How-to · People · Lattice AI · Oct 11, 2026
Draft five coaching prompts in Lattice a manager edits — never invent ratings
“Coaching prompts” here means five question stems a manager uses in Lattice 1:1s or growth chats — AI may draft wording; managers edit; ratings and performance scores stay human. This is not employment-law or performance-calibration advice. Terms: HCM means human capital management, the core HR suite.
Who this is for
People partners and managers whose performance / engagement home is already Lattice and who want AI help on coaching questions — not AI-assigned scores. If Workday is HCM system of record for broader HR system jobs, see Workday AI. If BambooHR is HR system of record, see BambooHR AI.
How to do it
This page is a how-to. It is not a ranking of performance AI. Product detail and dated packaging notes live on Lattice AI. Confirm AI features on your Lattice plan before you pilot.
1. Step 1 — Draft five prompt stems
What it is: Create five reusable question stems grounded in your competency model or values — not invented score labels.
- Cover: wins, blockers, growth skill, stakeholder feedback, wellbeing/workload (per your policy).
- Keep stems open-ended; ban leading questions that imply a rating.
- Source language from existing Lattice competencies or a pasted framework.
- Cap at five for the pilot so managers will actually use them.
Stems: (1) What shipped that you are proud of since we last met? (2) What is blocked and who can unblock it? (3) Which skill from our framework are you practicing? (4) What stakeholder feedback surprised you? (5) Where is workload unsustainable this month? No “Are you a 4 or a 5?” stems.
Ask AI to draft five stems from your pasted competency names only. Delete any stem that mentions scores, performance improvement plans, or compensation.
2. Step 2 — Manager edits before use
What it is: Each manager rewrites stems for their team context before the 1:1.
- Edit for role (individual contributor vs lead), tone, and private context AI does not have.
- Save the edited set in the manager’s Lattice 1:1 template or notes — not as company-wide “AI truth.”
- Share only stems that people ops reviewed for bias/policy.
- Do not auto-send AI coaching messages to employees unattended.
People ops stem #3 becomes “Which part of the checkout reliability skill are you practicing on the payments squad?” Manager removes wellbeing stem if that conversation is handled by HR business partner separately per policy.
Managers: rewrite all five in fifteen minutes. Mark one “skip for my team.” Use the remaining in the next 1:1 only.
3. Step 3 — Never invent ratings
What it is: Hard rule — AI does not propose performance ratings, calibration positions, or comp outcomes.
- Ratings and review scores: human only in Lattice’s review flow.
- If AI output includes a suggested score, discard it.
- Calibration stays with your existing people process.
- Do not add a second performance AI seat to “score” the same reviews.
AI draft accidentally adds “likely Exceeds.” Manager deletes. Review form scores entered only by the manager after evidence review. Comp discussion stays on the human cycle.
Publish a one-line rule in the manager wiki: “AI may draft questions; AI may not draft ratings.” Spot-check five 1:1 notes for leaked scores.
Pricing context (October 2026)
This how-to is not a price sheet. Plan notes live on Lattice AI. Recheck lattice.com pricing and your Lattice admin before you budget. Related paths: Workday AI, BambooHR AI. Dated October 2026.
Checked Oct 11, 2026 on the vendor’s own pricing page: Lattice’s pricing page lists a Foundations package at $13 per seat per month (it names 1:1s, Weekly Updates, Feedback, Q&A Boards, Performance, Goals & OKRs, Analytics and the AI Agent), base products such as Performance at $10, Goals & OKRs at $8 and Engagement at $4 per seat per month, add-ons such as Compensation (+$6) and Grow (+$4), and Enterprise by custom quote. Billing terms were not shown in what we captured.
Uncertainty: Lattice AI features vary by package and rollout. If an invoice and a review disagree, trust the invoice. Do not paste a marketing list price you did not pay. The only prices this site sells here are the optional $9 AI toolkit spreadsheet and $19 AI toolkit audit.
When this helps (honest take)
Useful when Lattice is the performance home, managers will edit stems, and ratings stay human.
Not useful when you want AI to calibrate ratings, or HR system of record is BambooHR/Workday for a different job you are mixing in.
Related options (educational)
| Need | Where to look | Why |
|---|---|---|
| Lattice AI coaching | Lattice AI | Primary path on this page |
| Workday HCM pilot | Workday AI | HCM system of record jobs |
| BambooHR onboarding FAQ | BambooHR AI | When BambooHR is HR system of record |
| People stack map | Stack map for people ops | Job | Tool | Owner |
| Before another seat | Three checks before an AI seat · Find unused AI seats | Live how-tos |
Related reviews: Lattice AI · Workday AI · BambooHR AI. Free: seat-waste calculator if multiple people-AI seats draft the same coaching content.
FAQ
Can AI pre-fill review scores from 1:1 notes?
No. Scores stay human. Notes may inform the manager; they do not auto-rate.
Is this HR legal advice?
No. Follow your handbook, counsel, and people ops for sensitive topics.
Where do dated prices live?
On the Lattice AI review plus the vendor site. This October 2026 how-to does not invent list prices. Our Oct 11, 2026 check of the vendor’s own pricing page is summarized in the pricing section above.
Is the Lattice AI Agent a separate purchase?
On Oct 11, 2026 Lattice listed the AI Agent among the items that come with its base products and in the Foundations package. Check your own plan before you rely on it for prompt drafts.
Optional next step
Free reviews stay free. Neither offer is required to use this page. If Lattice and another people-AI seat already draft the same coaching prompts, optional help: $9 AI toolkit spreadsheet or $19 AI toolkit audit when you want a written memo.