all work

// observability [Agent spend monitoring]

Burnwatch Observability

Observe-only SDK ingest, explainable rules, and wallet-risk alerts

Observability for autonomous payments

Autonomous agents can make hundreds of payments a minute. Burnwatch treats that wallet activity like production telemetry: mirror the payment metadata, scope it to an org and agent, learn normal behavior, and raise explainable alerts when spend changes shape. The important architecture choice is what Burnwatch refuses to do — it never holds keys, never approves payments, and never becomes a dependency in the payment path.

  • Python SDK
  • Next.js 15
  • TypeScript
  • Postgres
  • Stripe
  • Vercel
  • Slack webhooks
Agent payment ──► SDK record() ──► ingest API ──► rules + baselines ──► email / Slack / webhook alert
~ Observe-only SDK

Agents call bw.record() after each payment with amount, recipient, rail, timestamp, and metadata. The SDK mirrors telemetry only; payment authorization stays with the agent and its wallet provider.

~ Fail-open ingest path

Burnwatch is deliberately outside the transaction path. If ingest is slow or unavailable, the agent can keep paying. The product should reveal risk without becoming a new outage mode.

~ Org-scoped tokens

Each agent posts with an ingest token scoped to an organization. The backend associates events to agent, org, and rail before any rule evaluation so dashboards and audit logs stay tenant-isolated.

~ Warm-up baselines

New agents enter a learning period before anomaly rules fire. Burnwatch builds normal ranges for recipient frequency, spend velocity, rail mix, and active hours so first-run traffic does not become noise.

~ Transparent rule engine

Rules cover velocity spikes, drain bursts, unknown payees, new rails, off-hours spend, and pattern changes. The system favors readable thresholds and evidence JSON over black-box anomaly scores.

~ Alert delivery surfaces

Alerts can route to email, Slack, Discord, Teams, or webhook endpoints depending on plan. Every alert includes why it fired, the triggering event window, and enough context for a human to decide whether to pause an agent.

~ Dashboard + billing shell

Next.js powers fleet views, per-agent spend charts, alert management, settings, and Stripe-backed plans. The dashboard explains what Burnwatch saw; it does not hide the rule that made the call.

$
Never touches keys

Burnwatch mirrors metadata only. It cannot sign, approve, block, or reroute a payment, which keeps blast radius low.

$
Payment telemetry model

Each event carries amount, rail, recipient, agent, timestamp, and evidence metadata so spend can be queried like production observability data.

$
Explainable detections

Alerts include the exact rule, threshold, and event window that fired — useful for operators, support, and audit trails.

$
Baseline warm-up

Agents learn normal behavior before detections fire, reducing alert fatigue during setup and first traffic.

$
Tenant-scoped dashboard

Fleet view, per-agent charts, alert state, and audit history are scoped by organization and ingest token.

$
Designed for agent rails

Built around autonomous x402, stablecoin, and custom-rail payments where a human may not be watching every transaction.

SDK and ingest contract

Small Python package plus token-scoped API endpoint for recording payment metadata after the agent pays.

Rules, baselines, and evidence

Detection layer that combines warm-up ranges with transparent rules and stores human-readable evidence for every alert.

Operator workflow

Dashboard, notifications, and webhook delivery that help teams investigate, suppress, or escalate risky payment behavior.