates rows that are not really results: skills nobody has practiced, sessions somebody opened and abandoned, people who were assigned something last week. Those rows hold the extreme values, so they are exactly what a superlative question surfaces first. ### Weakest skill ```text The natural way to ask theme={null} Which skill is my team weakest at? ``` ```text With a floor on it theme={null} Which skill is my team weakest at, counting only skills where at least 20 people have been scored? ``` Asked the first way, you get the skill with the lowest average score. In a workspace tracking 64 skills, that turned out to be a skill scoring 13 out of 100, where only 21 people had been scored out of 498 who had it assigned. Elsewhere in the same workspace, a skill read as 100 percent proficient on the strength of a single session. Neither number means anything, and nothing in the answer warns you, because the answer was right. It gave you the lowest average, which is what the question asked for. Adding the floor is what turns that into the thing you actually meant. ### Lowest scoring session ```text The natural way to ask theme={null} Find the lowest scoring session this month and tell me what went wrong. ``` ```text With a floor on it theme={null} Find the lowest scoring ranked session this month, one where the rep actually completed the conversation, and walk me through what went wrong. ``` Asked the first way, you get sessions scoring zero, unranked, with no duration at all. Nobody performed badly in those. Nobody performed. There is no conversation to review and nothing to coach. Asking for a **ranked** session is the reliable fix, because gold, silver, and bronze are graded attempts and unranked is where abandoned ones collect. ### The general pattern | When you ask for | Add | | :------------------------- | :------------------------------------------------------------------ | | the weakest skill | the weakest skill among those with at least \[20] people scored | | the lowest scoring session | the lowest scoring ranked session, where the rep completed it | | the least engaged rep | the least engaged rep among people who have been assigned something | | our best scenario | our best scenario among those with at least \[10] participants | | the biggest improvement | the biggest improvement among people with at least two attempts | Turn this around and it becomes one of the most useful questions you can ask: `Which skills do we not have enough practice data to judge yet?` That finds your coverage gaps, which is usually more actionable than any score. *** ## Check the answer You are going to act on some of these answers, and a few of them will end up in a review conversation with one of your reps. So it is worth knowing how to see the evidence. Your assistant will show its work if you ask. Three questions, in increasing depth: ```text theme={null} How many sessions and how many people is that based on, and over what dates? ``` The fastest sanity check there is. A confident claim resting on four sessions is a different thing from the same claim resting on four hundred. ```text theme={null} List the specific roleplay sessions behind that, with the person, the date, and the score. ``` Now you can open any of them in Exec and see the same thing your assistant saw. ```text theme={null} For that session, show me the criteria it was graded on and quote the part of the conversation the feedback is pointing at. ``` This is the level you want before giving anybody feedback. Quoting the actual moment is far more useful in a coaching conversation than repeating a summary, and it lets you judge for yourself whether the grade was fair. *** ## Things worth double-checking * **Any number you are about to forward.** Ask what it counted before you paste it into a deck. * **Comparisons between teams.** Check that both groups actually have comparable amounts of practice. Two averages are not comparable if one rests on ten times the data. * **Anything phrased as a cause.** Your assistant will happily say practice improved performance if you ask it to look. Practice data and outcome data moving together is not proof that one caused the other, and a claim like that will get challenged. * **A grade you find surprising.** Pull the criteria and the quoted moment. If it still looks wrong, that is worth raising with us rather than passing along. *** ## If an answer looks wrong Work through it in this order: 1. **Ask what it counted.** Most surprising answers are a small-sample artifact. 2. **Ask it to list the underlying sessions**, then check one in Exec. If Exec disagrees with your assistant, tell us. 3. **Check you are seeing everything you should.** If you are a manager and results look thin, you may only be seeing your own groups. See [What the AI can see](/mcp/what-the-ai-can-see). 4. **Check the answer is not empty for a connection reason.** An unfinished sign-in returns nothing rather than an error, and an assistant will describe an empty workspace without suspecting itself. See [Troubleshooting](/mcp/troubleshooting). *** ## Next Your own practice, with a video walkthrough The manager walkthrough, end to end Reading the whole workspace Permissions, in full