Skip to content
Back to home

§ REFERENCE ARCHITECTURE

Reference Deployment

What a governed two-agent production fleet looks like end to end: stack, autonomy tiers, policy set, measured enforcement cost, SIEM routing, and the audit evidence each control produces.

What this page is — and is not

This is a reference architecture, not an anonymized customer case study. The scenario is drawn from how we run and test Execlave ourselves; every capability and number on this page is documented elsewhere on this site — latency figures come from the published, reproducible benchmarks and nothing here is an estimate. When we publish customer case studies, they will be labelled as such.

§ 01

Scenario & stack

A mid-size product company runs two production agents with different risk profiles — the common starting shape we see.

ComponentChoiceWhy
Support agentLangChain (Python), customer-facingHandles end-user input — highest injection and PII exposure.
Ops agentOpenAI Agents SDK (Python), internalWrites to internal systems — tool misuse is the main risk.
GovernanceExeclave cloud (self-hosted available)Both agents instrumented with one SDK call each.
Environmentsproduction + stagingSame policies in both; staging is where tightened policies are re-tested.
SIEMSplunk or Microsoft SentinelViolations land in the existing SOC queue — see the integration guides.
# Support agent — LangChain (Python)handler = ExeclaveCallbackHandler(exe, agent_id="support-bot")chain.invoke(input, config={"callbacks": [handler]}) # Ops agent — OpenAI Agents SDK (Python)add_trace_processor(ExeclaveTracingProcessor(exe, agent_id="ops-agent"))
§ 02

Autonomy tiers & policy set

Each agent declares one autonomy level; Execlave applies the matching control bundle. Policies that fall outside the tier are flagged as audited overrides.

AgentAutonomy levelWhat that means
support-botact_with_approvalReplies freely; outbound actions (refunds, emails) queue for human sign-off with a 30-minute approval expiry.
ops-agentautonomousWrites without per-action approval, inside cost caps, tool allowlist, and external-call limits.
# Representative policy set (4 of 19 available policy types) prompt_injection:        # both agents  enforcement: block     # 13-language scanning, severity-scoredpii_detection:           # support agent  enforcement: warn      # 14 categories, hashed at the boundarytool_allowlist:          # both agents  enforcement: block     # send_email requires approval; db_write denied to supportcost_budget:             # org + per-agent  enforcement: block     # per-agent daily cap, org monthly cap, burn-rate alert at 80%

Four enforcement modes are available per policy — monitor, warn, require_approval, block — so the same policy can roll out as monitor-only first and graduate to block after a week of clean signal. See Policies for the full 19-type catalogue.

§ 03

What enforcement costs at runtime

Published, measured figures — reproduce them with the checked-in harnesses (backend/scripts/bench-enforcement.ts, bench-enforce-e2e.ts).

MetricMeasured
In-process policy evaluation — p50 / p95 / p998.4 µs / 10.6 µs / ~21 µs
Evaluation throughput — single core~96,000 passes/sec
Server-side enforce decision, DB-inclusive — p50 / p95 / p992.1 ms / 2.9 ms / 3.9 ms
Semantic tier (model-backed checks)not yet published — never estimated

Methodology, environment, and caveats are on the benchmarks page. The practical takeaway for this deployment: pattern-tier governance adds microseconds in-process and low single-digit milliseconds server-side — small enough to sit in the request path of both agents.

§ 04

When something fires

The operational loop this architecture produces.

A prompt-injection attempt against support-bot is blocked at enforcement time and the trace is marked policy_blocked. The trace streams to the SIEM, where the violation-burst rule (shipped in the Splunk / Sentinel guides) raises an incident in the SOC queue. The analyst follows the incident response workflow: pivot by trace_id, review the span timeline and agent passport, tighten or confirm the policy, and attach the hash-chained audit export to the incident record.

§ 05

Evidence this deployment produces

What you hand an auditor — each artifact maps to a concrete control above.

ArtifactProduced by
Signed compliance report (RSA-SHA256, offline-verifiable)GET /api/v1/compliance/report — 7 frameworks including EU AI Act
Append-only, hash-chained audit log (retention up to 10 years)Every enforcement decision, approval, and policy change
Approval records with human identity + timestampact_with_approval actions on support-bot
Per-article EU AI Act evidence mappingdocs/compliance/eu-ai-act — article-by-article

Full mapping with per-article evidence links: EU AI Act compliance. To reproduce this architecture, start with Getting started and the framework integrations.