The dealgraph

One record of everything that decides a deal.

The dealgraph is a structured, auditable record of a deal, built from the sources a sales team already has. Every fact in it carries its evidence, its source, its time and its coverage. This page explains what it holds, how it is built, and why you can trust it.

Diagram: four contexts around one fact, each fact carrying its evidence, source, time and coverage.

Definition

The dealgraph is one structured, auditable record of everything that decides a deal. It is built across four contexts. Your company context is declared and versioned: ICP, personas, buying roles, products, pricing, proof points, competitive position, sales process, stages, exit criteria, playbook rules and policy limits. Account, deal and rep context are observed and append-only: firmographics, funding and leadership changes; stakeholders, objections, commitments, requirements and risk; execution, follow-through and method adherence over time. Every fact carries its evidence (the statements behind it, with speaker and timestamp), its source (which system it came from), its time (when it was first observed and when it was superseded) and its coverage (how much of the available input was read). A fact is one of four kinds: observed, derived, inferred absent, or unknown, and the record says which.

One graph, comprehensive context

A deal cannot be understood from the deal alone. It takes what you sell, who you sell to, what happened, and how your team sells.

Diagram: four contexts, your company declared and versioned, and account, rep and deal observed and append-only, wired to one fact in the middle, champion equals Priya Nair, carrying its evidence, source, time and coverage.

Declared · versionedYour company
  • ICP, personas, buying roles
  • Products, capabilities, pricing
  • Proof points, competitive position
  • Sales process, stages, exit criteria
  • Playbook rules and policy limits
Observed · append-onlyAccount
  • Firmographics and growth
  • Funding, leadership changes
  • Tech stack and incumbents
  • Hiring signals, news
  • Every deal you have run there
One fact, with what it carries
champion = Priya Nair
confidence 0.86
GongGmailSalesforceClay
evidence3 statementssource4 systemstime12 Jul → 12 Augcoverage14 of 14
Observed · append-onlyRep
  • Execution and follow-through
  • Method adherence
  • Outcomes over time
  • Where coaching would pay
Observed · append-onlyDeal
  • Stakeholders and multi-threading
  • Objections raised, commitments made
  • Requirements and decision criteria
  • Process, risk and slippage
  • What was never discussed

Every fact has a parent

  • Evidence

    The statements behind the fact, with speaker and timestamp, and the candidates it beat, with the reason each lost.

  • Source

    Which system the evidence came from, and which producer and prompt version turned it into a fact.

  • Time

    When it was first observed, when it was superseded, and by what. History is append-only; nothing is overwritten.

  • Coverage

    How many inputs were read, how many failed, and what was never mentioned at all. Unknown is an answer.

A fact is one of four kinds: observed derived inferred absent unknown, and it says so

Capture, interpret, resolve

Diagram, read bottom to top: the sources you connect, then capture, interpret and resolve, then the dealgraph with its four contexts, then the agents that run on it.

  • Chat agentask anything, grounded, coverage stated
  • Action agentwhat to do next, driven by your playbook
  • Artifact agentspitch · mutual work plan · proposal
  • MCP · your own agentscall the dealgraph from Claude, Codex, anywhere
The dealgraph · four contexts, one record
  • Your companyICP · products · pricing · proof · method · playbook
  • Accountfirmographics · funding · stack · incumbents
  • Dealstakeholders · objections · commitments · risk
  • Repexecution · method · outcomes over time
Every fact, with its evidenceits source, its speaker, its time, and how much of the picture we read. Append-only, so history is never overwritten
  1. 1 · CAPTUREEvery payload exactly as it arrived, and kept, so a better extractor improves the past too, not only the future.
  2. 2 · INTERPRETTurn what was said into what it means, against your company context: your stages, your competitors, your product lines, your method.
  3. 3 · RESOLVEMatch people and companies across every source, decide which source wins when they disagree, and record what was never mentioned at all.
Connect what you already have
  • CRMread/writeSalesforce · HubSpot
  • CallsGong · Fireflies
  • Email & calendarGmail · Outlook
  • DocumentsDrive · SharePoint
  • CollaborationSlack · Teams
  • External dataClay · LinkedIn
  • WebAI search

Capture.Every payload is kept exactly as it arrived, so a better extractor improves the past as well as the future.

Interpret.What was said is turned into what it means against your company context, so “champion” means what your playbook says it means.

Resolve.People and companies are matched across sources, conflicts are decided in a fixed order of authority (your declared context, then your CRM, then facts already persisted, then web and enrichment only when the record cannot answer), and the losing candidate is kept with the reason it lost.

Auditable, and correctable

Query any field across the whole book, see what each value rests on, and overrule it. A correction is not a ticket. It becomes the highest-authority fact in the system.

Illustration: the data workbench, a structured query across the book with the selected claim, its supporting evidence, the rejected candidates, and the accept, override and flag producer controls.

RevOps is the function most likely to block AI-generated deal data, precisely because they cannot inspect it. This is the inspection surface.

A correction is not a ticket. Overrule any fact from the workbench and the correction writes a user-authority claim that supersedes the producer's, permanently. The record remembers who made it and when. Flag a producer and the same mistake is caught across the book.

Update your CRM, and keep what it cannot hold

Reps stay where they work and your automations keep firing. But a CRM field holds a value, and nothing that lets anyone check it.

What the CRM can holdchampion__c = "Priya Nair"

A value, written by us so nobody has to type it. That is genuinely useful: the field is populated, the report runs, the workflow fires.

And that is all it can hold. Not the three statements behind it, not the two candidates it beat, not the fact that fourteen of fourteen inputs were read, not that she was a supporter in July and a champion by August.

The schema was never built to carry any of that, and no amount of custom fields fixes it.

What the dealgraph holds

champion = Priya Nair  ·  confidence 0.86

  • Evidence · 3 statementsI'll take this to Marcus and push for Q1 budget. Priya Nair, Gong, 12 Aug  ·  +2 more, Gmail and Gong
  • Rejected · 2 candidates, and whyMarcus Bell: authority observed, no advocacy  ·  R. Voss: detractor signals outweigh
  • Coverage · 14 of 14 inputs read0 failed, 0 skipped. If a call had not been transcribed, this line would say so.
  • History · append-onlySupporter · 12 JulthenChampion · 12 Aug resolver v2.3 pinned

The same fact, with everything that makes it defensible: challengeable by a person, usable by an agent.

Your CRM stays clean. Your automations keep firing.Because the record underneath holds what the CRM never could. Write-back is a projection, not the original, which is also why the record survives a CRM migration.

One dealgraph, endless possibilities

Connected in days. No new system for your reps to learn, and no change to how they work. Everything sits on one record.

dealmkr agents

  • AskChat agent“What is actually holding Northwind up?” Grounded in the record, says what it rests on, says when coverage is thin.included
  • ActAction agentThe next action, driven by your playbook: your stages, your exit criteria, your policy limits. Every step inspectable.optional
  • CreateArtifact agentsPitch, mutual work plan and proposal, built from what actually happened, and saying so where a fact is missing.optional
  • LearnInsights and reportsWhat changed since Friday, what is at risk, where the data is thin. Change queries over the record.optional

Your own agents · MCPincluded

The dealgraph as a tool your agents can call, typed, with evidence and coverage. What in-house teams build with it:

  • Deal desk in Slackdiscount ask, policy limit and the evidence behind both, posted to the approver automatically
  • Commit inspection in the warehouseexit-criteria checks exported to Snowflake weekly, into the board pack
  • Coaching feed into the LMSrep graph signals, method adherence and follow-up, routed to enablement
  • Your own write-back ruleswhich facts land in which CRM fields, on your schedule, under your governance

Your automations, your models, your tokens.

The dealgraphYour whole pipeline, backfilled. Every fact with its evidence, its source, its time and its coverage. Included. This is what you buy.

everything above runs on the same record

One record, seven different jobs

Everyone touching a new customer asks a different question of the same record, and every answer names what it rests on.

Who uses the dealgraph: seven roles, the question each asks of the record, and what each gets back.
RoleThe question they askWhat they get
Rep“What changed on my deals since Friday?”Ranked actions with the reason attached, and a champion alert before the forecast call.
Sales leader“Which of these commits are real?”Deal inspection without a pipeline review. Evidence per deal, not a color.
RevOps“Where is our data actually thin?”Coverage per dimension, and who owns fixing it. No more spreadsheet reconciliation.
CRO“Will the number hold, and why?”Pipeline health with the reasoning attached, and fewer surprises at the board.
Finance“How good is the pipeline behind it?”Slippage and discount patterns from deal facts, not stage percentages.
Enablement“What separates our best reps?”Behaviors that actually correlate with winning, with the evidence behind them.
Marketing“What comes up in deals we win?”Objections counted for the content roadmap. ICP validated against closed deals.

Glossary

dealgraph
One structured, auditable record of everything that decides a deal, across four contexts, where every fact carries its evidence, source, time and coverage.
context
One of the four areas the record covers: your company (declared and versioned), account, deal and rep (observed and append-only).
fact
A single claim in the record, with its status, its evidence, its source, its time and its coverage.
claim
A fact as asserted by a particular producer or person at a particular time; a fact may have several claims, and the highest-authority one is current.
producer
The extractor, resolver or scoring routine that wrote a claim, pinned by version so a later change does not rewrite the past.
coverage
How much of the available input a fact rests on, stated as inputs read, failed and skipped.
status
One of observed, derived, inferred absent or unknown.
company context
What you declare about your own company, versioned so old artifacts resolve against the version current when they were built.
override
A user-authority claim written from the workbench that supersedes the producer's claim permanently.
write-back
The projection of selected facts into CRM fields; a projection, not the original.

Questions about the record

The dealgraph is one structured, auditable record of everything that decides a deal. It is built from the sources a sales team already has, across four contexts: your company (declared and versioned), the account, the deal and the rep (observed and append-only). Every fact in it carries its evidence, its source, its time and its coverage, meaning how much of the available input was actually read.

A CRM field holds a value and nothing else. It cannot hold the three statements behind a champion, the two candidates that lost and why, the fact that fourteen of fourteen inputs were read, or that the value was different in July. dealmkr writes the value back to your CRM so nobody has to type it, and keeps everything that makes it defensible in the record underneath. Write-back is a projection, not the original, which is also why the record survives a CRM migration.

Open any fact and you see the statements that support it, with speaker and timestamp; the candidates it beat and why each lost; how many inputs were read and how many failed; when it was first observed and when it was superseded; and which producer and prompt version wrote it. Facts are one of four kinds: observed, derived, inferred absent, or unknown, and the record says which.

The record resolves the conflict and writes down the decision. Authority runs in a fixed order: your declared company context first, then your CRM, then facts already persisted from calls, email and documents, then web and enrichment sources only when the internal record cannot answer. The losing candidate is kept, with the reason it lost.

It says so. If budget has never come up across twenty-two inputs, the record holds "budget: never asked" as a fact, and counts it as a gap rather than a pass. An unreadable or unclassified value always fails toward gap present, never toward no gap.

Yes, from the data workbench. A correction is not a ticket. It writes a user-authority claim that supersedes the producer's, permanently, and the record remembers who made it and when. You can also flag a producer so the same mistake is caught across the book.

Company context is what you declare: ICP, personas, buying roles, products, pricing, proof points, competitive position, sales process, stages, exit criteria, playbook rules and policy limits. It is versioned so that an artifact built in October resolves against October pricing even after the price list changes, and so that "champion" means what your playbook says it means, not what a generic model assumes.

Yes. dealmkr reads your CRM and writes facts back to the fields you choose, so reports keep running and automations keep firing. The record underneath holds what the CRM cannot.

Get better at selling every quarter.

Evidence-backed, AI-supported, on purpose. Not because a model improved, but because what you know about your deals finally accumulates instead of evaporating.