Sales Call Memory
Turn call notes into an account update and a memory graph of contacts, deals and objections.
The full canvas, before you import it
Click any node to see its config.
Click a node to select it — same as the Heym editor; the panel shows its settings.
3 nodes · Free & source-available
Sales Call Memory
Paste the notes from a sales call and get a short account update back, while an agent keeps a memory graph of the accounts, contacts, deals, objections, competitors and next steps it has heard about. The graph grows with every call, so the agent starts the next one already knowing the account. It is a small, automatic version of an ontology: a map of the account drawn by a model and stored in your own database.
What this workflow does
- notes is a text input with the call notes. The default text is invented.
- SalesMemory is an Agent node with persistent memory switched on. Its instruction asks for six kinds of thing (Account, Contact, Deal, Objection, Competitor, Next step) and for every link as a full sentence, such as "Lena Okafor works for Brightwater Foods".
- Reply returns the account update.
After each run a second model call reads the notes and the reply and merges the entities and links into the agent's graph. The graph is stored in two PostgreSQL tables, agent_memory_nodes and agent_memory_edges.
Setup
- Import the template into Heym: download the JSON from this page and drag it onto the Workflows tab, or paste it.
- On SalesMemory, pick your credential and a model.
- Run it with the sample notes, then replace the text and run it again after each new call.
- Start a message with
QUESTION:to ask what the graph knows. The agent answers from memory only and says what is missing. - Click the brain icon on the Agent node to read and edit the graph.
What to expect
We ran this template on Heym 0.0.148 on 7 November 2026 with claude-haiku-5-5, using three sets of invented call notes and one question. With the short vocabulary in the instruction, three runs ended at 12 to 14 entities and 15 to 20 links. The stored rows, the SQL queries and what the runs showed are in Auto Ontology: A Guide With Templates to Try. Its Campaign Memory twin does the same for marketing briefs.
FAQ
What does the agent remember? Entities such as people, companies, products and topics, and the links between them. Heym stores them in two PostgreSQL tables that belong to the Agent node, and you can read, edit and delete them from the brain icon on the node.
Does the memory cost extra model calls? Yes. After each successful run a second model call updates the graph. In our twelve test runs of the two templates it used 1.5 to 2.7 times the tokens of the agent's own calls.
What happens when a fact changes? Some links are replaced and some are kept. In six sales runs a new employer replaced the old one every time, but an offered discount stayed linked after the offer was withdrawn in four of the six. Read the graph once a week and delete what is wrong.
Is the sample text real? No. Every name, company and figure in the sample notes is invented.
How to import this template
- 1Click Import → Copy JSON on this page.
- 2Open your Heym and navigate to a workflow canvas.
- 3Press Cmd+V / Ctrl+V — nodes appear instantly.
- 4Add your API keys in the node config panels and click Run.
Discover more automations
- Sales & CRMCold Email AI OutreachRead leads from Google Sheets, craft a personalised cold email per row with an LLM, and send each one automatically.
- Sales & CRMAI Lead Qualification AgentSubmit lead details — an LLM scores the fit 1–10, routes hot leads to Slack, and logs cold leads separately.
- Sales & CRMCRM Contact Sync to DataTablePull contacts from your CRM on a daily schedule, normalise field names to a standard schema, and upsert each record into a Heym DataTable for downstream sales and ops workflows.
- Sales & CRMHyper-Personalized LinkedIn Sales OutreachRead leads with LinkedIn job-change signals from Google Sheets, enrich via Apollo, personalise emails with AI, and send automatically.
- Sales & CRMSales Pipeline Risk Slack StandupScan a pipeline sheet every morning, flag stalled or high-risk deals, and send a standup brief to Slack.
- Sales & CRMSpeed-to-Lead Auto-ResponderReply to every inbound lead within seconds with a personalized email, score the fit, and push hot leads to your sales channel.
- Sales & CRMAccount ICP Scoring & RoutingScore new accounts against your ideal customer profile on a schedule and route strong-fit accounts to the sales team in Slack.
- Sales & CRMAI Sales Proposal GeneratorTurn a short post-call form into a structured, customer-ready proposal draft and email it to the rep for review.
- Sales & CRMSales Call Notes to CRMPaste a sales call transcript and get a structured summary, action items, and next steps posted to your sales channel.
- Sales & CRMRenewal & Upsell Opportunity FinderScan customer accounts on a schedule for renewal and upsell signals, then alert the account team about the best opportunities.
- Sales & CRMERP CRM Account Reconciliation AgentCompare ERP customers against CRM accounts, detect mismatched ownership or billing fields, and open a governed RevOps review queue.
- Sales & CRMRevOps Enrichment Waterfall AgentUse HubSpot MCP and Brave Search MCP to enrich accounts, resolve duplicate records, and route only high-confidence updates.