Pylon

Live

BEARER TOKEN

CUSTOMER SUPPORT

Customer Support

Pylon gives your agent authenticated access to customer support issues, accounts, and knowledge base articles, with every action attributed to a real user.

  • Per-user credentials: each call uses the actual user's token, never a shared bot.
  • Encrypted per-tenant vault: AES-256, resolved at request time, never in LLM context.
  • Scoped before every call: pre-call scope check, 90-day SIEM-exportable audit chain.
Pylon
agent · Acme Q3
Run
What is open for Acme and who is on it?
S
pylon_issues_search
96ms
Support agent
4 open issues for Acme. 2 escalated, oldest 6 days. Priya owns three, one unassigned since Tuesday.
Sources: 4 issues, account Acme
pylon
4 issues
18:29
Message Claude...

Tools your agent reaches for on Pylon, scoped per user.

CALL ANY TOOL
Search and update support issues, manage accounts and contacts, and read knowledge base articles with the signed-in user's own Pylon permissions.
pylon_account_activity_create
Create account activity
Creates a new activity (a timeline event) for a Pylon account, identified by a custom activity type slug configured in your Pylon organization. Optionally attach HTML body content, a link, and note the contact or user who performed the activity, and when it happened.
Parameters
Name
Type
Required
Description
id
string
Required
The ID or external ID of the account to create the activity for. Required.
slug
string
Required
The slug of the custom activity type to create. Required. Slugs for available activity types can be found via the GET /activity-types endpoint.
body_html
string
Optional
Optional HTML content to display in the activity.
contact_id
string
Optional
Optional contact ID of the actor of the activity.
happened_at
string
Optional
Timestamp (RFC 3339) of when the activity happened. Defaults to the current time if empty.
link
string
Optional
Optional link to add to the activity.
link_text
string
Optional
Optional link text to display on the activity. Defaults to "Open link" if not provided. Applies only if a link is provided.
user_id
string
Optional
Optional Pylon user ID of the actor of the activity.
pylon_account_delete
Delete account
pylon_account_file_upload
Upload account file
pylon_account_get
Get account
pylon_account_highlight_update
Update account highlight
pylon_account_relationships_list
List account relationships
pylon_accounts_merge
Merge accounts
pylon_accounts_search
Search accounts
pylon_attachment_create
Create attachment
pylon_contact_delete
Delete contact
pylon_contact_update
Update contact
pylon_custom_fields_list
List custom fields
pylon_custom_object_get
Get custom object
pylon_feature_request_create
Create feature request
pylon_feature_request_set_portal_visibility
Feature request set portal visibility
pylon_feature_request_update
Update feature request
pylon_feature_requests_search
Search feature requests
pylon_issue_reply_create
Create issue reply
pylon_issue_voice_calls_list
List issue voice calls
pylon_kb_article_delete
Delete kb article
pylon_kb_collection_get
Get kb collection
pylon_kb_collection_update
Update kb collection
pylon_kb_route_redirect_create
Create kb route redirect
pylon_macro_groups_list
List macro groups
pylon_milestone_get
Get milestone
pylon_project_delete
Delete project
pylon_tag_create
Create tag
pylon_tag_update
Update tag
pylon_task_get
Get task
pylon_tasks_list
List tasks

For more tools, view docs.

Build your Agent
Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.
Python · LlamaIndex
import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Pylon tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pylon"], toolNames: [
    "pylon_account_activity_create",
    "pylon_account_delete",
    "pylon_account_file_upload"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Is the Salesforce sync healthy?" }] });
import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pylon"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Which data sources are connected?" }],
  tools,
});

// Execute the tool call with the user's vaulted Pylon credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");
import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pylon"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Pull open Zendesk tickets created this week." }],
  tools,
});

// Tool call runs with the user's vaulted Pylon credential
await sk.tools.executeTool(msg.content, "user_123");
import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["pylon"] }, pageSize: 100,
});

const agent = new Agent({
  name: "pylon_agent",
  model: "gemini-2.5-pro",
  instruction: "Work with Pylon for the signed-in user.",
  tools,
});

await agent.run("What auth does the Shopify connector need?");
Try these prompts
Paste any prompt into your agent to get started.
Issue triage
Copy the prompt
Copied
What issues are open for this account and how old are they?
Copy the prompt
Copied
Summarise the escalated issues from the last week.
Copy the prompt
Copied
Assign the unowned issues to the on-call engineer.
Account health
Copy the prompt
Copied
Show me the accounts with the most open issues.
Copy the prompt
Copied
Get the contacts and recent activity for this account.
Copy the prompt
Copied
Which accounts have not been touched in 30 days?
Knowledge base
Copy the prompt
Copied
Find knowledge base articles about SSO setup.
Copy the prompt
Copied
Draft a support reply citing the relevant article.
Copy the prompt
Copied
List the tags used across our support issues.
SEE HOW AUTH WORKS
Your users connect Pylon once. Their credentials stay vaulted, every call is scope checked, and every issue change is logged.
1
Authorize
Your user connects
Pylon
once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access
Who:
user ‘A’
when:
Once per user
access:
Limited to user
2
Store
Their
Pylon
token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection
vault:
encrypted
scope:
per-user
tokens:
auto-refreshed
3
Resolve
When your agent calls a
Pylon
tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs
speed:
~40ms
check:
before every call
seen by:
nobody
4
Audit
Every
Pylon
tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it
history:
90 days
export:
SIEM-ready
logged:
every call
Test other agents
See the same per-user auth pattern across other connectors.
Support and Ops Teams
Support triage agent
Fetches new Zendesk tickets, classifies them by type and urgency, searches the Notion knowledge base for an answer, and routes what it cannot resolve to Slack. Every call runs on the support agent's own delegated OAuth.
Support and Ops Teams
Support ticket automation agent
Fetches new Zendesk tickets, drafts a reply from Notion knowledge base articles, digests what it cannot answer to Slack, and archives the rest, acting as the support agent rather than a shared API key.
Support and Ops Teams
Freshdesk CSAT agent
Watches Freshdesk for resolved tickets, emails each requester a CSAT survey from Gmail, and writes the score and the verbatim back onto the ticket, every call on the support rep's own delegated OAuth.
Engineering Teams
Slack triage
Polls Slack for new messages, classifies bugs and support requests with a LangGraph router, files GitHub issues or Zendesk tickets, and confirms in the thread.
Test other agents
See the same per-user auth pattern across other connectors.
SUPPORT
Support triage agent
Classify new Zendesk tickets, search the Notion knowledge base for an answer, and route what it cannot resolve to Slack.
SUPPORT
Support ticket automation (Google ADK)
Fetch, annotate, and archive Zendesk tickets with Notion context, digesting anything it cannot answer to Slack.
SUPPORT
Freshdesk CSAT follow-up agent
Spot resolved Freshdesk tickets, email the CSAT survey from Gmail, and write the score back onto the ticket.
ENGINEERING
Slack triage agent
Classify new Slack messages as bugs or support requests, file the GitHub issue or Zendesk ticket, and reply in the thread.
Why Scalekit
Secure your agent's access. Connectors ship in minutes
01.
Shared tokens break per-user analytics
A shared Pylon token looks fine in a demo. In production every action looks like one service account, and you cannot tell who wired a source or ran a query. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.
// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓
02.
Authentication is not authorization
03.
Multi-tenancy is architectural
04.
Pylon today. Ten connectors tomorrow.
“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”
Venu Madhav Kattagoni
Head of Engineering / Von
FAQs
Frequently Asked Questions
Does an agent reply appear as a bot or as the user?
As the user. The credential resolved at request time belongs to the person who triggered the agent, so replies and issue changes keep real attribution.
Can I let the agent read issues but not close them?
Yes. Scope the connection to the search and get tools. Update, merge, and delete stay unavailable and the check runs before the API call.
How many Pylon tools are available?
134 across issues, accounts, contacts, teams, knowledge base, and custom fields. The page shows a representative 30; the docs list all of them.
How is the bearer token stored?
Encrypted per tenant with AES-256, resolved at request time and never placed in LLM context or logs.
Does this work for a multi-tenant support product?
Yes. Each customer's Pylon credential is namespaced to their tenant, so one tenant's agent can never resolve another tenant's token.
Start in your coding agent
Up and running in one command
Install the Scalekit skill in your editor of choice. Connector, auth, tools, prompt, all wired up
Claude Code REPL
/plugin marketplace add scalekit-inc/claude-code-authstack
/plugin install agentkit@scalekit-auth-stack
Cursor Code REPL
# ~/.cursor/mcp.json
{
""mcpServers"": {
""pylon"": {
""url"": ""https://mcp.scalekit.com/pylon"",
""headers"": { ""Authorization"": ""Bearer $SCALEKIT_TOKEN"" }
}
}
}
Codex Code REPL
# ~/.codex/config.toml
[mcp_servers.pylon]
url = ""https://mcp.scalekit.com/pylon""
auth_env = ""SCALEKIT_TOKEN""
Copilot Code REPL
# .vscode/mcp.json
{
""servers"": {
""pylon"": {
""url"": ""https://mcp.scalekit.com/pylon"",
""type"": ""http""
}
}
}