Showcase agents / GTM / Outbound
Sales / GTM
GTM / Outbound
What problem? Outbound agents burn budget when every lead hits an expensive model — with no per-lead cost attribution or cache visibility.
Sales reference: enrich company → draft email → CRM upsert → schedule. Stresses cost routing, cache hits, and model-mix policy.
What Inferix observes
Every run dual-writes to LensAI and TraceForge. Switch to this tenant in the console to see live KPIs.
- RouteIQ — model mix and cache hit rate per campaign
- LensAI — $/lead and latency by intent
- DriftWatch — aggressive-prompt quality drift
- TraceForge — enrichment → draft → send waterfall
Tools & models
Real SQLite backends, not mocked HTTP stubs.
- enrich.company
- enrich.person
- crm.upsert_lead
- email.draft
- email.send
- calendar.book
Model routing
- slm-support-v* (FAQ copy)
- general-llm-v* (personalized drafts)
- cache-heavy path
Try it
Start the stack, then run the golden scenario. Traffic appears in the console within seconds.
1. Start stack + agents
cd inferix && ./run-inferix.sh --full --agents
2. Golden scenario
curl -s -X POST http://localhost:9103/scenarios/cold_outbound | jq
Expect HTTP 200 with JSON status and tool steps. Traces appear under this tenant in ~10s.
3. All agents at once
cd inferix && ./scripts/generate-agent-traffic.sh
Expected: JSON with status and tool steps. Then open the tenant console and filter traces by tenant-gtm-labs. In-browser runner stays deferred — curl is the verified path.
Console: /console/overview?tenant_id=tenant-gtm-labs · API traces: GET /v1/traces?tenant_id=tenant-gtm-labs
See all seven agents in the console
Multi-tenant super-dashboard. Filter by tenant, drill into traces and costs.