Objection-handling coach

Use case Β· Enablement

← All use cases
✺

Objection-handling coach

Enablement

Takes a verbatim objection a rep heard on a call and returns a coached, iCompaas-specific response framework (acknowledge β†’ reframe β†’ proof β†’ advance), two ready-to-say variations, the trap to avoid, and the one discovery question that should have prevented it.

The routing recipe
Job typeGeneral chat / assistantPolicyBalanced
routes to
GPT-OSS 20B groq
groq:openai/gpt-oss-20b
87.1
match score
77.7
task fit
100
cost
96.4
speed
Why this model from benchmarks & capabilities
  • "General chat / assistant" leans hardest on instruction; GPT-OSS 20B scores 78/100 there β€” #23 of 40.
  • Strength on this class of work shows up on LMArena Elo, MT-Bench, IFEval, where OpenAI (open-weight) models are competitive.
  • Cost: free tier. Speed: ~1000 tok/s on Groq LPU.
  • Chosen over NVIDIA Nemotron 3 Super 120B-A12B for faster.
Capability the job needsWeightGPT-OSS 20BCatalog rank
instruction0.8078#23 of 40
knowledge0.6070#26 of 40
speed0.6096#1 of 40
Relevant benchmarksLMArena Elo MT-Bench IFEval EconomicsCost: free tier.
Speed: ~1000 tok/s on Groq LPU.
vs runner-upChosen over NVIDIA Nemotron 3 Super 120B-A12B for faster. (NVIDIA Nemotron 3 Super 120B-A12B, score 85.3)
Example result
Sample input β–Ύ
Objection (verbatim, mid-deal, 75-person fintech going for SOC 2 + ISO 27001): "Honestly Vanta is cheaper and everyone uses it β€” why would we pay more for you?"
OBJECTION: "Vanta is cheaper and everyone uses it β€” why pay more for you?" 1. WHAT THEY REALLY MEAN Not really price β€” they're de-risking. "Everyone uses it" = fear of being second-guessed for a non-obvious choice. The real question: "will you actually get us through the audit faster and with less of MY time?" 2. FRAMEWORK β€’ Acknowledge: Vanta's a legit tool β€” fair to put us side by side. β€’ Reframe: The cost that matters isn't the license, it's the engineering hours and the calendar β€” especially running SOC 2 AND ISO 27001 in parallel. β€’ Proof: We connect your stack, auto-collect evidence across BOTH frameworks from one control set, and give you white-glove + a trust center so you stop fielding security questionnaires by hand. β€’ Advance: Put us head-to-head on your actual stack for two weeks β€” let the time-to-evidence decide. 3. SAY IT a) Concise: "Totally fair to compare us. The price difference is a rounding error next to your engineers' hours β€” and you're doing SOC 2 and ISO at once. We map both to one control set and auto-pull the evidence. Want to run us against your real AWS/Okta stack for two weeks and let speed decide?" b) Consultative: "Vanta's a real option, no argument. But 'cheaper' usually means license price β€” the expensive part is the 3 weeks of evidence-chasing per cycle and the security questionnaires landing on your team. Because you're stacking SOC 2 + ISO, the dual-framework evidence reuse and the trust center are where the hours actually disappear. Who on your side feels that pain most β€” should we get them on a 2-week head-to-head?" 4. TRAP Arguing price down or trashing Vanta. You'll win the feature war and lose the deal β€” and you'll have validated that this is a price decision instead of a time/risk decision. 5. PREVENT IT Earlier, you should have asked: "Besides the tool, what's this costing you in engineering hours per audit cycle β€” and who feels that most?" Anchor on hours/risk before price ever comes up, and this objection mostly dissolves.
Test it on your own data
Sign in to continue

LLM Switchboard is private β€” sign in with Authlee to access the control room.

Sign in with Authlee
← Back to home