Agent Templates
Deal Intelligence Agent

Deal intelligence agents that risk-score every call on-behalf-of your users

Connect three real services, delegate OAuth to your users, and ship a working agent in minutes. Clone the sample, swap in your tools, and it runs automatically every hour, no manual runs needed.

Deal Intelligence Agent
Sample Agent for Acme
May 22 · 10:00 AM ·
47s
Score yesterday's calls and flag deal risk
J
Fetching yesterday's calls from Gong
Fetch recent calls
gong_list_calls
Look up Attio deal
attio_search_records
Post risk report
slack_send_message
Risk report: 3 calls scored
Acme Corp — risk 0.72
"Stage: Proposal, $85k, sentiment negative"
Prioritized report DM'd to the AE in Slack
Result
3 calls analyzed, sorted by risk score
Runs automatically every hour via scheduler.py
Message Claude...
Trusted by teams shipping agents to production
Deal Intelligence Agent
Sample Agent for Acme
May 22 · 10:00 AM ·
47s
Score yesterday's calls and flag deal risk
J
Fetching yesterday's calls from Gong
Fetch recent calls
gong_list_calls
Look up Attio deal
attio_search_records
Post risk report
slack_send_message
Risk report: 3 calls scored
Acme Corp — risk 0.72
"Stage: Proposal, $85k, sentiment negative"
Prioritized report DM'd to the AE in Slack
Result
3 calls analyzed, sorted by risk score
Runs automatically every hour via scheduler.py
Message Claude...

How the agent pulls Gong calls, scores deal risk, checks Attio, and DMs a report in five steps

A real working agent you can deploy

This repo uses per-connector *_USER env vars to simulate one user. In production, pass each user's real ID as the identifier on every Scalekit call, and send them an authorization link whenever their connector status is not ACTIVE.

01
Authorize, then orchestrate
run_flow.py
Every connector is authorized once via a one-time link, and Scalekit refreshes tokens for you across Gong, Attio, and Slack. ensure_authorized() checks get_or_create_connected_account for each service at startup; if any connector is not ACTIVE it prints the magic link and exits rather than running with stale credentials.
run_flow.py
sk = ScalekitClient(
    client_id=SCALEKIT_CLIENT_ID,
    client_secret=SCALEKIT_CLIENT_SECRET,
    env_url=SCALEKIT_ENV_URL,
)
connect = sk.connect

def ensure_authorized(connect, connector, user_id):
    resp = connect.get_or_create_connected_account(
        connection_name=connector, identifier=user_id,
    )
    if resp.connected_account.status != "ACTIVE":
        link = connect.get_authorization_link(
            connection_name=connector, identifier=user_id,
        ).link
        print(f"Not authorized for {connector}. Open:\n{link}")
        return False
    return True

for connector, user in [("gong", GONG_USER), ("attio", ATTIO_USER), ("slack", SLACK_USER)]:
    if not ensure_authorized(connect, connector, user):
        sys.exit(1)
02
Fetch yesterday's calls from Gong
connectors/gong.py
03
Score every call with an LLM
analysis.py
04
Cross-reference the deal in Attio
connectors/attio.py
05
Post the risk report to Slack, on a schedule
scheduler.py

Agents that score every deal call, without the auth plumbing

Three things you'd otherwise build: Gong OAuth, Attio credentials, Slack identity. All must be live when the report fires. Handled.

1
Install
npx @scalekit-inc/cli setup
# select your coding agent
# enable scalekit MCP server on coding agent
terminal
npx @scalekit-inc/cli setup
# select your coding agent
# enable scalekit MCP server on coding agent
terminal
npx @scalekit-inc/cli setup
# select your coding agent
# enable scalekit MCP server on coding agent
terminal
npx @scalekit-inc/cli setup
# select your coding agent
# enable scalekit MCP server on coding agent
terminal
npx @scalekit-inc/cli setup
# select your coding agent
# enable scalekit MCP server on coding agent
2
You have the Scalekit authstack plugin installed (AgentKit + SaaSKit skills and MCP auth). Before coding, auto-load the AgentKit skills relevant to connectors (Gong, Attio, Slack) and use the Scalekit MCP server to validate tool calls instead of hand-written API logic.

Fetch recent calls from Gong. For each, analyze sentiment and objections using an LLM or a rule-based fallback. Cross-reference with Attio deals via the connector tools. Compute a risk score (0.0 safe to 1.0 high risk). Format and post the prioritized risk report to the AE as a Slack DM. Run automatically every hour via scheduler.py so no manual runs are needed.

Read-only steps (Gong, Attio) run without asking; ask before using write tools (the Slack DM). Exit with code 0 on success, 1 on error, 2 if no calls are found.
Why choose Scalekit

Delegated identity. Not service accounts.

Credentials never touch agent code or LLM context. The agent acts as the user, not as a shared bot.
Delegated OAuth - Agent reads your calendar, your inbox — scoped to the authorizing identity, not org-wide.
Credentials outside agent runtime  -  Tokens never touch agent code or LLM context. Both failure modes covered.
Token lifecycle automatic  -  Refresh, expiry, rotation across all connectors. One SDK call. Zero management code.
200+ prebuilt connectors  -  Google, Slack, HubSpot, GitHub, Jira, Notion, Salesforce — same auth pattern everywhere.
Try other Agent Templates

Prebuilt agents you can ship today

Each one runs on delegated identity, scoped per user.

SALES
Sales call prep agent
Pull Granola notes and Attio contact history to draft a pre-call brief before every sales meeting. Zero rep input.
GTM
CRM AI agent
Log calls, update opportunity stages, and surface stalled deals across HubSpot or Salesforce. No manual data entry.
SALES
Deal intelligence agent
Combine Gong, Attio, and Slack signals to surface deal risks and next-best actions. Updated after every call.
SALES
Outbound prospecting agent
Build targeted prospect lists with Apollo, enrich with firmographic data, and draft personalised outreach. Runs on a schedule.
GTM
HubSpot to Slack updates agent
Watch HubSpot deal stage changes and post structured updates to the right Slack channel. Reps stop checking the CRM all day.
ENGINEERING
Engineering standup agent
Aggregate GitHub and GitLab activity, link to Jira, and post a daily standup digest to Slack. No async updates.

Build your own
multi-connector agent

Add connectors. Change the LLM. Same delegated auth pattern.