Skip to content

AI & Agentic Systems

An AI agent that resolves 62% of support tickets

Non-engineers needed to triage field faults across a device fleet. We built the telemetry path and a retrieval-grounded agent over internal runbooks and ticket history.

Client
Hardware and cloud device vendor
Industry
Connected hardware
Disclosure
Anonymised under NDA
Support tickets auto-resolved
62%Support tickets auto-resolved
End-to-end answer at p95
<4 sEnd-to-end answer at p95
Languages, English and Hindi
2Languages, English and Hindi

The challenge

Fleet faults could only be diagnosed by firmware engineers, so support queues grew with every device shipped.

Stack

  • MQTT
  • pgvector
  • RAG
  • Function calling
  • GCP

What we did

  1. 01MQTT field telemetry landed in cloud storage
  2. 02Runbooks and ticket history chunked and indexed in pgvector
  3. 03Function-calling agent grounded in the retrieved runbooks
  4. 04Bilingual answers on one pipeline
Generic reference architecture
fallbackQUERYuser · agentCACHEprompt · semanticEMBEDvectorHYBRID SEARCHbm25 + knnRERANKcross-encoderLLMrouted by tierEVAL · TRACEfaithfulness · cost

A generic representation of the pattern, not the client’s topology.

How you would buy this

Fixed-scope Delivery Sprint

One outcome, one price: a cloud-cost cut, a platform migration, a ClickHouse or IIoT ingestion path, or a production AI-agent pilot.

Compare all engagements →

Fixed fee · 2–6 weeks

Fixed-scope Delivery Sprint

From

$25,000

fixed fee

One outcome, one price: a cloud-cost cut, a platform migration, a ClickHouse or IIoT ingestion path, or a production AI-agent pilot.

  • Written acceptance criteria per milestone
  • Demo at every milestone
  • Source, runbooks and handover included
  • Milestone billing 30 / 40 / 30
Ask about this engagement

More ai & agentic systems work

AI & Agentic SystemsNDA · Consumer AI

An $80K a month inference bill cut to $22K at the same quality

Consumer AI product

Model spend was growing faster than revenue. An audit of the inference path found the waste; routing, caching and budgets removed it.

Lower monthly inference bill
73%Lower monthly inference bill
Per month, down from $80K
$22KPer month, down from $80K
Answer quality after the change
SameAnswer quality after the change

Start with a scoping call.

Thirty minutes with the founder. Bring your architecture diagram, your cloud bill or your plant drawings, and leave with what is realistic — including when the answer is that you do not need us yet.

Mutual NDA before any detail is shared. First response within 24 hours.