Back to use cases
People & HR

Promotion packet from the actual work

Decisions led, cross-team impact, customer outcomes: assembled, cited, ready for committee.

Best for
Promotion committee
Primitives
ActorsDecisionsImpact
Token savings
75%

The prompt

You are assembling a promotion packet for {{person_name}}, targeting the {{target_level}} criteria. Using Sentra: 1. Pull every Decision {{person_name}} owned or led in the last {{lookback_months}} months, scoped to the {{target_level}} rubric (scope, autonomy, cross-team impact, technical / strategic judgment, mentorship). 2. For each Decision, attach the Rationale, the Outcome (was the prediction borne out?), and the Interactions that demonstrate cross-team impact. 3. Pull peer Interactions where {{person_name}} was named — credit, dependence, mentorship. 4. Pull the customer impact — Accounts touched, deals influenced, incidents resolved, features shipped. Output: - A draft packet structured to the {{target_level}} rubric. - Every rubric line backed by 2-3 cited Sentra moments. - A short "gaps" section noting any rubric dimension Sentra didn't find evidence for.

See it work

Run it from

ClaudeCursorChatGPTAny agent · MCP

How it runs

  1. 01Copy the prompt into any agent connected to Sentra over MCP.
  2. 02The agent reads the company memory, scoped to what you are allowed to see.
  3. 03One grounded answer comes back, with every line traceable to its source.

Or automate it with Actions

The same prompt runs as a Sentra Action: on a schedule, or on a semantic trigger. Output lands in Slack or email, and every send waits for your approval.

Trigger idea: promotion committee

Sentraover MCPDecisions led, impact, outcomes · assembled and cited

Priya → Staff · packet draft

Decisions led

3 decision records

Token-rotation architecture, the incident RCA process now used org-wide, and the staging snapshot pin.

Cross-team impact

incident review · Aug 20

The Singapore parallel-validation path she proposed recovered eight hours and saved the Atlas Friday delivery.

Customer outcomes

account thread · Aug

Solara's SSO audit unblocked twice; their security sign-off cites her documentation.

The prompt above becomes this. Fictional data, real mechanics: every line cites the meeting, thread, or record it came from.

Without Sentra

  1. 01Pull every meeting transcript, design doc, ticket, and Slack thread involving the person over the lookback period.
  2. 02Read each to extract decisions led, with scope (small / cross-team / company-wide).
  3. 03Identify cross-team impact by searching for the person's name in other teams' artifacts.
  4. 04Search peer interactions for credit, dependence, or mentorship signals.
  5. 05Cross-reference customer/account impact — which deals, incidents, or shipped features they touched.
  6. 06Map each piece of evidence to the target-level rubric (autonomy, judgment, mentorship, etc.).
  7. 07Compose the packet with citations.

~180,000 tokens

With Sentra

  1. 01Pull every `Decision` led by the `Actor` over the lookback, with `scope`, `Rationale`, and `Outcome`.
  2. 02Pull cross-team peer `Interactions` mentioning them — credit, dependence, mentorship are typed.
  3. 03Pull `Accounts`, `Services`, and shipped features they touched as `Value Object` relations.
  4. 04Map each to the target-level rubric.
  5. 05Compose the packet with the gaps section.

~45,000 tokens

Book a DemoStart Free