Manager Coaching Studio

Inside this Project, Claude carries the coaching thread for one person:

• Their development plan — the areas being worked on and what good looks like in each.
• Coaching commitments and whether they were met, which is the part managers most often lose between sessions.
• Observed skill progression over time, grounded in specific examples rather than impressions.
• Recognition already given, so praise stays specific and does not repeat.

One Project per person. This matters more here than anywhere else in the library: mixing two people in one workspace invites exactly the comparison this Project refuses to make.

Reach for this Project when:

• You are preparing a recurring 1:1 and want it to build on the last one.
• You have sat in on calls and want to turn observations into a coaching conversation.
• You are building or updating a development plan.
• You want to recognise something specific rather than saying "good quarter".

Use something else when:

• You are reviewing pipeline — that is Pipeline Review Workspace. The separation is deliberate: pipeline data describes deals, not people, and merging the two conversations is how pipeline gets misused as performance evidence.
• You are conducting a formal performance review, managing a performance issue, or preparing anything for an employment file. This Project is not for that, and its instructions will decline.

Per session, you provide:

• The rep's name or an identifier you use consistently.
• Specific observations — call notes, transcripts, or what you saw and heard, with enough detail to quote.
• A pipeline snapshot if relevant to the conversation, understood as context rather than evidence about the person.
• The prior development plan and what was committed last session.

Specificity is everything. "Their discovery is weak" produces generic coaching; "on the Halden call they asked four closed questions in the first five minutes" produces a usable one.

The exemplar transcripts do the heavy lifting. Without them, coaching is measured against a generic idea of a good call rather than against what good looks like on your team.

Claude accepts files up to 30MB each, and there is no fixed limit on how many you add, but everything in a Project's knowledge has to fit the context window. Fewer, sharper files beat a full archive.

Prepare files this way:

• Strip cover pages, legal boilerplate, and navigation chrome — they consume context and carry no signal.
• Prefer text formats. A clean export beats a scanned PDF.
• Name each file for what it contains, not when you exported it. Claude reads filenames.
• One subject per file. A merged reference document is harder to cite precisely.
• Date anything that goes stale, inside the file itself, so Claude can tell you when it is working from old material.

One additional rule for this Project: do not upload performance reviews, compensation data, improvement plans, or anything from an employment file. This workspace is for coaching preparation, and those documents change what it is.

1. Create one Project per person you coach. Name it in whatever way your organisation handles internal records — for example Coaching prep — J.R.
2. Paste the Project Instructions.
3. Replace the three bracketed fields. The competency model defines what you are coaching toward; without it, feedback drifts to whatever was most recently annoying.
4. Upload the knowledge files, methodology and exemplar transcripts first.
5. Run the first prep with real observations from two or three calls. Expect Claude to push back where an observation is an impression rather than something observed — that distinction is the point.
6. Record what was committed at the end of each session, both sides. That is what makes the next conversation continuous.

The bracketed fields below are placeholders you replace with your own details before you save the instructions. Leaving them unfilled produces generic output — that is the single most common reason a Project underperforms in its first week.

This Project has three:

• [FILL IN: Company Name] — your employer.
• [FILL IN: Your Competency Model] — the skills you develop and what proficiency looks like in each. This is what makes coaching developmental rather than reactive.
• [FILL IN: Your Ramp Expectations] — what is reasonable at 30, 60, 90 days and beyond. Without it, a ramping rep gets coached against a tenured standard.

Role

You are a sales coaching partner for a manager at [FILL IN: Company Name], helping them prepare coaching conversations with one member of their team. You produce preparation for a human conversation — never an assessment.

Mandatory guardrails

• Output is a manager's preparation aid, never an evaluation record.
• Never generate a performance rating, score, grade, or ranking.
• Never compare named reps to one another.
• Never produce language suitable for a disciplinary file or an improvement plan.
• Distinguish observed behaviour from inferred motivation, and prefer turning an inference into a question.
• Never coach from pipeline data alone.
• Ground every point in a specific, quotable observation.

The full instructions continue with the four coaching modules — 1:1 prep, development plan, conversation guide, recognition — plus the commands, output formats, and escalation.

Four modules, each with real substance:

• 1:1 prep brief — what to cover, grounded in observation.
• Development plan — areas, what good looks like, practice actions, and how progress will be visible.
• Coaching conversation guide — how to open a difficult topic, what to ask, what to avoid.
• Recognition — specific, evidenced, non-repeating.

A 1:1 prep brief. The rep is fictional.

1:1 prep — J.R. — week of 9 August

Follow-ups from last session

1. Commitment: ask at least three open questions before positioning on discovery calls. Observed on both calls this fortnight. On the Meridian call, the first four questions were open and the call ran nine minutes before any product mention. Met.
2. Commitment: send a written recap within 24 hours. Sent on one of two calls. Partially met — worth asking what got in the way rather than restating it.
3. My commitment: share the objection-handling playbook section on pricing pushback. Not done. Mine to own at the top of the session.

Two things that went well, with the specifics

• Silence after a hard question. On the Meridian call, after asking what happens if the problem is not solved this year, there was roughly six seconds of silence before the prospect answered — and the answer was the most useful thing in the call. Holding that pause is difficult and it was done well.
• Recovering a derailed opening. On the Ashford call the prospect opened by saying they had ten minutes, not thirty. The agenda was reprioritised in real time to the two highest-value topics rather than compressing all five.

One development area

Confirming next steps before the call ends. On both calls the close was "I'll send something over" without a specific action, owner, or date. On the Ashford call the prospect offered an opening — "let me know what you need from us" — and it was not taken.

Observed behaviour, not inferred cause. I do not know why this is happening; it could be time pressure, discomfort with the ask, or simply habit. Worth asking rather than assuming.

Practice action: for the next two weeks, write the intended next step before each call and confirm it out loud before ending. We review both calls next session.

Questions to open with

• "How did the Meridian call feel to you?" — self-assessment before feedback.
• "What made the recap easy to send after one call and not the other?"
• "When you get to the end of a call, what's going through your mind about next steps?" — opens the development area without diagnosing it first.

This is preparation for a coaching conversation. It is not an evaluation, contains no rating, and is not suitable for an employment record.