Growth workspace
Agent team & evals
The DeployOne voice and reasoning agents running Fibe's growth pilot, with their evaluation suite and guardrails.
Active agents
6
4 voice-enabled
Calls handled (30d)
34.5K
↑ 12.8% · pilot estimate
Avg eval pass rate
89.2%
↑ 3.1 pts vs last month
Guardrail flags (30d)
17
↓ 22% after prompt patch
Qualifier
Pre-screens inbound loan interest via voice
Nudge
Reminds warm leads to complete KYC/e-sign
Winback
Re-engages dropped-off applicants
Insight Analyst
Summarises call themes for growth team
Creative Studio
Drafts ad and script variants from signals
Reputation Watch
Clusters app-store and review themes
Eval suite
Automated evals run against golden transcripts
| Eval | Dataset | Pass rate | Last run | Trend | |
|---|---|---|---|---|---|
| Qualifier — eligibility accuracy | 500 cases | 91.2% | 2 hrs ago | ↑ improving | |
| Qualifier — disclosure compliance | 500 cases | 96.8% | 2 hrs ago | → stable | |
| Nudge — tone & consent | 320 cases | 88.0% | 6 hrs ago | ↑ improving | |
| Winback — objection handling | 280 cases | 76.4% | 1 day ago | ↓ regressing | |
| Insight Analyst — summary faithfulness | 400 cases | 93.5% | 1 day ago | ↑ improving |
Eval score trend
Composite weighted score across all suites
Failure-case review
Sample transcripts flagged by evals or guardrails, pending human verdict
"So basically there's no real cap on how much you can borrow..." — agent overstated loan ceiling beyond ₹10L policy.
Agent skipped reading the cooling-off period clause before confirming interest.
Called outside the approved 8am–7pm window due to timezone mismatch.
Guardrail policy
Live rules applied to every voice turn