Skip to main content
If your job is to operate the platform rather than write agent code — wiring alerts, debugging cross-agent flows, managing access, integrating with your observability stack — this is your reading path.
This page is a curated reading path, not new material. Every link goes to an existing guide. Treat it as the “what to read in what order” map.

​
The problem this page solves

You have engineering teams shipping agents on DecimalAI. Your job is to make sure:
  • When something goes wrong, the right person gets paged (webhooks).
  • When something goes wrong across multiple agents, you can trace the cross-agent flow (multi-agent debugging).
  • The right people have access to the right agents (teams + RBAC).
  • The deployment satisfies your org’s security and compliance bar.
This reading path covers all four.

​
Reading path (in order)

1

Step 0 — new to DecimalAI? (2 minutes)

Before wiring anything up, get a feel for what DecimalAI does. Run the 2-minute demo:
pip install decimalai          # Python 3.10+
decimalai demo regression      # → a live impact report on a seeded v1→v2 change
The 2-Minute Demo walkthrough explains what the report is telling you. Prefer prose? Skim the Introduction first.
2

Understand the multi-agent debugging model

Multi-agent guide — how orchestrator → sub-agent handoffs get traced, how parent_trace_id links them, and what the dashboard shows for cross-agent flows.Read this even if your engineers don’t think they have a multi-agent system. Any agent that calls another agent (e.g. a router calling specialists) shows up here.
3

Wire webhooks for production alerts

Webhooks guide — outbound HTTP callbacks. The event registry includes regression.detected, regression.resolved, manifest.changed, usage.warning, usage.limit_reached, payment.failed, and payment.confirmed.The common pattern: webhook → PagerDuty / Opsgenie / Slack. Specifically: subscribe to regression.detected to feed your existing incident system, and regression.resolved to auto-close.
4

Set up teams and per-agent RBAC

Teams guide — workspaces, teams, per-agent role assignments, the audit log.The common shape: one workspace per business unit, one team per product, agents owned by the team that ships them. Platform team gets workspace-admin; product engineers get team-member.
5

Review the security model

Security page — encryption at rest / in transit, data residency, retention policies, SOC-2 status, and the redaction / PII handling model.Pay special attention to the redaction section if your agents see PII — DecimalAI’s default is to store full payloads; redaction is opt-in via SDK config.
6

Configure trace retention + budgets

Pricing page for the per-tier retention limits.Trace volume budgets are set per workspace. Set conservative budgets early — you can raise them; you can’t easily un-page someone who got an after-hours bill alert.

​
Operational dashboards you’ll live in

DashboardWhat it tells you
Traces volume chart (/traces)Daily ingest rate per agent. Watch for sudden drops (instrumentation broken) or spikes (someone reran a backfill).
Eval verdict mix (/)What fraction of traces are landing as keep / repair / replay / drop. Drift in this mix usually means a model regression or a policy change.
Manifest timeline (per agent)Which manifest is active. When you see two manifests both labeled “active” — that’s a red flag (rollback in progress, or stale traffic from a previous deploy).
Regression alerts (/alerts)Currently-firing alerts and their dismissal history.

​
Integration patterns

Subscribe a webhook to regression.detected with severity threshold = high_risk. Webhook fires to PagerDuty Events API. Auto-page the on-call for the affected agent’s team.See Webhooks → Event types.
Webhook → simple Cloud Run function → Slack incoming webhook for the team channel. Filter by agent_name to route to the right team’s channel.
Two options: (1) periodic JSONL export via the Datasets API into your bucket, or (2) webhook-based per-trace streaming via the Webhooks guide. Option 1 is cheaper for daily/weekly aggregates; option 2 is needed for real-time dashboards.
Use the generic OTel integration on the SDK side. The SDK can dual-emit to DecimalAI and your existing OTel collector, so you get DecimalAI’s manifest-aware view and your APM’s flame-graph view without instrumenting twice.

​
When to talk to the engineers page instead

If your job is more about writing agent code — adding traces, configuring regression checks, debugging your own agent’s behavior — read DecimalAI for Engineers first.

​
What’s next

Multi-agent

Cross-agent trace linking and orchestrator patterns.

Webhooks

Event types, payloads, retry / signature verification.

Teams

Workspaces, RBAC, audit log.

Security

Encryption, data residency, SOC-2.