Augment Code’s routing guide is the practical item of the week because it treats coding-agent model choice as a task-fit decision.
Published 2026-04-12Source: Augment Code
Why it matters
Agent cost problems often come from using the same expensive model for planning, search, code edits, tests, and summarization. A routing guide gives teams a way to separate those jobs.
Tokenmaxxing read
The practical tokenmaxxing move is to reserve premium context and reasoning for the steps that need it, then route cheaper models through bounded subtasks and verification.
Source takeaway
Use this as the agent-spend takeaway: good routing is less about finding one best model and more about matching model cost to workflow risk.
‘What we’re seeing right now is just rapid escalation in AI token spend’: Accenture tells staff to stop using AI for unnecessary tasks amid surging costs
Leaked internal audio, reported by IT Pro via 404 Media, shows Accenture telling staff to stop burning AI tokens on low-value work like turning PDFs into slide decks, as its agentic-AI lead flags a sharp jump in token spend.
AI cost challenges mount as agent use gets more complex: KPMG
KPMG’s Q2 AI Pulse (204 US leaders at $1B+ firms) finds twice as many companies now running fleets of coordinated agents — up to 18% from 9% — yet only 26% can see in real time what AI at scale actually costs them.
How Ramp is Fuelling AI Spend Management Expansion
Ramp closed a $750M round at a $44B valuation and is launching AI token spend management, procurement agents, and accounting agents on top of $1B+ annualized revenue and 70,000+ customers.
