⚑
Support ticket triage
SupportCategorize, prioritize (P1-P4), detect churn/security signals, and route every inbound ticket the moment it lands.
The routing recipe
Job typeClassification / routingPolicyFastest that passesConstraintsgroq
routes to
GPT-OSS 20B groq
groq:openai/gpt-oss-20b
90.2
match score
84.6
task fit
75.4
cost
96.4
speed
Why this model from benchmarks & capabilities
- "Classification / routing" leans hardest on instruction; GPT-OSS 20B scores 78/100 there — #18 of 32.
- Strength on this class of work shows up on IFEval, MMLU (zero-shot), where OpenAI (open-weight) models are competitive.
- Cost: ~$0.112/Mtok blended ($0.03 in / $0.14 out). Speed: ~1000 tok/s on Groq LPU.
- Chosen over Llama 3.1 8B Instant for higher task-fit (84.6 vs 75.6) & faster.
| Capability the job needs | Weight | GPT-OSS 20B | Catalog rank |
|---|---|---|---|
| instruction | 0.90 | #18 of 32 | |
| speed | 0.90 | #1 of 32 | |
| knowledge | 0.30 | #21 of 32 |
Relevant benchmarksIFEval MMLU (zero-shot)
EconomicsCost: ~$0.112/Mtok blended ($0.03 in / $0.14 out).
Speed: ~1000 tok/s on Groq LPU. vs runner-upChosen over Llama 3.1 8B Instant for higher task-fit (84.6 vs 75.6) & faster. (Llama 3.1 8B Instant, score 86.3)
Speed: ~1000 tok/s on Groq LPU. vs runner-upChosen over Llama 3.1 8B Instant for higher task-fit (84.6 vs 75.6) & faster. (Llama 3.1 8B Instant, score 86.3)
Example result
Sample input ▾
Ticket: 'Our auditor needs our evidence export TODAY and the download button 500s. We're considering other tools if this isn't fixed.'
category: bug — evidence export (500)
priority: P1
team: Eng (+ Success follow-up)
churn_risk: high
reason: Time-critical audit blocker + explicit switch threat; page Eng and have Success reach out within the hour.
Test it on your own data