Lane

Engineer · AI usage, harness practices and where spend could have gone further.

Demonstration report. This engineer and their usage are synthetic.

This page is for the engineer and their manager to find cheaper defaults and harness fixes. It is never used to rank people.

Period

Summary

FY2027 to date

AI spend

$1,410

139 sessions · $10 each

Savings opportunity

$324

23% of spend, at list price

Practices on target

4 of 7

Focus: rtk coverage, Knowledge MCP use

Cache hit rate

86%

Team 79% · org 82%

FY2027 to date · estimated at list price

$324 of $1,410 spend

Largest saving first

Improve prompt caching$163
Cache hit rate 86% against an 85% target.
Keep stable context at the front of prompts and avoid switching models mid-session, so 85% of input reads from cache.
Right-size models$111
38% of routine spend ran on Opus: code research $135 of $369, documentation $87 of $216, ops $6 of $19, presentation $35 of $79.
Run docs, decks, ops and read-only research on Sonnet instead of Opus.
Keep context lean$36
7% of input tokens were past 100K of context.
Compact or /clear between tasks instead of carrying more than 100K tokens of context.
Route commands through rtk$15
66% of 1,282 Bash calls ran through rtk; 1.8M tokens of command output went into context.
rtk compacts test, build, git and search output before it reaches the model (about 70% smaller).

Compared with Growth & SEO and the organization

Practice	Lane	Team	Org	Target	Recommendation
rtk coverage	66%Needs attention	62%	56%	≥ 80% of Bash calls	Install the rtk hook so test, build, git and search commands return compact output.
Knowledge MCP use 4 findings saved back	29%Needs attention	30%	30%	≥ 40% of sessions	Search the knowledge MCP before re-researching a codebase, and save findings back with remember.
Cache hit rate	86%On target	79%	82%	≥ 85% of input	On target
Context past 100K	7%On target	18%	10%	≤ 10% of input	On target
Opus on routine work	38%Needs attention	58%	44%	≤ 25% of routine spend	Default routine sessions to Sonnet and keep Opus for harness, design and hard debugging work.
Sessions using subagents	49%On target	47%	50%	≥ 30% of sessions	On target
Tool error rate	3.3%On target	3.0%	3.0%	≤ 4% of tool calls	On target

Is the engineer moving toward the targets?

Month	rtk	Knowledge	Cache	Context	Model fit	Subagents	Savings opportunity
Feb 2026	–	–	64%Off target	10%Needs attention	–	19%Needs attention	$5
Mar 2026	–	–	62%Off target	8%On target	62%Off target	46%On target	$17
Apr 2026	–	–	67%Off target	7%On target	62%Off target	28%Needs attention	$21
May 2026	17%Off target	–	70%Needs attention	7%On target	55%Off target	34%On target	$20
Jun 2026	43%Needs attention	13%Off target	71%Needs attention	10%Needs attention	53%Off target	39%On target	$82
Jul 2026	74%Needs attention	27%Needs attention	76%Needs attention	6%On target	40%Needs attention	46%On target	$87
Aug 2026	67%Needs attention	31%Needs attention	84%Needs attention	9%On target	38%Needs attention	47%On target	$22
Sep 2026	75%Needs attention	34%Needs attention	82%Needs attention	9%On target	30%Needs attention	59%On target	$37
Oct 2026	75%Needs attention	35%Needs attention	91%On target	6%On target	27%Needs attention	59%On target	$32

FY2027 to date

By model tier, by month

Routine types (documentation, presentation, ops, code research) rarely need Opus

Cache reads are billed at a fraction of uncached input; a high share is what good caching looks like

Model	Requests	Uncached input	Cache reads	Cache writes	Output	Spend
Opus 5.5	2,800	6.7M	146.2M	9.8M	4.2M	$190
Opus 5	1,910	12.6M	93.4M	6.8M	2.7M	$220
Opus 4.8	1,586	19.9M	72.8M	5.9M	2.6M	$239
Opus 4.6	806	11.8M	30.3M	2.7M	1.1M	$119
Opus 4.5	17	336K	701K	66K	25K	$3
Sonnet 5.5	4,419	9.9M	267M	17.7M	7.1M	$161
Sonnet 5	3,738	27.9M	184.5M	13.6M	5.5M	$273
Sonnet 4.6	1,169	15.9M	48.2M	4.1M	1.7M	$104
Sonnet 4.5	11	189K	395K	37K	16K	$1
Haiku 5.5	9,078	15.7M	483M	31.8M	15.3M	$18
Haiku 4.5	2,970	21.7M	136.2M	10.1M	4.3M	$69
GPT Realtime (meetings)	164	950K	8.2M	582K	263K	$14
Total	28,668	143.4M	1471M	103M	45M	$1,410

Spend and tokens come from LiteLLM gateway logs and imported agent session history, priced at API list rates.
Savings are estimates: routine Opus work repriced at the Sonnet available at the time; uncached input moved to cache reads up to an 85% hit rate; rtk removing 70% of unfiltered command output, which stays in context for about half the session's remaining turns; and 50% of input past 100K context avoided by compacting. Levers overlap, so the total is an upper bound.
rtk and the knowledge MCP are scored from their rollout (rtk May 2026, knowledge MCP Jun 2026).
Generated Oct 20, 2026, 7:46 AM.