FINTECH · 9 mo · live · 73% review-time cut

Pre-trade surveillance, MiFID II, in the loop.

A2A network of 4 specialized agents monitoring trade flows against 1,200+ compliance rules in real time.

Used with permission · Anonymized

1.8s
Latency p95
1,247
Rules covered
$0.011
Cost per call
1,420
Hours saved / month

The problem

The broker was hand-reviewing ~38,000 pre-trade alerts per week. Reviewers were missing the long tail. The compliance team wanted machine triage — but not the kind that gets explained to the regulator as "the model decided."

We needed a system that could justify every block in plain language, with citations.Head of Compliance, Fintech, Europe

Our approach

We didn't replace the reviewer — we replaced the triage queue. The system explains its reasoning span-by-span; the reviewer accepts or kicks back.

Three decisions shaped the system:

  1. Typed envelopes between agents. Every agent-to-agent message has a versioned schema. Codegen handles the boilerplate.
  2. Deterministic eval gates. A regression in rule-coverage stops the deploy automatically.
  3. Full audit trail. Trace IDs on every span. A reviewer can replay any decision exactly.

The architecture

02 · Reference architecture

What we actually ship.

Every system we build follows this shape. Client at the edge, tools in a sandbox, traces everywhere, evaluators gating output. No black boxes, no "it works on my machine."

EDGE
Client
web · mobile · API
Gateway
auth · rate-limit · PII redact
ORCHESTRATION
Orchestrator
planner · router · memory
Durable · exactly-once
AGENTS & TOOLS
Retrieval
hybrid · rerank · cite
Tool calls
sandboxed · timeboxed
Evaluator
gates · rubrics · LLM-judge
DATA & TRUST
Vector + BM25
tenant-isolated
Traces / logs
OTel · replayable
Signed output
auditable · rollback

A run, on this system

04 · Run

Watch an agent do the job.

Three real production scenarios, replayed at observed latency. Every box is a span; every span has tokens, cost, and an eval gate. This is what shows up in your traces, not a marketing animation.

POST/api/v1/agent/runTrade desk submits a €4.2M block trade. Agent must reject, approve, or flag in <3s.
trace · compliancespan_id 7c1f…
orchestrator.run0ms
PLANorchestrator.planorchestrator · 80ms · 184 tok · $0.0014
Plan rationale

Pretrade review requires: applicable-rules retrieval, market-data lookup, position-check, and a deterministic evaluator gate.

Subtasks
retrievaltool.market_datatool.position_checkevaluator
0ms/1.82s
LATENCY0msbudget 3.00s
TOKENS0in + out
COST$0.0000budget $0.025
EVAL GATEdeterministic + LLM-judge
APPROVED · 1 flag
Trade clears 11 of 12 rules. Rule 23.2 (book concentration) flagged for desk-head sign-off.
latency2.41scost$0.014tokens1,827evals12/12

Outcomes

0%
Review-time cut
0%
False-positive rate
0,247
Rules covered

They shipped a system that survived our peak weeks. The evals caught two regressions that would have made it to production otherwise.

— VP of Engineering, Fintech, Europe

START

Ship the first system.

Fixed-price discovery in 2 weeks. You leave with an architecture, a working spike, and a build plan.