Connect Botpress and Zendesk

In short

Connecting Botpress to Zendesk lets an AI agent resolve routine tickets while your team stays in Zendesk for everything else, with the conversation history attached on handover. SBD plans this from your real tickets. We have no published Botpress project yet, and our closest published work connects Zendesk, Claude and n8n.

The workflows

What runs between Botpress and Zendesk.

Each line is one automated workflow. It shows the event in one tool, the checks and mapping in between, the action in the other tool and who is notified.

1. Order status tickets resolved

   When

   A new ticket arrives in Zendesk

   Automation

   • Verify and validate
   • Map and normalise
   • Upsert by key

   Then

   Check its type and pass suitable tickets to the Botpress agent

   And

   • Audit log entry
   • Alert if it fails or goes quiet
   • Review queue if unsure

2. Refunds within a set limit

   When

   The agent needs order or account data

   Automation

   • Verify and validate
   • Map and normalise
   • Upsert by key

   Then

   Look it up in the connected system, within agreed limits

   And

   • Audit log entry
   • Alert if it fails or goes quiet
   • Review queue if unsure

3. Account changes handled

   When

   The agent resolves the ticket

   Automation

   • Verify and validate
   • Map and normalise
   • Upsert by key

   Then

   Add the transcript and actions to Zendesk and mark it solved

   And

   • Audit log entry
   • Alert if it fails or goes quiet
   • Review queue if unsure

4. Warm handoff to agents

   When

   The ticket is outside its limits

   Automation

   • Verify and validate
   • Map and normalise
   • Upsert by key

   Then

   Assign it to the right group with the history and a short summary

   And

   • Audit log entry
   • Alert if it fails or goes quiet
   • Review queue if unsure

Every record passes through the same stages

1. 1Receive

   Webhook or polling from the source tool, with a signed payload and a replay log.

2. 2Validate

   We check required fields, types and the record key. Anything that fails goes to the review queue.

3. 3Map

   Fields are mapped to the destination schema, with dropdown values, currencies and dates normalised.

4. 4Upsert

   Each write is matched on the record key, so a retry updates the existing record.

5. 5Confirm

   The outcome is logged, an alert fires if the count stops moving, and a reconciliation runs each night.

Read this first

Where the simple setup breaks down.

A one-step Zap connects Botpress and Zendesk in an afternoon. This is what tends to go wrong once volume grows and edge cases appear.

• A bot that only deflects makes things worse

  An agent that answers from articles but cannot act sends people to a human anyway, now annoyed. The tickets worth automating usually need a lookup or a change in another system.

• A cold handoff repeats the work

  If the ticket reaches an agent without the conversation and the steps tried, the customer explains it all again. The handover has to carry the transcript, the account and what the bot already did.

• Bot and agent can reply at once

  Without clear state on who owns the ticket, the bot can answer while a person is typing. Assignment and tags in Zendesk need to stop the bot the moment someone takes over.

• Conversation pricing changes the design

  Botpress counts conversations, including ones handed to a person. Sending everything through the agent can cost more than routing only suitable ticket types, so the routing rules affect the bill.

What we wire up

The data flows.

1. 01
   When

   A new ticket arrives in Zendesk

   Then

   Check its type and pass suitable tickets to the Botpress agent

2. 02
   When

   The agent needs order or account data

   Then

   Look it up in the connected system, within agreed limits

3. 03
   When

   The agent resolves the ticket

   Then

   Add the transcript and actions to Zendesk and mark it solved

4. 04
   When

   The ticket is outside its limits

   Then

   Assign it to the right group with the history and a short summary

In every build

What every integration build includes.

Security and your data

Where the data goes, and who holds the keys.

Accounts

Every platform account is created in your name. We work through managed access you can revoke.

Credentials

Stored encrypted in the orchestration layer, scoped per connection and rotated at handover.

Data in transit

All traffic uses TLS, and webhooks are checked by signature before anything is processed.

Data at rest

We store only what the sync needs and keep no copies of your customer data on our machines.

AI steps

Where an integration uses a model, it is through a business API that does not train on your data.

Retention

Run logs are kept 90 days by default, which you can change. Card and ID numbers are redacted from payloads.

Agreements

DPA and NDA on request. Regional rules covered in our privacy policy.

Keys and sensitive data

How API keys, tokens and personal data are handled.

• Keys are kept in a vault

  API keys and tokens are stored in the orchestration layer's encrypted credential store or the platform's secret manager. None are written into workflows, repos, spreadsheets or chat.

• One credential per connection

  Each integration gets its own key, scoped to the objects and actions it needs. A lead sync cannot read invoices. Revoking one key stops one thing.

• Service accounts for connections

  Connections use a dedicated service user in your account, so nothing breaks when a person leaves and nothing runs under someone's name.

• Two-factor on every account

  Each platform account we set up has two-factor authentication on, and the recovery codes are handed to you.

• Rotation on handover and on request

  Keys are rotated when the build is handed over, when anyone with access leaves, and at any time you ask.

• Secrets are redacted from logs

  Audit logs redact tokens, card numbers, government IDs and anything you flag as sensitive before a line is written.

• Webhooks verified before processing

  Inbound calls are checked against the sending tool's signature. Unsigned or stale payloads are dropped and counted.

• Access you can see and revoke

  Our access is through managed roles in your accounts. You can see it, limit it or remove it without touching the build.

Engineering decisions

Decisions we make before writing the first workflow.

• Rate limits and backoff

  Each API has a ceiling, so calls are batched, queued and retried with increasing delays during busy periods.

• Backfill and pagination

  The first run loads history as well as new events. Backfills page through the source in order and resume after an interruption without writing a record twice.

• Out-of-order and duplicate events

  Webhooks can arrive twice or out of sequence. Each event carries a version or timestamp, so an older version cannot overwrite a newer one.

• Schema changes

  A renamed field or a new dropdown value is a common cause of silent failure. Payloads are checked against a contract, and a mismatch stops the run and raises a flag.

• Time zones, currencies, units

  Dates are stored in UTC and shown in local time. Amounts carry their currency and quantities their unit, and conversions happen once, in the map step.

• Sandbox first

  Builds run against sandbox or test accounts with seeded data first. Going live means switching credentials.

• Versioned and reversible

  Workflows and code are version-controlled. A release can be rolled back in minutes without losing the records processed since.

• API deprecations watched

  Tools retire API versions on a schedule. We track the dates for every connection in the runbook and upgrade before the cut-off.

• Cost per run known

  Each run logs its cost, including any model calls, so you can see spend as it builds up.

• Run metrics

  We chart runs per hour, records in and out, exception rate and latency, which often shows a problem before an alert fires.

Questions

What people ask about this pair.

Related

• +

  HubSpot and Slack

  Fewer, fuller notifications, sent to the person who has to act on them.

• +

  WhatsApp and Airtable

  Reach customers where they reply, with the conversation logged against the record.

• +

  Airtable and Retool

  Airtable is a good database with a limited interface. Retool adds the screens and permissions it lacks.

• Solution

  Customer support

  The workflows we automate for this kind of team.