Back to use cases
Finance, Procurement, Legal

What the org thinks about this vendor up for renewal

Aggregate internal sentiment on every tool in your stack, before the auto-renew hits.

Best for
Procurement reviews
Primitives
VendorsSentimentInteractions
Token savings
67%

The prompt

You are evaluating the renewal of {{vendor_name}}. Using Sentra: 1. Resolve {{vendor_name}} as a Vendor Value Object — match against contract entity, billing records, the product names used internally, and any Slack channels that discuss it. 2. Pull relevant data around this Vendor — meetings, threads, support tickets opened against them, design discussions where they were considered. 3. Score sentiment per Interaction and aggregate by team, by month. 4. Extract the top three positive moments and the top three negative moments with quoted excerpts. 5. List any open Commitment this vendor owes us, or that we owe them. Output: - A one-page renewal brief: overall sentiment, trend, who loves it, who tolerates it, who actively wants to switch. - The dollar context: line-item cost, contract end date, last approver (from procurement system). - A recommendation paragraph: renew as-is, renegotiate, replace, with the strongest two pieces of evidence for the recommendation.

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: procurement reviews

Sentraover MCP9 mentions in 60 days, aggregated before the auto-renewal

DataViz Pro renewal · what the org thinks

The signal

threads · 9 sources

Six negative mentions (export bugs, two teams built spreadsheet workarounds), two neutral, one positive from a single power user.

The tell

threads · Aug

Two teams independently priced alternatives in the last month without telling each other.

Recommendation

Renegotiate seats down 40% or consolidate into the BI stack. The renewal auto-executes in 23 days.

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

Without Sentra

  1. 01Resolve the vendor across contracts, billing records, internal product names, and Slack channels by name and aliases.
  2. 02Pull every meeting transcript, thread, and support ticket referencing the vendor or its products in the last 12 months.
  3. 03Read each to score sentiment — positive, neutral, negative — and the reason.
  4. 04Aggregate sentiment by team and by month.
  5. 05Extract the three most-cited positive and negative quoted moments.
  6. 06Search for open commitments either side owes — re-read deal threads.
  7. 07Compose the renewal brief.

~135,000 tokens

With Sentra

  1. 01Resolve the vendor as a `Vendor` `Value Object` — joined across contracts, billing, internal product names, Slack channels.
  2. 02Pull `Interactions` referencing the vendor in the last 12 months with typed sentiment.
  3. 03Aggregate by team and by month — already structured.
  4. 04Pull top three positive and negative quoted moments.
  5. 05Pull `Commitments` either side owes.
  6. 06Compose the brief with the recommendation.

~45,000 tokens

Book a DemoStart Free