{"site":{"name":"Koji","description":"AI-native customer research platform that helps teams conduct, analyze, and synthesize customer interviews at scale.","url":"https://www.koji.so","contentTypes":["blog","documentation"],"lastUpdated":"2026-11-21T02:05:10.201Z"},"content":[{"type":"documentation","id":"9ffa24da-5db9-43a0-9b31-bf0a37164926","slug":"salesforce-research-integration","title":"Sync Koji AI Interviews to Salesforce: Customer Insights on Every Account, Contact, and Opportunity","url":"https://www.koji.so/docs/salesforce-research-integration","summary":"Two ways to connect Koji to Salesforce. No code (Interviews and Enterprise plans): export a Salesforce report as CSV, upload it in the study share sheet under A link per person, download it back with an Interview link column, send the links as a merge field from Salesforce email, then Download latest status and import response status and start and completion times onto the Contacts. With code: create custom Contact fields, deploy a worker that receives Koji's signed interview.completed webhook (study, Integrate, Webhooks, paid plans), fetches the interview and its analysis from the read API, and PATCHes the Contact via the Salesforce REST API using a Connected App with the Client Credentials Flow. data.participant.external_id can carry the Salesforce Contact ID so no lookup is needed. The data then drives churn risk flows, discovery gates, theme-based reports and pre-renewal briefs. Zapier or Make can catch the webhook instead of a custom worker.","content":"# Sync Koji AI Interviews to Salesforce\n\n**Answer first:** Koji sends a signed `interview.completed` webhook when an interview finishes, so the sync is a push, and it takes three steps: (1) create three or four custom fields on the Contact and Account objects (Latest_Customer_Quote__c, Interview_Themes__c, Interview_Quality_Score__c, Transcript_URL__c), (2) deploy a small sync worker that PATCHes those fields via the Salesforce REST API, and (3) point a Koji webhook at that worker and, for each `interview.completed` event, fetch the full interview from the read endpoint once its `analysis` is present. If you would rather not write code at all, the no-code path below sends a personal interview link to each contact from a Salesforce report and brings everyone's status back with a CSV. With tools like Koji, your reps no longer need to dig through transcripts — the customer's own words live on the account record.\n\nIf you're tired of customer voice being trapped in survey dashboards, this is the integration that closes the loop between your AI-native research stack and the system of record your revenue team already runs on.\n\n## Why connect Koji to Salesforce\n\nSalesforce is the system of record for B2B revenue. But Salesforce alone can only tell you *what* a customer did (deals, support tickets, product usage events) — it cannot tell you *why* they did it. Traditional CX programs try to fill that gap with NPS surveys piped into custom fields, but a numeric score with one open-text field is a very thin signal compared with a 12-minute conversational interview moderated by an AI that knows when to probe.\n\nKoji is purpose-built to generate that deeper signal at scale. The AI interviewer asks the questions you scope, follows up automatically when answers are vague, scores each conversation for quality (only 3+ conversations count toward usage), extracts themes and sentiment, and writes back a clean structured artifact. Pipe that into Salesforce and three things change:\n\n- **Account executives** open an opportunity and immediately see the prospect's own words about their current pain, who else is in the buying committee, and what alternatives they're evaluating — no waiting for a researcher to summarize.\n- **Customer success managers** get an automatic alert in the account feed when a renewal-cycle interview comes back with negative sentiment or a churn-risk theme, weeks before the renewal date.\n- **Revenue operations** can build reports and dashboards that segment customers by themes extracted from interviews (e.g., \"all accounts where 'integration friction' surfaced in the last 90 days\") — something no survey tool can do because surveys do not extract themes natively.\n\n## What the integration writes back\n\nWhen a completed interview arrives and its analysis is attached, the worker writes the following onto the matching Salesforce Contact (and rolls up to the parent Account):\n\n- **Latest customer quote** — The single most representative pull-quote, picked by the AI consultant.\n- **Interview themes** — Comma-separated list of top themes extracted from the conversation.\n- **Sentiment** — `positive`, `neutral`, or `negative`, with optional sub-scores per theme.\n- **Quality score** — 1–5, the same score Koji uses for credit gating. Below 3 = filtered.\n- **Transcript URL** — A signed link to the full transcript inside Koji, for reps who want context.\n- **Completion timestamp** — Used to power \"last spoken to\" filters in pipeline reports.\n\nOptionally you can map structured-question answers to dedicated fields. Koji supports eight structured question types, including `open_ended`, `scale`, `single_choice`, `multiple_choice`, `ranking`, `yes_no`, task questions and price tests (see the [structured questions guide](/docs/structured-questions-guide)) — and each carries a stable question ID, so a single integration build will continue to work as you tweak interview wording.\n\n## No-code path: personal links from a Salesforce report\n\nOn the Interviews and Enterprise plans you can run the whole loop without code or API keys:\n\n1. **Export the contacts.** Run a Salesforce report of the people you want to interview (for example, accounts renewing in the next 60 days) and export it as CSV, keeping the Contact ID and email columns.\n2. **Upload the list.** In the study's share sheet, choose **A link per person** and click **Upload your list**. Koji finds the email or ID column and keeps the rest. Each upload takes up to 500 rows and 50 columns.\n3. **Download it with links.** Your file comes back with an **Interview link** column, one personal link per person.\n4. **Send from Salesforce.** Import that column into a custom URL field on the Contact and use it as a merge field in a Salesforce email template, or in any email tool you send from.\n5. **Bring the status back.** As responses come in, click **Download latest status**. Your file comes back with Response status, Started at (UTC) and Completed at (UTC) columns next to your own, ready to import onto the same Contacts with the Data Import Wizard.\n\nEach response shows up in Participants under that person, so you can see who replied and read what they said. To put quotes, themes and quality scores on the record as well, use the API path below.\n\n## Step 1 — Create the Salesforce custom fields\n\nIn Salesforce Setup, navigate to **Object Manager → Contact → Fields & Relationships** and create the following:\n\n| API Name | Type | Length | Notes |\n|---|---|---|---|\n| `Latest_Customer_Quote__c` | Long Text Area | 4000 | Visible on layouts |\n| `Interview_Themes__c` | Text | 255 | Comma-separated themes |\n| `Interview_Sentiment__c` | Picklist | — | positive / neutral / negative |\n| `Interview_Quality_Score__c` | Number | 1, 0 | 1–5 scale |\n| `Transcript_URL__c` | URL | 255 | Signed Koji link |\n| `Last_Koji_Interview_At__c` | Date/Time | — | Sort & filter |\n\nRepeat on the **Account** object if you want roll-up visibility, or create a Salesforce flow that propagates the Contact-level fields to the parent Account whenever the Contact is updated.\n\nAdd the new fields to your default Contact and Account page layouts so reps can see them without expanding \"Show more.\"\n\n## Step 2: Deploy the sync worker\n\nThe simplest production-grade pattern is a scheduled serverless function (Vercel Function, AWS Lambda, Cloudflare Worker) that:\n\n1. **Receives the webhook**, verifies its signature, then fetches the interview with `GET /api/v1/interviews/{id}` (the `data.links.api` URL in the event) using a server-side key holding the `interview:read` permission. If `analysis` is not there yet, fetch again a minute later.\n2. **Looks up the Salesforce Contact.** If you imported contacts with their Salesforce ID, `data.participant.external_id` is that ID and no lookup is needed. Otherwise match by email with a SOQL query: `SELECT Id FROM Contact WHERE Email = :email LIMIT 1`.\n3. **PATCHes the Contact** via `/services/data/vXX.0/sobjects/Contact/{id}` with the fields above.\n4. **Handles anonymous interviews** — if `respondent_email` is null (interview was run in anonymous mode), do not write back. Optionally log the event to a dead-letter queue for manual review.\n\nFor authentication to Salesforce, the recommended path is a **Connected App with the OAuth 2.0 Client Credentials Flow** (server-to-server). Avoid the username/password flow — it's deprecated and triggers security alerts in modern orgs.\n\nA single worker typically runs at <100ms p95 for the Salesforce write, well within Salesforce's API limits as long as you don't fire thousands of interviews concurrently. Mind the Koji side too: each API key allows 60 requests per minute by default, so spread large batches across cycles. For high-volume programs, queue the writes and send them in micro-batches.\n\n## Step 3: Point a Koji webhook at the worker\n\nIn the study, open **Integrate**, then **Webhooks**, and add the worker's https URL (workspace owners and admins can do this). Choose **Only this study** or **All studies, including new ones**, copy the signing secret into the worker's environment and click **Send test event** to check the worker answers 2xx.\n\n- Verify every request with its Standard Webhooks signature before you trust it, and answer within 10 seconds. Queue the Salesforce write rather than doing it inside the request.\n- Skip `webhook.test` events and ignore repeats by `webhook-id`: delivery is at least once, and failed deliveries are retried for about 35 hours.\n- Use `data.trust.meets_quality_bar` to decide whether to write at all, so low-quality interviews never reach the account record.\n- Keep a nightly poll of the read endpoint as a safety net for anything the worker missed while it was down.\n\nThe [webhook setup](/docs/webhook-setup) doc has the payload, signature code and delivery rules, and the [research automation](/docs/research-automation-webhooks) page covers idempotency, retries and replay.\n\n## No-code path — Zapier or Make\n\nIf you cannot run a serverless function, the same integration is buildable in Zapier or Make in under 30 minutes:\n\n1. Trigger: **Webhooks by Zapier, Catch Hook** (or a Make custom webhook). Add the hook URL as a Koji webhook endpoint (study, Integrate, Webhooks) and filter on `type` = `interview.completed`. There is no Koji app to install, and these tools do not check the signature, so treat the hook URL as a secret. Add an HTTP step that fetches the interview from `data.links.api` if you need the quote and themes.\n2. Action: **Salesforce → Find Contact** by Email.\n3. Action: **Salesforce → Update Contact** with the mapped fields.\n4. Optional action: **Slack** post to a `#customer-voice` channel with the quote.\n\nThis path is what most early-stage teams pick when they don't yet have an engineering team to own the forwarder. See the [Zapier research automation](/docs/zapier-research-automation) doc for the full step-by-step.\n\n## Workflows that become possible\n\nOnce interview data flows into Salesforce, the Salesforce platform itself unlocks a set of automations that would be impossible with surveys:\n\n- **Churn risk flow** — When `Interview_Sentiment__c = 'negative'` AND the parent Account's ARR is above a threshold, create a high-priority Case routed to the CSM and post to a Slack channel.\n- **Discovery completeness scoring** — In Sales Cloud, populate a custom Opportunity field that says \"discovery interview complete\" only when an Account has at least N interviews with quality score ≥4 in the last 60 days. This becomes a forecast-stage gate.\n- **Voice-of-customer reports** — Build a Salesforce report that groups Accounts by themes pulled from interviews (`CONTAINS(Interview_Themes__c, 'onboarding')`) and intersects with deal stage. You now have a quantitative view of qualitative signal.\n- **Renewal pre-work** — Trigger an interview link 60 days before each renewal, write the result back, and brief the CSM with a pre-renewal call summary generated from the transcript.\n\n## Comparison: Koji + Salesforce vs survey-tool + Salesforce\n\nMost teams already have a Qualtrics, SurveyMonkey, or Typeform integration with Salesforce. Why replace it with Koji? Three concrete differences:\n\n- **Open-text quality**. Surveys collect a sentence. Koji's AI moderator probes — it sees a thin answer and asks the follow-up the human researcher would have asked. The \"Latest Customer Quote\" field ends up populated with substance, not \"it's fine.\"\n- **Built-in theme extraction**. With surveys, theming requires a separate tagging pass (or a manual researcher). Koji writes the themes directly. Salesforce filtering on themes becomes a native CRM operation, not a separate analytics workflow.\n- **Quality gating**. Surveys cannot tell whether the respondent took the survey seriously. Koji scores each interview 1–5 and only writes back the ones that pass the bar — keeping your CRM clean.\n\nIf you're still on a traditional survey + CRM pattern, the [convert survey to AI interview](/docs/convert-survey-to-ai-interview) guide walks through the migration without breaking your existing flows.\n\n## Plan requirements\n\nThe headless API, API keys and the MCP connector come with the Interviews and Enterprise plans, so the sync worker and the Zapier path both need one of those plans. Webhooks come with every paid plan (Insights, Interviews and Enterprise), and personal links from an uploaded list come with Interviews and Enterprise. Interviews start as low as €1 per qualified interview, and €3 per qualified voice interview. The no-code Zapier path above is the lightest way to build the same sync without running your own forwarder. See the [plan comparison guide](/docs/plan-comparison-guide) for the full feature matrix and the [API authentication](/docs/api-authentication) doc to set up your first key.\n\n## Anonymous mode and compliance\n\nKoji supports a fully anonymous mode in which no respondent email is collected. For those interviews, the read endpoint returns `respondent_email = null` and your worker should skip the Salesforce write rather than try to match. For compliance-heavy industries, see the [GDPR-compliant AI user research](/docs/gdpr-compliant-ai-user-research) doc and the [anonymizing customer interview data](/docs/anonymizing-customer-interview-data) walkthrough.\n\n## Related Resources\n\n- [Structured Questions Guide](/docs/structured-questions-guide) — the question types Koji supports and how each renders in reports.\n- [HubSpot Research Integration](/docs/hubspot-research-integration) — the same pattern, mapped to HubSpot CRM.\n- [Webhook Setup](/docs/webhook-setup): add an endpoint, verify signatures and read the interview.completed payload.\n- [Research Automation](/docs/research-automation-webhooks): idempotency, replay, and dead-letter patterns for webhook pipelines.\n- [Zapier Research Automation](/docs/zapier-research-automation) — no-code automations across your stack.\n- [CRM Research Integration Guide](/docs/crm-research-integration-guide) — broader patterns for any CRM.\n- [User Research API Guide](/docs/user-research-api-guide) — programmatic access to studies, interviews, and reports.","category":"API Reference","lastModified":"2026-11-15T18:20:18.407773+00:00","metaTitle":"Salesforce + Koji: Sync AI Interview Insights to Every Account","metaDescription":"Connect Koji AI interviews to Salesforce with a scheduled worker on the Koji read API and the Salesforce REST API. Push transcripts, themes, sentiment, and quality scores onto Contact and Account records.","keywords":["salesforce integration","salesforce research integration","salesforce customer interview","salesforce voice of customer","crm research integration","salesforce webhook","salesforce ai research","customer insights salesforce"],"aiSummary":"Two ways to connect Koji to Salesforce. No code (Interviews and Enterprise plans): export a Salesforce report as CSV, upload it in the study share sheet under A link per person, download it back with an Interview link column, send the links as a merge field from Salesforce email, then Download latest status and import response status and start and completion times onto the Contacts. With code: create custom Contact fields, deploy a worker that receives Koji's signed interview.completed webhook (study, Integrate, Webhooks, paid plans), fetches the interview and its analysis from the read API, and PATCHes the Contact via the Salesforce REST API using a Connected App with the Client Credentials Flow. data.participant.external_id can carry the Salesforce Contact ID so no lookup is needed. The data then drives churn risk flows, discovery gates, theme-based reports and pre-renewal briefs. Zapier or Make can catch the webhook instead of a custom worker.","aiPrerequisites":["Koji account (webhooks and the headless API are included on every plan)","Salesforce org with Setup access to create custom fields and a Connected App","Ability to run a small webhook forwarder (Vercel/Lambda/Cloudflare) or a Zapier seat","Familiarity with HMAC signature verification (or the Zapier route)"],"aiLearningOutcomes":["Map Koji interview fields onto Salesforce Contact and Account objects","Poll the Koji read endpoint for finished interviews before writing to Salesforce","Detect an analysis-ready interview by polling for status completed with analysis present","Build churn-risk, discovery-completeness, and renewal-pre-brief workflows on top of the synced data","Handle anonymous-mode interviews safely"],"aiDifficulty":"intermediate","aiEstimatedTime":"18 minutes"}],"pagination":{"total":1,"returned":1,"offset":0}}