Back to use cases
Sales

What has the CFO said about pricing?

Every time a specific contact has weighed in on price: quoted, dated, and sourced.

Best for
Negotiation prep
Primitives
ActorsInteractionsDecisions
Token savings
58%

The prompt

You're building a stance summary for {{contact_name}} at {{account_name}} on the topic of pricing. Using Sentra: 1. Resolve {{contact_name}} as an Actor across CRM, calendar invites, email headers, and meeting transcripts (the Ontology Agent's actor unification should handle aliases). 2. Pull every recent Interaction where this Actor spoke and the topic facet includes pricing, discount, contract value, or budget. 3. For each Interaction, extract the quote, the date, the surface (meeting / thread / email), and the Decision or Rationale Sentra associated with it. 4. Order chronologically and flag any reversals. Output: - A timeline of three to seven entries, each: date · one-sentence quote · source. - One paragraph: how their position has moved over time, and what's likely to land in the next negotiation.

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: negotiation prep

Sentraover MCP3 statements across 5 weeks, quoted and dated

Tomas Rivera on pricing · every mention

Aug 12 · renewal call

call · 00:22:10

"The number I can defend internally is one-fifty, not one-eighty."

Aug 28 · email to Naomi

email · Aug 28

Asked whether usage-based pricing was on the table "before we take this to the board."

Sep 2 · meeting

meeting · Sep 2

Agreed to bring their CFO to the Oct 3 call if the ROI sheet lands first. No objection to the term length, only to the per-seat basis.

Read

The resistance is framing, not budget. Every objection targets per-seat; none target total spend.

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

Without Sentra

  1. 01Search the CRM for every contact matching the name. Resolve aliases manually across email, calendar, and call recordings.
  2. 02Pull every Gmail thread where the contact's address appears. Skim hundreds of messages to find pricing-adjacent ones.
  3. 03Search Slack DMs and channels for mentions of the contact. Filter to material moments by re-reading each.
  4. 04Search the meeting-transcript tool for sessions the contact attended. Re-read each one for pricing moments.
  5. 05Manually extract quotes, dates, and surfaces from every relevant moment.
  6. 06Order chronologically. Re-read to detect reversals or shifts in position.

~85,000 tokens

With Sentra

  1. 01Resolve the contact as an `Actor` — Sentra's Ontology Agent unifies aliases across CRM, calendar, email, and transcripts.
  2. 02Pull every `Interaction` where this Actor spoke, filtered by topic facet = pricing | discount | contract value | budget.
  3. 03Each Interaction returns the quote, date, surface, and the typed `Decision` or `Rationale` already extracted.
  4. 04Order chronologically. The `polarity` field flags reversals automatically.
  5. 05Compose the timeline.

~36,000 tokens

Book a DemoStart Free